Embed Size (px)
Citation preview
2008 15th IEEE International Conference on Image Processing
San Diego, California, USA 12 – 15 October 2008
CFP08CIP-PRT 978-1-4244-1765-0
IEEE Catalog Number: ISBN:
(ICIP 2008)
Pages 1-644
Table of ConTenTs
WS-LW: ICIP WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL ORAL SESSION
WS-LW: INCORPORATING SPATIO-TEMPORAL MID-LEVEL FEATURES ......................................1IN A REGION SEGMENTATION ALGORITHM FOR VIDEO SEQUENCESIván González-Díaz, Universidad Carlos III de Madrid, Spain; Kevin McGuinness, Tomasz Adamek, Noel E. O’connor, Dublin City University, Ireland; Fernando Díaz-de-María, Universidad Carlos III de Madrid, Spain
WS-LW: SPATIOTEMPORAL MODELING AND MATCHING OF VIDEO ............................................5SHOTSEric Galmar, Benoit Huet, EURECOM, France
WS-LW: CROWD BEHAVIOURS ANALYSIS IN DYNAMIC VISUAL SCENES ....................................9OF COMPLEX ENVIRONMENTLi-Qun Xu, Arasanathan Anjulan, British Telecommunications PLC, United Kingdom
WS-LW: A PROBABILISTIC MODEL FOR FLOOD DETECTION IN VIDEO .....................................13SEQUENCESPaulo Vinicius Koerich Borges, Queen Mary, University of London, United Kingdom; Joceli Mayer, Federal University of Santa Catarina, Brazil; Ebroul Izquierdo, Queen Mary, University of London, United Kingdom
WS-PW: ICIP WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL POSTER SESSION
WS-PW: A GROUND-TRUTH FOR MOTION-BASED VIDEO-OBJECT ...............................................17SEGMENTATIONFabrizio Tiburzi, Marcos Escudero, Jesús Bescós, José María Martínez, Universidad Autónoma de Madrid, Spain
WS-PW: COMBINED NONLINEAR INVERSE DIFFUSION FILTER AND ...........................................21TRIANGLE METHOD USED FOR NOISE REMOVAL FROM POLYGONAL SHAPESVesna Zeljkovic, Claude Tameze, Robert Vincelette, Delaware State University, United States
WS-PW: THE SPARSE IMAGE REPRESENTATION FOR AUTOMATED ...........................................25IMAGE RETRIEVALPavel Praks, University of Economics, Prague, Czech Republic; Radek Kucera, VSB - Technical University of Ostrava, Czech Republic; Ebroul Izquierdo, Queen Mary University of London, United Kingdom
WS-PW: A COLLABORATIVE APPROACH TO AUTOMATIC RUSHES VIDEO ...............................29SUMMARIZATIONWerner Bailer, JOANNEUM RESEARCH, Austria; Emilie Dumont, EURECOM, France; Slim Essid, Telecom ParisTech, France; Bernard Merialdo, EURECOM, France
WS-PW: DYNAMIC ORGANIZATION OF AUDIOVISUAL DATABASE USING A .............................33USER-DEFINED SIMILARITY MEASURE BASED ON LOW-LEVEL FEATURESJérémy Philippeau, INA/IRIT, France; Jean Carrive, INA, France; Philippe Joly, Julien Pinquier, IRIT, France
WS-PW: EYE DETECTION BASED ON THE POLYNOMIAL HERMITE .............................................37EXPANSIONLicia Capodiferro, Fondazione Ugo Bordoni, Italy; Elio D. Di Claudio, Giovanni Jacovitti, University of Rome, Italy; Federica Mangiatordi, Fondazione Ugo Bordoni, Italy
WS-PW: ESTIMATION AND REPRESENTATION OF ACCUMULATED .............................................41MOTION CHARACTERISTICS FOR SEMANTIC EVENT DETECTIONGeorgios Th. Papadopoulos, Vasileios Mezaris, Ioannis Kompatsiaris, Michael G. Strintzis, Informatics and Telematics Institute, Greece
WS-PW: GRADUAL TRANSITION DETECTION USING COLOR .........................................................45COHERENCE AND OTHER CRITERIA IN A VIDEO SHOT META-SEGMENTATION FRAMEWORKEfthymia Tsamoura, Vasileios Mezaris, Ioannis Kompatsiaris, Informatics and Telematics Institute / Centre for Research and Technology Hellas, Greece
WS-PW: DESCRIBING LOW-LEVEL IMAGE FEATURES USING THE ...............................................49COMM ONTOLOGYMiroslav Vacura, Vojtech Svatek, University of Economics, Prague, Czech Republic; Carsten Saathoff, Thomas Franz, University of Koblenz-Landau, Germany; Raphael Troncy, Centrum voor Wiskunde en Informatica (CWI), Netherlands
WS-PW: USING REGION SEMANTICS AND VISUAL CONTEXT FOR ................................................53SCENE CLASSIFICATIONEvaggelos Spyrou, Phivos Mylonas, Yannis Avrithis, National Technical University of Athens, Greece
WS-PW: IDENTIFYING AND RETRIEVING DISTRESS IMAGES FROM ............................................57ROAD PAVEMENT SURVEYSHenrique Oliveira, Paulo Lobato Correia, Instituto de Telecomunicações, Portugal
WS-PW: HD MOTION ESTIMATION IN A WAVELET PYRAMID IN ...................................................61JPEG2000 CONTEXTClaire Morand, Jenny Benois-Pineau, Jean-Philippe Domenger, University of Bordeaux, France
WS-PW: ON THE ROLE OF STRUCTURE IN PART-BASED OBJECT .................................................65DETECTIONGiuseppe Passino, Ioannis Patras, Ebroul Izquierdo, Queen Mary, University of London, United Kingdom
WS-PW: FAST DIALOGUE INDEXING BASED ON STRUCTURE .........................................................69INFORMATIONSergio Benini, Pierangelo Migliorati, Riccardo Leonardi, Università degli Studi di Brescia, Italy
WS-PW: VIDEO SCENE DETECTION USING DOMINANT SETS ...........................................................73Ufuk Sakarya, TÜBITAK UZAY (The Scientific and Technological Research Council of Turkey, Space Technologies Research Institute), Turkey; Ziya Telatar, Ankara University, Turkey
WS-PW: USING A GAME TO EVALUATE IMAGE RETRIEVAL, .........................................................77ORGANIZATION, AND ANNOTATIONLiam M. Mayron, Oge Marques, Florida Atlantic University, United States
WS-PW: IMAGE RETRIEVAL AND WEB 2.0 -- WHERE CAN WE GO FROM ....................................81HERE?Christian Bauckhage, Tansu Alpcan, Deutsche Telekom Laboratories, Germany; Robert Wetzker, Winfried Umbrath, Technical University Berlin, Germany
WS-PW: MEAN SHIFT CLUSTERING FOR PERSONAL PHOTO ALBUM ..........................................85ORGANIZATIONE. Ardizzone, Marco La Cascia, Universita degli Studi di Palermo, Italy; F. Vella, Consiglio Nazionale delle Ricerche, Italy
WS-PW: WEB VIDEO RETRIEVAL BASED ON THE EARTH MOVER’S ............................................89DISTANCE BY INTEGRATING COLOR, MOTION AND SOUNDKeisuke Takada, Keiji Yanai, University of Electro-Communications, Japan
WS-PW: A MULTIMODAL APPROACH TO MUSIC TRANSCRIPTION ...............................................93Marco Paleari, Benoit Huet, Antony Schutz, Dirk Slock, EURECOM, France
MA-L1: IMAGE AESTHETICS, MOOD AND EMOTION
MA-L1.1: MULTIDIMENSIONAL IMAGE VALUE ASSESSMENT AND RATING ..............................97FOR AUTOMATED ALBUMING AND RETRIEVALAlexander Loui, Mark Wood, Anthony Scalise, John Birkelund, Eastman Kodak Company, United States
MA-L1.2: EMOTIONAL VALENCE CATEGORIZATION USING HOLISTIC ....................................101IMAGE FEATURESVictoria Yanulevskaya, Jan van Gemert, University of Amsterdam, Netherlands; Katharina Roth, Ann-Katrin Herbold, University Clinic of Bonn, Germany; Nicu Sebe, Jan-Mark Geusebroek, University of Amsterdam, Netherlands
MA-L1.3: ALGORITHMIC INFERENCING OF AESTHETICS AND EMOTION ...............................105IN NATURAL IMAGES: AN EXPOSITIONRitendra Datta, Jia Li, James Z. Wang, Pennsylvania State University, United States
MA-L1.4: ANALYSIS OF HUMAN ATTRACTIVENESS USING MANIFOLD .....................................109KERNEL REGRESSIONBradley Davis, Svetlana Lazebnik, University of North Carolina at Chapel Hill, United States
MA-L1.5: AN ANALYSIS OF THE RELATIONSHIP BETWEEN PAINTERS .....................................113BASED ON THEIR WORKMarco Bressan, Claudio Cifarelli, Florent Perronnin, Xerox, France
MA-L1.6: A SURVEY ON EMOTIONAL SEMANTIC IMAGE RETRIEVAL........................................117Weining Wang, Qianhua He, South China University of Technology, China
MA-L1.7: IMAGE HARMONY FOR CONSUMER IMAGES ....................................................................121Elena Fedorovskaya, Carman Neustaedter, Wei Hao, Eastman Kodak Company, United States
MA-L2: IMAGE CODING I
MA-L2.1: INTRA PREDICTION USING TEMPLATE MATCHING WITH ..........................................125ADAPTIVE ILLUMINATION COMPENSATIONYunfei Zheng, Thomson / West Virginia University, United States; Peng Yin, Oscar Divorra Escoda, Thomson, United States; Xin Li, West Virginia University, United States; Cristina Gomila, Thomson, United States
MA-L2.2: IMAGE COMPRESSION WITH GENERALIZED LIFTING AND .......................................129PARTIAL KNOWLEDGE OF THE SIGNAL PDFJulio Rolon, Philippe Salembier, Xavier Alameda, Technical University of Catalonia, Spain
MA-L2.3: IMAGE COMPRESSION USING HIGH ORDER WEDGELETS IN A .................................133GENERALIZED QUAD-TREEAzar Rahimi, Ashraf A.Kassim, National University of Singapore, Singapore
MA-L2.4: INTRA PREDICTION VERSUS WAVELETS AND LAPPED ................................................137TRANSFORMS IN AN H.264/AVC CODERRafael G. de Oliveira, Ricardo L. de Queiroz, Universidade de Brasília, Brazil
MA-L2.5: MULTISCALE RECURRENT PATTERN IMAGE CODING WITH A .................................141FLEXIBLE PARTITION SCHEMENelson Francisco, Instituto de Telecomunicações/UTAD, Portugal; Nuno Rodrigues, Instituto de Telecomunicações/ESTG IPLeiria, Portugal; Eduardo Silva, Univ. Fed. Rio Janeiro, Brazil; Murilo Carvalho, Univ. Fed. Fluminense, Brazil; Sérgio Faria, Instituto de Telecomunicações/ESTG IPLeiria, Portugal; Vitor Silva, Instituto de Telecomunicações/Univ. Coimbra, Portugal; Manuel Reis, Univ. Trás-os-Montes Alto Douro, Portugal
MA-L2.6: DIRECTION-ADAPTIVE PARTITIONED BLOCK TRANSFORM FOR ............................145IMAGE CODINGChuo-Ling Chang, Bernd Girod, Stanford University, United States
MA-L2.7: SPARSE ORTHONORMAL TRANSFORMS FOR IMAGE ....................................................149COMPRESSIONOsman G. Sezer, Georgia Institute of Technology, United States; Oztan Harmanci, Onur Guleryuz, DoCoMo USA Labs, United States
MA-L2.8: MODULO-PCM BASED ENCODING FOR HIGH SPEED VIDEO .......................................153CAMERASJosep Prades-Nebot, Antoni Roca, Universidad Politécnica de Valencia, Spain; Edward J. Delp, Purdue University, United States
MA-L3: IMAGE/VIDEO RETRIEVAL I
MA-L3.1: RANK CORRELATION AS ILLUMINATION INVARIANT .................................................157DESCRIPTOR FOR COLOR OBJECT RECOGNITIONDamien Muselet, Alain Trémeau, LIGIV, Université Jean Monnet, France
MA-L3.2: CROSS-DOMAIN LEARNING METHODS FOR HIGH-LEVEL ...........................................161VISUAL CONCEPT CLASSIFICATIONWei Jiang, Eric Zavesky, Shih-Fu Chang, Columbia University, United States; Alexander Loui, Kodak Research, United States
MA-L3.3: WAVELET-BASED COLOR TEXTURE RETRIEVAL USING THE ....................................165INDEPENDENT COMPONENT COLOR SPACEYe Mei, Dimitrios Androutsos, Ryerson University, Canada
MA-L3.4: MULTISCALE COLOUR TEXTURE RETRIEVAL USING THE .........................................169GEODESIC DISTANCE BETWEEN MULTIVARIATE GENERALIZED GAUSSIAN MODELSGeert Verdoolaege, Steve De Backer, Paul Scheunders, University of Antwerp, Belgium
MA-L3.5: INEQUIVALENT MANIFOLD RANKING FOR CONTENT-BASED ...................................173IMAGE RETRIEVALFan Wang, Guihua Er, Qionghai Dai, Tsinghua University, China
MA-L3.6: ROBUST MULTI-DIMENSIONAL NULL SPACE ...................................................................177REPRESENTATION FOR IMAGE RETRIEVAL AND CLASSIFICATIONXu Chen, Dan Schonfeld, Ashfaq Khokhar, University of Illinois at Chicago, United States
MA-L3.7: FAST ADAPTIVE MAHALANOBIS DISTANCE-BASED SEARCH AND ...........................181RETRIEVAL IN IMAGE DATABASESSharadh Ramaswamy, Kenneth Rose, Signal Compression Lab, United States
MA-L3.8: SALIENT REGION DETECTION AND FEATURE EXTRACTION IN ...............................1853D VISUAL DATAMing Dong, Yanhua Chen, Wayne State University, United States
MA-L4: STEREO AND 3D I
MA-L4.1: USING SOLAR SHADOW TRAJECTORIES FOR CAMERA ...............................................189CALIBRATIONImran Junejo, INRIA, France; Hassan Foroosh, University of Central Florida, United States
MA-L4.2: USING POINT CORRESPONDENCES WITHOUT PROJECTIVE ......................................193DEFORMATION FOR MULTI-VIEW STEREO RECONSTRUCTIONAdrien Auclair, Nicole Vincent, Université Paris-Descartes, France; Laurent D. Cohen, Université Paris-Dauphine, France
MA-L4.3: GLOBALLY OPTIMAL SOLUTION TO EXPLOIT RIGIDITY ............................................197WHEN RECOVERING STRUCTURE FROM MOTION UNDER OCCLUSIONPedro Aguiar, João Xavier, Marko Stosic, Institute for Systems and Robotics, Portugal
MA-L4.4: A NEW SYMMETRIC SHAPE FROM SHADING ALGORITHM .........................................201WITH AN APPLICATION TO 3-D FACE RECONSTRUCTIONAbdelrehim Ahmed, Aly Farag, Thomas Starr, University of Louisville, United States
MA-L4.5: 3D RECONSTRUCTION WITH UNCALIBRATED CAMERAS USING ..............................205THE SIX-LINE CONIC VARIETYPablo Carballeira, José I. Ronda, Universidad Politécnica de Madrid, Spain; Antonio Valdés, Univ. Complutense de Madrid, Spain
MA-L4.6: MULTIPLE IMAGE DISPARITY CORRECTION FOR 3-D SCENE ....................................209REPRESENTATIONMatthew Grum, Adrian Bors, University of York, United Kingdom
MA-L4.7: SHAPE FROM INCONSISTENT SILHOUETTE FOR FREE ................................................213VIEWPOINT VIDEOJose-Luis Landabaso, Leonardo Lizcano, Telefonica R&D, Spain; Montse Pardàs, Technical University of Catalunya, Spain
MA-L4.8: RATE-EFFICIENT VISUAL CORRESPONDENCES USING ................................................217RANDOM PROJECTIONSChuohao Yeo, Parvez Ahammad, Kannan Ramchandran, University of California, Berkeley, United States
MA-L5: MOTION DETECTION AND ESTIMATION I
MA-L5.1: COMPRESSED SENSING FOR MULTI-VIEW TRACKING AND .......................................2213-D VOXEL RECONSTRUCTIONDikpal Reddy, Aswin Sankaranarayanan, University of Maryland, United States; Volkan Cevher, Rice University, United States; Rama Chellappa, University of Maryland, United States
MA-L5.2: ROBUST MOTION DETECTION BY FUSION OF 6D FEATURE ........................................225SPACE DECOMPOSITIONSStephen Reilly, Fatih Kurugollu, Paul Miller, Institute of Electronics, Communications and Information Technology, Queen’s University Belfast, United Kingdom
MA-L5.3: MOTION DETECTION WITH AN UNSTABLE CAMERA .....................................................229Pierre-Marc Jodoin, Université de Sherbrooke, Canada; Janusz Konrad, Venkatesh Saligrama, Boston University, United States; Vincent Gaboury, Université de Sherbrooke, Canada
MA-L5.4: LINEAR EGO-MOTION RECOVERY ALGORITHM BASED ON .......................................233QUASI-PARALLAXChuanxin Hu, Loong Fah Cheong, National University of Singapore, Singapore
MA-L5.5: MULTIPLE CUE ADAPTIVE TRACKING OF DEFORMABLE ...........................................237OBJECTS WITH PARTICLE FILTERAlessio Dore, Andrea Beoldo, Carlo Regazzoni, University of Genova, Italy
MA-L5.6: TRACKING THROUGH CHANGES IN SCALE .......................................................................241Shawn Lankton, James Malcolm, Georgia Institute of Technology, United States; Arie Nakhmani, Technion - Israel Institute of Technology, Israel; Allen Tannenbaum, Georgia Institute of Technology, United States
MA-L5.7: EKF POSE ESTIMATION: HOW MANY FILTERS AND CAMERAS .................................245TO USE?Mohammad Ehab Ragab, Kin Hong Wong, Jun Zhou Chen, Michael Ming-Yuen Chang, Chinese University of Hong Kong, Hong Kong SAR of China
MA-L5.8: MPEG4 PERFORMANCE-DRIVEN AVATAR VIA ROBUST FACIAL ...............................249MOTION TRACKINGHao Tang, Thomas Huang, University of Illinois at Urbana-Champaign, United States
MA-PA: BIOMETRICS I
MA-PA.1: FEATURE-LEVEL FUSION OF PALMPRINT AND PALM VEIN FOR .............................253PERSON IDENTIFICATION BASED ON A “JUNCTION POINT” REPRESENTATIONJian-Gang Wang, Wei-Yun Yau, Andy Suwandy, Institute for Infocomm Research, Singapore
MA-PA.2: COMPARISON OF EYELID AND EYELASH DETECTION ................................................257ALGORITHMS FOR PERFORMANCE IMPROVEMENT OF IRIS RECOGNITIONTae-Hong Min, Rae-Hong Park, Sogang University, Republic of Korea
MA-PA.3: ENHANCED USABILITY OF IRIS RECOGNITION VIA EFFICIENT ...............................261USER INTERFACE AND IRIS IMAGE RESTORATIONZhaofeng He, Zhenan Sun, Tieniu Tan, Xianchao Qiu, Institute of Automation, Chinese Academy of Sciences, China
MA-PA.4: ROBUST EYELID, EYELASH AND SHADOW LOCALIZATION FOR .............................265IRIS RECOGNITIONZhaofeng He, Tieniu Tan, Zhenan Sun, Xianchao Qiu, Institute of Automation, Chinese Academy of Sciences, China
MA-PA.5: A NEW CLASS OF IMAGE REGISTRATION FOR GUARANTEEING .............................269SECURE DATA MANAGEMENTIzumi Ito, Hitoshi Kiya, Tokyo Metropolitan University, Japan
MA-PA.6: RANDOMIZED RADON SIGNATURE FOR FACE BIOMETRIC .......................................273VERIFICATIONMohammad A. Dabbah, Satnam S. Dlay, Wai L. Woo, University of Newcastle, United Kingdom
MA-PA.7: IRIS RECOGNITION PERFORMANCE ENHANCEMENT USING ....................................277WEIGHTED MAJORITY VOTINGSheikh Ziauddin, Matthew Dailey, Asian Institute of Technology, Thailand
MA-PA.8: MULTISPECTRAL PALM IMAGE FUSION FOR ACCURATE ..........................................281CONTACT-FREE PALMPRINT RECOGNITIONYing Hao, Zhenan Sun, Tieniu Tan, Chao Ren, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
MA-PA.9: PALMPRINT IMAGE SYNTHESIS: A PRELIMINARY STUDY ..........................................285Zhuoshi Wei, Yufei Han, Zhenan Sun, Tieniu Tan, Institute of Automation, Chinese Academy of Sciences, China
MA-PA.10: EAR RECOGNITION USING A NEW LOCAL MATCHING ..............................................289APPROACHYimo Guo, Zhengguang Xu, University of Science and Technology Beijing, China
MA-PB: STEREO AND 3D II
MA-PB.1: REDUCING AMBIGUITY IN FEATURE POINT MATCHING BY ......................................293PRESERVING LOCAL GEOMETRIC CONSISTENCYOuk Choi, In So Kweon, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
MA-PB.2: HOMOGRAPHY-BASED PLANE IDENTIFICATION AND ..................................................297MATCHINGAmirhasan Amintabar, Boubakeur Boufama, University of Windsor, Canada
MA-PB.3: EFFICIENT BP STEREO WITH AUTOMATIC PARAMETER ............................................301ESTIMATIONShafik Huq, Andreas Koschan, Besma Abidi, Mongi Abidi, University of Tennessee, United States
MA-PB.4: A ROBOT-BASED 3D BODY SCANNING SYSTEM USING .................................................305PASSIVE STEREO VISIONKazuyuki Miyazawa, Takafumi Aoki, Tohoku University, Japan
MA-PB.5: MIRROR-ADAPTED MATCHING OF CATADIOPTRIC IMAGES .....................................309Samia Ainouz, Olivier Morel, Nicolas Walter, David Fofi, Laboratoire d’Electronique, d’Informatique et Image, France
MA-PB.6: SCALABLE STEREO MATCHING WITH LOCALLY ADAPTIVE ....................................313POLYGON APPROXIMATIONKe Zhang, Jiangbo Lu, University of Leuven and IMEC, Belgium; Gauthier Lafruit, IMEC, Belgium
MA-PB.7: UNCALIBRATED VIEW SYNTHESIS FROM RELATIVE AFFINE ...................................317STRUCTURE BASED ON PLANES PARALLELISMStefano Tebaldini, Marco Marcon, Augusto Sarti, Stefano Tubaro, Politecnico di Milano, Italy
MA-PC: SUPER-RESOLUTION
MA-PC.1: SUPER-RESOLUTION OF VIDEO USING KEY FRAMES AND .........................................321MOTION ESTIMATIONFernanda Brandi, Ricardo L. de Queiroz, Universidade de Brasilia, Brazil; Debargha Mukherjee, Hewlett-Packard Laboratories, Brazil
MA-PC.2: CONSISTENT AND REGULARIZED MAGNIFICATION OF IMAGES ..............................325Aurélien Bourquard, Philippe Thévenaz, Katarina Balac, Michael Unser, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
MA-PC.3: A SINGLE IMAGE BASED BLIND SUPER-RESOLUTION ..................................................329APPROACHWei Zhang, Wai-Kuen Cham, Chinese University of Hong Kong, Hong Kong SAR of China
MA-PC.4: UNIVERSAL HMT BASED SUPER RESOLUTION FOR REMOTE ...................................333SENSING IMAGESFeng Li, Xiuping Jia, Donald Fraser, University of New South Wales at Australian Defence Force Academy, Australia
MA-PC.5: USING BOUNDED-INFLUENCE M-ESTIMATORS IN .........................................................337MULTI-FRAME SUPER-RESOLUTION RECONSTRUCTION: A COMPARATIVE STUDYNoha El-Yamany, Panos Papamichalis, Southern Methodist University, United States
MA-PC.6: TOEPLITZ-BASED ITERATIVE IMAGE FUSION SCHEME FOR ....................................341MRIKrzysztof Malczewski, Ryszard Stasinski, Poznan University of Technology, Poland
MA-PC.7: SUPER-RESOLUTION MOSAICKING OF UAV SURVEILLANCE ....................................345VIDEOYi Wang, Ronald Fevig, Richard R. Schultz, University of North Dakota, United States
MA-PC.8: FAST VIDEO SUPER-RESOLUTION VIA CLASSIFICATION .............................................349Karen Simonyan, Sergey Grishin, Moscow State University, Russian Federation; Dmitriy Vatolin, Dmitriy Popov, YUVsoft, Russian Federation
MA-PC.9: FACE HALLUCINATION USING OLPP AND KERNEL RIDGE ........................................353REGRESSIONB.G.Vijay Kumar, R Aravind, Indian Institute of Technology, Madras, India
MA-PC.10: THREE-TIERED NETWORK MODEL FOR IMAGE ..........................................................357HALLUCINATIONLin Ma, Harbin Institute of Technology, China; Yonghua Zhang, Yan Lu, Feng Wu, Microsoft Research Asia, China; Debin Zhao, Harbin Institute of Technology, China
MA-PD: IMAGE QUALITY ASSESSMENT I
MA-PD.1: PREDICTION OF PREFERRED CLEARTYPE FILTERS USING .......................................361THE S-CIELAB METRICJiajing Xu, Joyce Farrell, Stanford University, United States; Tanya Matskewich, Microsoft, United States; Brian A. Wandell, Stanford University, United States
MA-PD.2: IMPACT OF SUBJECTIVE DATASET ON THE PERFORMANCE OF ..............................365IMAGE QUALITY METRICSSylvain Tourancheau, Florent Autrusseau, IRCCyN, France; Parvez Sazzad, Yuukou Horita, University of Toyama, Japan
MA-PD.3: A NO-REFERENCE PERCEPTUAL IMAGE SHARPNESS METRIC .................................369BASED ON SALIENCY-WEIGHTED FOVEAL POOLINGNabil Sadaka, Lina Karam, Rony Ferzli, Glen Abousleman, Arizona State University, United States
MA-PD.4: PARETO OPTIMAL WEIGHTING OF STRUCTURAL ........................................................373IMPAIRMENTS FOR WIRELESS IMAGING QUALITY ASSESSMENTUlrich Engelke, Hans-Jürgen Zepernick, Blekinge Institute of Technology, Sweden
MA-PD.5: DISCRETE WAVELET TRANSFORM-BASED STRUCTURAL ..........................................377SIMILARITY FOR IMAGE QUALITY ASSESSMENTChun-Ling Yang, Wen-Rui Gao, South China University of Technology, China; Lai-Man Po, City University of Hong Kong, China
MA-PD.6: A PSYCHOVISUAL IMAGE QUALITY METRIC BASED ON .............................................381MULTI-SCALE STRUCTURE SIMILARITYMin Zhang, Xuanqin Mou, Xi’an Jiaotong University, China
MA-PD.7: NR OBJECTIVE CONTINUOUS VIDEO QUALITY ASSESSMENT ...................................385MODEL BASED ON FRAME QUALITY MEASUREYoshikazu Kawayoke, Yuukou Horita, University of Toyama, Japan
MA-PD.8: USING DISPARITY FOR QUALITY ASSESSMENT OF .......................................................389STEREOSCOPIC IMAGESAlexandre Benoit, Patrick Le Callet, IRCCYN Université de Nantes, France; Patrizio Campisi, Università degli Studi di Roma “Roma Tre”, Italy; Romain Cousseau, IRCCYN Université de Nantes, France
MA-PD.9: SEGMENTATION-BASED PERCEPTUAL IMAGE QUALITY ...........................................393ASSESSMENT (SPIQA)Bernard Ghanem, Esther Resendiz, Narendra Ahuja, University of Illinois at Urbana-Champaign, United States
MA-PD.10: IMAGE CLASSIFICATION BASED ON FOCUS....................................................................397Mehul Patel, Jeffrey Rodriguez, Arthur Gmitro, University of Arizona, United States
MA-PD.11: AN IMPROVED PERCEPTION-BASED NO-REFERENCE ................................................401OBJECTIVE IMAGE SHARPNESS METRIC USING ITERATIVE EDGE REFINEMENTSrenivas Varadarajan, Lina Karam, Arizona State University, United States
MA-PD.12: MEASURING MULTIMEDIA QUALITY IN MOBILE NETWORKS ................................405WITH AN OBJECTIVE PARAMETRIC MODELJörgen Gustafsson, Gunnar Heikkilä, Martin Pettersson, Ericsson AB, Sweden
MA-PE: SECURITY AND AUTHENTICATION I
MA-PE.1: DESYNCHRONIZED IMAGE FINGERPRINT FOR LARGE SCALE .................................409DISTRIBUTIONZhongxuan Liu, Shiguo Lian, Yuan Dong, Haila Wang, France Telecom R&D Beijing, China
MA-PE.2: GEOMETRICALLY INVARIANT WATERMARKING USING AFFINE ............................413COVARIANT REGIONSCheng Deng, Xinbo Gao, Xidian University, China; Dacheng Tao, Hong Kong Polytechnic University, Hong Kong SAR of China; Xuelong Li, University of London, United Kingdom
MA-PE.3: A WAVELET-BASED WATERMARKING SCHEME USING DOUBLE .............................417WAVELET TREE ENERGY MODULATIONMin-Jen Tsai, Ching-Ting Lin, Jung Liu, National Chiao Tung University, Taiwan
MA-PE.4: AN ADAPTIVE QIM- AND SVD-BASED DIGITAL IMAGE .................................................421WATERMARKING SCHEME IN THE WAVELET DOMAINXiaojun Qi, Stephen Bialkowski, Gary Brimley, Utah State University, United States
MA-PE.5: ROBUST WATERMARK DETECTION AGAINST D-A/A-D ................................................425CONVERSION FOR DIGITAL CINEMA USING LOCAL AUTO-CORRELATION FUNCTIONMin-Jeong Lee, Kyung-Su Kim, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea; Hae-Yeoun Lee, Kumoh National Institute of Technology, Republic of Korea; Tae-Woo Oh, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea; Young-Ho Suh, Electronics and Telecommunications Research Institute, Republic of Korea; Heung-Kyu Lee, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
MA-PE.6: CONTOURLET BASED IMAGE WATERMARKING USING ..............................................429OPTIMUM DETECTOR IN THE NOISY ENVIRONMENTSayed Mohammad Ebrahim Sahraeian, Mohammad Ali Akhaee, Amir Hejazi, Farokh Marvasti, Sharif University of Technology, Iran
MA-PE.7: IMPROVED QUANTIZATION INDEX MODULATION ........................................................433WATERMARKING ROBUST AGAINST AMPLITUDE SCALING AND CONSTANT CHANGE DISTORTIONSXinshan Zhu, Yangzhou University, China; Zhi Tang, Peking University, China
MA-PE.8: ON THE SECURITY OF SINGULAR VALUE BASED ...........................................................437WATERMARKINGChangzhen Xiong, North China University of Technology, China; Rabab K. Ward, University of British Columbia, Canada; Junyi Xu, Shandong University of Science and Technology, China
MA-PE.9: PRINCIPAL COMPONENT ANALYSIS OF SPECTRAL ......................................................441COEFFICIENTS FOR MESH WATERMARKINGMing Luo, Adrian Bors, University of York, United Kingdom
MA-PE.10: TREE ENERGY DIFFERENTIATION (TED) BASED WAVELET .....................................445WATERMARKING FOR DIGITAL IMAGESMin-Jen Tsai, Bai-Jiun Chen, National Chiao Tung University, Taiwan
MA-PE.11: ADAPTIVE SPREAD-TRANSFORM DITHER MODULATION .........................................449USING AN IMPROVED LUMINANCE-MASKED THRESHOLDDong Yu, Lihong Ma, South China University of Technology, China; Guoxi Wang, Guangdong Telecom, China; Hanqing Lu, Chinese Academy of Sciences, China
MA-PE.12: REVERSIBLE WATERMARKING BASED ON PMO OF TRIPLETS ................................453Shaowei Weng, Yao Zhao, Beijing Jiaotong University, China; Jeng-Shyang Pan, Kaohsiung University of Applied Sciences, Taiwan; Rongrong Ni, Beijing Jiaotong University, China
MA-PF: COLOR AND MULTISPECTRAL PROCESSING
MA-PF.1: REALISTIC COLORIZATION VIA THE STRUCTURE TENSOR .......................................457Mark Drew, Simon Fraser University, Canada; Graham Finlayson, University of East Anglia, United Kingdom
MA-PF.2: A QUATERNION PHASE-ONLY CORRELATION ALGORITHM FOR ............................461COLOR IMAGESWei Feng, Bo Hu, Cheng Yang, Fudan University, China
MA-PF.3: HALLUCINATING FACES FROM THERMAL INFRARED IMAGES ................................465Jun Li, Pengwei Hao, Queen Mary, University of London, United Kingdom; Chao Zhang, Mingsong Dou, Peking University, China
MA-PF.4: MULTI-SOURCE COLOR TRANSFER FOR NATURAL IMAGES ......................................469Yao Xiang, Beiji Zou, Central South University, China; Hui Wang, University of Alberta, Canada; Hong Li, Zheng Xie, Central South University, China
MA-PF.5: SPATIO-SPECTRAL RECONSTRUCTION OF THE ..............................................................473MULTISPECTRAL DATACUBE USING SPARSE RECOVERYManu Parmar, Steven Lansel, Brian A. Wandell, Stanford University, United States
MA-PF.6: DICHROMATIC LEVEL-LINES .................................................................................................477Michèle Gouiffès, Bertrand Zavidovique, IEF CNRS UMR 8622 Université d’Orsay, France
MA-PF.7: A SECOND GENERATION VISUAL SECRET SHARING SCHEME ..................................481FOR COLOR IMAGESMohsen Heidarinejad, Konstantinos N. Plataniotis, University of Toronto, Canada
MA-PF.8: AUTOMATIC WHITE BALANCE BASED ON ADAPTIVE FEATURE ..............................485SELECTION WITH STANDARD ILLUMINANTSSujung Kim, Wook-Joong Kim, Seong-Dae Kim, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
MA-PF.9: REFLECTANCE SPECTRA MODELING METHODS ............................................................489Michael Vrhel, Artifex Software, Inc., United States; H. Joel Trussell, North Carolina State University, United States
MA-PF.10: AN AUTOMATIC METHOD TO LEARN AND TRANSFER THE ......................................493PHOTOMETRIC APPEARANCE OF PARTIALLY OVERLAPPING IMAGESMarco Zuliani, Mayachitra, Inc., United States; Luca Bertelli, B. S. Manjunath, University of California, Santa Barbara, United States
MA-PF.11: MULTIRESOLUTIONAL REGULARIZATION OF LOCAL LINEAR ..............................497REGRESSION OVER ADAPTIVE NEIGHBORHOODS FOR COLOR MANAGEMENTNasiha Hrustemovic, Maya Gupta, University of Washington, United States
MA-PG: RESTORATION I
MA-PG.1: ROBUST IMAGE RESTORATION FOR ROTARY MOTION ..............................................501DEGRADATIONS AND THE MOTION PARAMETER IDENTIFICATIONZheng Yuan, Jianxun Li, Shanghai Jiao Tong University, China; Zhengfu Zhu, Optical Signature of Targets and Environments Key Laboratory, China
MA-PG.2: REDUCING BOUNDARY ARTIFACTS IN IMAGE ...............................................................505DECONVOLUTIONRenting Liu, Jiaya Jia, Chinese University of Hong Kong, Hong Kong SAR of China
MA-PG.3: STATE-SPACE MODEL IDENTIFICATION AND KALMAN ..............................................509FILTERING FOR IMAGE SEQUENCE RESTORATIONXin Lu, Kiyoshi Nishiyama, Iwate University, Japan
MA-PG.4: EFFICIENT IMAGE RESTORATION WITH THE .................................................................513HUBER-MARKOV PRIOR MODELStéphane Pelletier, Jeremy Cooperstock, McGill University, Canada
MA-PG.5: HIGH-S/N IMAGING OF A MOVING OBJECT USING A ....................................................517HIGH-FRAME-RATE CAMERATakashi Komuro, Yoshihiro Watanabe, Masatoshi Ishikawa, University of Tokyo, Japan; Tadakuni Narabu, Sony Corporation, Japan
MA-PG.6: ADAPTIVE BLOCK-BASED APPROACH TO IMAGE STABILIZATION .........................521Marius Tico, Nokia Research Center, Finland
MA-PG.7: LONGITUDINAL ABERRATIONS CAUSED BY OPTICAL FILTERS ..............................525AND THEIR COMPENSATION IN MULTISPECTRAL IMAGINGJohannes Brauers, Til Aach, RWTH Aachen University, Germany
MA-PG.8: A NONINTRUSIVE METHOD FOR GENERATING ALL-FOCUSED ................................529PROJECTIONHanhoon Park, Byung-Kuk Seo, Jong-Il Park, Hanyang University, Republic of Korea
MA-PG.9: AN OBJECT INPAINTING ALGORITHM FOR MULTI-VIEW ..........................................533VIDEO SEQUENCESSoon-Young Lee, Jun-Hee Heu, Seoul National University, Republic of Korea; Chang-Su Kim, Korea University, Republic of Korea; Sang-Uk Lee, Seoul National University, Republic of Korea
MA-PH: ENHANCEMENT AND DENOISING I
MA-PH.1: A PERCEPTUALLY ADAPTIVE APPROACH TO IMAGE DENOISING ..........................537USING ANISOTROPIC NON-LOCAL MEANSAlexander Wong, Paul Fieguth, David. A Clausi, University of Waterloo, Canada
MA-PH.2: RECOVERING WAVELET RELATIONS USING SVM FOR IMAGE ................................541DENOISINGValero Laparra, Juan Gutierrez, Gustavo Camps-Valls, Jesus Malo, Universitat de Valencia, Spain
MA-PH.3: A POST-COMPENSATION SCHEME FOR NONLOCAL MEANS ......................................545FILTER BASED IMAGE RESTORATIONHao Xu, University of Science and Technology of China, China; Jizheng Xu, Feng Wu, Microsoft Research Asia, China
MA-PH.4: SPHERICAL WIENER FILTER ..................................................................................................549Raman Arora, University of Wisconsin-Madison, United States; Harish Parthasarathy, Netaji Subhas Institute of Technology, India
MA-PH.5: ULTRASOUND IMAGING LV TRACKING WITH ADAPTIVE ..........................................553WINDOW SIZE AND AUTOMATIC HYPER-PARAMETER ESTIMATIONJacinto Nascimento, João Sanches, Instituto de Sistemas e Robótica, Portugal
MA-PH.6: A LOW-COMPLEXITY, MOTION-ROBUST, .........................................................................557SPATIO-TEMPORALLY ADAPTIVE VIDEO DE-NOISER WITH IN-LOOP NOISE ESTIMATIONChirag Jain, Sriram Sethuraman, Ittiam Systems (Pvt.) Ltd., India
MA-PH.7: NOISE IN HIGH DYNAMIC RANGE IMAGING .....................................................................561Andre Bell, Claude Seiler, Jens Kaftan, Til Aach, RWTH Aachen University, Germany
MA-PH.8: IMAGE DENOISING USING MIXTURES OF GAUSSIAN SCALE .....................................565MIXTURESJose A. Guerrero-Colón, Universidad de Granada, Spain; Eero P. Simoncelli, Center for Neural Science and Courant Institute of Mathematical Sciences, United States; Javier Portilla, Consejo Superior de Investigaciones Científicas, Spain
MA-PH.9: PERCEPTUAL SOFT THRESHOLDING USING THE ..........................................................569STRUCTURAL SIMILARITY INDEXSumohana Channappayya, Alan Bovik, Robert Heath Jr., University of Texas at Austin, United States
MA-PH.10: IMAGE RESTORATION USING A KNN-VARIANT OF THE ............................................573MEAN-SHIFTCesario Vincenzo Angelino, Eric Debreuve, Michel Barlaud, Université de Nice-Sophia Antipolis/CNRS, France
MA-PH.11: INCORPORATING KNOWN FEATURES INTO A TOTAL ...............................................577VARIATION DICTIONARY MODEL FOR SOURCE SEPARATIONTieyong Zeng, l’École normale supérieure de Cachan, France
MA-PH.12: SPATIALLY VARYING WEIGHTED HSI DIFFUSION FOR .............................................581COLOR IMAGE DENOISINGLei He, Armstrong Atlantic State University, United States
MA-PI: IMAGE SEGMENTATION I
MA-PI.1: EFFECT OF GRAY-LEVEL RE-QUANTIZATION ON ...........................................................585CO-OCCURRENCE BASED TEXTURE ANALYSISMehul Patel, Jeffrey Rodriguez, Arthur Gmitro, University of Arizona, United States
MA-PI.2: IMAGE SEGMENTATION USING HISTOGRAM SPECIFICATION ...................................589Gabriel Thomas, University of Manitoba, Canada
MA-PI.3: INTEGRATING REGION GROWING AND CLASSIFICATION FOR .................................593SEGMENTATION AND MATTINGMiti Ruchanurucks, Kasetsart University, Thailand; Koichi Ogawara, Kyushu University, Japan; Katsushi Ikeuchi, University of Tokyo, Japan
MA-PI.4: THE PATH ASSIGNED MEAN SHIFT ALGORITHM: A NEW FAST .................................597MEAN SHIFT IMPLEMENTATION FOR COLOUR IMAGE SEGMENTATIONAkash Pooransingh, Cathy-Ann Radix, University of the West Indies, Trinidad and Tobago; Anil Kokaram, Trinity College Dublin, Ireland
MA-PI.5: LOCAL ADAPTIVE NONLINEAR DIFFUSION ........................................................................601Antonio Pinheiro, Universidade da Beira Interior, Portugal
MA-PI.6: SKIN DETECTION ALGORITHM BASED ON DISCRETE COSINE ...................................605TRANSFORM AND GENERALIZED GAUSSIAN DENSITYSanaa Ghouzali, Sheila Hemami, Cornell University, Morocco; Mohammed Rziza, Driss Aboutajdine, Med V University, Morocco; El Mustapha Mouaddib, Picardie Jules Verne University, France
MA-PI.7: SUPPORTING RANGE AND SEGMENT-BASED HYSTERESIS ..........................................609THRESHOLDING IN EDGE DETECTIONLu Wang, Suya You, Ulrich Neumann, University of Southern California, United States
MA-PI.8: EDGE DETECTION BY SELECTION OF PIECES OF LEVEL .............................................613LINESEnric Meinhardt-Llopis, Universitat Pompeu Fabra, Spain
MA-PI.9: AUTOMATIC DETECTION OF RED-EYE ARTIFACTS IN DIGITAL ...............................617COLOR PHOTOSAhmet Mufit Ferman, Sharp Laboratories of America, Inc., United States
MA-PI.10: DARK LINE DETECTION WITH LINE WIDTH ESTIMATION .........................................621Qin Li, Lei Zhang, Jane You, David Zhang, Prabir Bhattacharya, Hong Kong Polytechnic University, Hong Kong SAR of China
MA-PI.11: SEGMENTATION ON STATISTICAL MANIFOLD WITH ..................................................625WATERSHED TRANSFORMSang-Mook Lee, A. Lynn Abbott, Virginia Tech, United States; Philip A. Araman, U.S. Forest Service, United States
MP-L1: RECENT ADVANCES IN SUPER-RESOLUTION IMAGING
MP-L1.1: EFFICIENT RESTORATION AND ENHANCEMENT OF .....................................................629SUPER-RESOLVED X-RAY IMAGESM. Dirk Robinson, Ricoh Innovations, United States; Sina Farsiu, Joseph Y. Lo, Cynthia A. Toth, Duke University, United States
MP-L1.2: DIRECTIONAL INTERPOLATION OF NOISY IMAGES .......................................................633Lei Zhang, Hong Kong Polytechnic University, Hong Kong SAR of China; Xin Li, West Virginia University, United States
MP-L1.3: SPATIO-TEMPORAL VIDEO INTERPOLATION AND DENOISING .................................637USING MOTION-ASSISTED STEERING KERNEL (MASK) REGRESSIONHiroyuki Takeda, University of California, Santa Cruz, United States; Peter van Beek, Sharp Laboratories of America, Inc., United States; Peyman Milanfar, University of California, Santa Cruz, United States
MP-L1.4: TOTAL VARIATION SUPER RESOLUTION USING A VARIATIONAL ...........................641APPROACHSevket Derin Babacan, Northwestern University, United States; Rafael Molina, Universidad de Granada, Spain; Aggelos K. Katsaggelos, Northwestern University, United States
MP-L1.5: SUBSPACE-BASED METHODS FOR IMAGE REGISTRATION AND ................................645SUPER-RESOLUTIONPatrick Vandewalle, Philips, Netherlands; Loïc Baboulaz, Pier Luigi Dragotti, Imperial College London, United Kingdom; Martin Vetterli, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
MP-L1.6: ROBUST AND ACCURATE ESTIMATION OF MULTIPLE .................................................649MOTIONS FOR WHOLE-IMAGE SUPER-RESOLUTIONMasayuki Tanaka, Yoichi Yaguchi, Masatoshi Okutomi, Tokyo Institute ot Technology, Japan
MP-L1.7: ROBUST MULTICHANNEL SAMPLING ..................................................................................653Ha Nguyen, Sony Electronics, United States; Minh Do, University of Illinois at Urbana-Champaign, United States
MP-L2: RESTORATION II
MP-L2.1: LOCALIZED AND COMPUTATIONALLY EFFICIENT APPROACH ................................657TO SHIFT-VARIANT IMAGE DEBLURRINGMurali Subbarao, Youn-sik Kang, Satyaki Dutta, Xue Tu, State University of New York at Stony Brook, United States
MP-L2.2: ESTIMATING SPACE-VARIANT MOTION BLUR WITHOUT ............................................661DEBLURRINGShengyang Dai, Ying Wu, Northwestern University, United States
MP-L2.3: RECURSIVE RISK ESTIMATION FOR NON-LINEAR IMAGE ..........................................665DECONVOLUTION WITH A WAVELET-DOMAIN SPARSITY CONSTRAINTCédric Vonesch, Sathish Ramani, Michael Unser, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
MP-L2.4: BLIND RESTORATION OF BLURRED PHOTOGRAPHS VIA AR .....................................669MODELLING AND MCMCTom Bishop, University of Edinburgh, United Kingdom; Rafael Molina, Universidad de Granada, Spain; James Hopgood, University of Edinburgh, United Kingdom
MP-L2.5: BLIND DECONVOLUTION OF VIDEO SEQUENCES ............................................................673Ferréol Soulez, Université Jean Monnet, France; Eric Thiébaut, Yves Tourneur, Université Claude Bernard Lyon 1, France; Alain Gressard, Raphël Dauphin, Hospices Civils de Lyon, France
MP-L2.6: CROSS-TALK EXPLAINED .........................................................................................................677Keigo Hirakawa, Harvard University, United States
MP-L2.7: VIDEO ENHANCEMENT ON AN ADAPTIVE IMAGE SENSOR ..........................................681Maria E. Angelopoulou, Christos-Savvas Bouganis, Peter Y.K. Cheung, Imperial College London, United Kingdom
MP-L2.8: AN ITERATIVE ALGORITHM FOR LINEAR INVERSE PROBLEMS ...............................685WITH COMPOUND REGULARIZERSJosé Bioucas-Dias, Mário Figueiredo, Instituto de Telecomunicações, Portugal
MP-L3: IMAGE/VIDEO MODELING I
MP-L3.1: MODELING THE IMPACT OF FRAME RATE ON PERCEPTUAL ....................................689QUALITY OF VIDEOYen-Fu Ou, Tao Liu, Zhi Zhao, Zhan Ma, Yao Wang, Polytechnic University, United States
MP-L3.2: A STUDY ON THE EFFECT OF CAMERA MOTION ON HUMAN .....................................693VISUAL ATTENTIONGolnaz Abdollahian, Zygmunt Pizlo, Edward J. Delp, Purdue University, United States
MP-L3.3: FIXATION SELECTION BY MAXIMIZATION OF TEXTURE AND ..................................697CONTRAST INFORMATIONRaghu Raj, Alan Bovik, Lawrence Cormack, University of Texas at Austin, United States
MP-L3.4: ON THE NEARLY SCALE-INDEPENDENT RANK BEHAVIOR OF ...................................701IMAGE QUALITY METRICSMatthew Gaubatz, Hewlett-Packard Company, United States; Sheila Hemami, Cornell University, United States
MP-L3.5: A GAZE PREDICTION TECHNIQUE FOR OPEN SIGNED VIDEO ....................................705CONTENT USING A TRACK BEFORE DETECT ALGORITHMSam Davies, Dimitris Agrafiotis, Nishan Canagarajah, David Bull, University of Bristol, United Kingdom
MP-L3.6: TOWARDS REAL-TIME MARKERLESS HUMAN MOTION ...............................................709CAPTURE SYSTEM FROM AMBIANCE CAMERAS USING AN HYBRID PARTICLE FILTERMathias Fontmarty, Frédéric Lerasle, Patrick Danes, LAAS-CNRS, France
MP-L3.7: IMAGE RETRIEVAL AND CLASSIFICATION USING ASSOCIATIVE .............................713RECIPROCAL-IMAGE ATTRACTORSDouglas S. Greer, General Manifolds, United States; Mihran Tuceryan, Indiana University Purdue University Indianapolis, United States
MP-L3.8: A VIDEO TIME ENCODING MACHINE....................................................................................717Aurel Lazar, Eftychios Pnevmatikakis, Columbia University, United States
MP-L4: IMAGE SEGMENTATION II
MP-L4.1: PROCESS FLOW FOR CLASSIFICATION AND CLUSTERING OF ...................................721FRUIT FLY GENE EXPRESSION PATTERNSAndreas Heffel, Peter F. Stadler, Interdisciplinary Centre for Bioinformatics, Germany; Sonja J. Prohaska, School of Computing and Informatics, Arizona State University, United States; Gerhard Kauer, University of Applied Sciences, Germany; Jens-Peer Kuska, Interdisciplinary Centre for Bioinformatics, Germany
MP-L4.2: GRAPH CUT SEGMENTATION OF NEURONAL STRUCTURES .......................................725FROM TRANSMISSION ELECTRON MICROGRAPHSNhat Vu, B. S. Manjunath, University of California, Santa Barbara, United States
MP-L4.3: A NOVEL FRAMEWORK FOR N-D MULTIMODAL IMAGE ..............................................729SEGMENTATION USING GRAPH CUTSAsem Ali, Aly Farag, University of Louisville, United States
MP-L4.4: MARKOVIAN SEGMENTATION OF 3D BRAIN MRI TO DETECT ...................................733MULTIPLE SCLEROSIS LESIONSStephanie Bricq, Christophe Collet, LSIIT, France; Jean-Paul Armspach, LIGIV, Université Jean Monnet, France
MP-L4.5: SUPERVISED IMAGE SEGMENTATION VIA GROUND TRUTH ......................................737DECOMPOSITIONIlya Levner, Russell Greiner, Hong Zhang, University of Alberta, Canada
MP-L4.6: NORMALIZATION AND PREIMAGE PROBLEM IN GAUSSIAN ......................................741KERNEL PCANicolas Thorstensen, Florent Ségonne, Renaud Keriven, École Nationale des Ponts et Chaussées, France
MP-L4.7: TAC: THRESHOLDING ACTIVE CONTOURS ........................................................................745Samuel Dambreville, Anthony Yezzi, Shawn Lankton, Allen Tannenbaum, Georgia Institute of Technology, United States
MP-L4.8: GRAPH-CUT OPTIMIZATION OF THE RATIO OF FUNCTIONS ......................................749AND ITS APPLICATION TO IMAGE SEGMENTATIONHui Wang, Nilanjan Ray, Hong Zhang, University of Alberta, Canada
MP-L5: ACTIVITY & MOTION UNDERSTANDING
MP-L5.1: HUMAN ACTION RECOGNITION USING ROBUST POWER .............................................753SPECTRUM FEATURESHossein Ragheb, Sergio Velastin, Paolo Remagnino, Tim Ellis, Kingston University, United Kingdom
MP-L5.2: ‘BAG OF SEGMENTS’ FOR MOTION TRAJECTORY ANALYSIS......................................757Yue Zhou, Thomas Huang, University of Illinois at Urbana-Champaign, United States
MP-L5.3: UNSUPERVISED LEARNING OF MOTION PATTERNS USING .........................................761GENERATIVE MODELSJacinto Nascimento, Instituto de Sistemas e Robótica, Portugal; Mário Figueiredo, Instituto de Telecomunicações, Portugal; Jorge Marques, Instituto de Sistemas e Robótica, Portugal
MP-L5.4: MATCHING TRACKING SEQUENCES ACROSS WIDELY .................................................765SEPARATED CAMERASYinghao Cai, Kaiqi Huang, Tieniu Tan, National Laboratory of Pattern Recognition, China
MP-L5.5: MOTION SEGMENTATION AND ABNORMAL BEHAVIOR ...............................................769DETECTION VIA BEHAVIOR CLUSTERINGErhan Baki Ermis, Venkatesh Saligrama, Boston University, United States; Pierre-Marc Jodoin, University of Sherbrooke, Canada; Janusz Konrad, Boston University, United States
MP-L5.6: A SCRAMBLING METHOD FOR MOTION JPEG VIDEOS .................................................773ENABLING MOVING OBJECTS DETECTION FROM SCRAMBLED VIDEOSMasaaki Fujiyoshi, Keijiro Kuroiwa, Hitoshi Kiya, Tokyo Metropolitan University, Japan
MP-L5.7: ESTIMATION OF VEHICLE VELOCITY AND TRAFFIC ....................................................777INTENSITY USING RECTIFIED IMAGESCristina Maduro, Katherine Batista, Paulo Peixoto, Jorge Batista, ISR- Institute of Systems and Robotics, Portugal
MP-L5.8: ANOMALOUS ACTIVITY DETECTION AND CLASSIFICATION IN A ............................781DISTRIBUTED CAMERA NETWORKXiaotao Zou, Motorola, Inc., United States; Bir Bhanu, University of California, Riverside, United States
MP-PA: IMAGE & VIDEO FILTERING
MP-PA.1: FAST ADAPTIVE ELLIPTICAL FILTERING USING BOX SPLINES .................................785Kunal Chaudhury, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland; Maria Arrate Munoz-Barrutia, Center for Applied Medical Research, University of Navarra, Spain; Michael Unser, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
MP-PA.2: AM-FM IMAGE FILTERS ............................................................................................................789Chuong Nguyen, Joseph Havlicek, University of Oklahoma, United States
MP-PA.3: TEXTURE MODULATION-CONSTRAINED IMAGE ............................................................793DECOMPOSITIONGeorgios Evangelopoulos, Petros Maragos, National Technical University of Athens, Greece
MP-PA.4: EDGE-BASED DIRECTIONAL FUZZY FILTER FOR ...........................................................797COMPRESSION ARTIFACT REDUCTION IN JPEG IMAGESDung Vo, Truong Nguyen, University of California, San Diego, United States; Sehoon Yea, Anthony Vetro, Mitsubishi Electric Research Laboratories, United States
MP-PA.5: PARTIAL DIFFERENCE EQUATIONS ON GRAPHS FOR ..................................................801MATHEMATICAL MORPHOLOGY OPERATORS OVER IMAGES AND MANIFOLDSVinh-Thong Ta, Abderrahim Elmoataz, Olivier Lezoray, Université de Caen Basse-Normandie, France
MP-PA.6: WORD LENGTH REDUCTION FOR THE INTEGRAL IMAGE ...........................................805Harm Belt, Philips, Netherlands
MP-PA.7: GENERALIZED NEWTON METHODS FOR ENERGY .........................................................809FORMULATIONS IN IMAGE PROCESSINGLeah Bar, Guillermo Sapiro, University of Minnesota, United States
MP-PA.8: ADAPTIVE-NEIGHBORHOOD BEST MEAN RANK VECTOR ...........................................813FILTER FOR IMPULSIVE NOISE REMOVALMihai Ciuc, Universitatea Politehnica Bucuresti, Romania; Valeriu Vrabie, Michel Herbin, Universite de Reims Champagne-Ardenne, France; Constantin Vertan, Universitatea Politehnica Bucuresti, Romania; Philippe Vautrot, Universite de Reims Champagne-Ardenne, France
MP-PA.9: INTEREST POINT DETECTION ON INCOMPLETE IMAGES ............................................817Dermot Kerr, Bryan Scotney, Sonya Coleman, University of Ulster, United Kingdom
MP-PA.10: TRANSPARENT LAYER SEPARATION FOR DUAL ENERGY ........................................821IMAGINGYunqiang Chen, Matthieu Maitre, Tong Fang, Siemens Corporate Research, United States
MP-PA.11: ASYMPTOTIC CONVERGENCE OF THE ENSEMBLE KALMAN ..................................825FILTERMark Butala, Jonghyun Yun, Yuguo Chen, University of Illinois at Urbana-Champaign, United States; Richard Frazin, University of Michigan, United States; Farzad Kamalabadi, University of Illinois at Urbana-Champaign, United States
MP-PB: MOTION DETECTION AND ESTIMATION II
MP-PB.1: BIDIRECTIONAL BIAS CORRECTION FOR GRADIENT-BASED ....................................829SHIFT ESTIMATIONTuan Q. Pham, Matthew Duggan, Canon Information Systems Research Australia, Australia
MP-PB.2: OPTICAL FLOW ESTIMATION FOR A PERIODIC IMAGE ...............................................833SEQUENCELing Li, Yongyi Yang, Illinois Institute of Technology, United States
MP-PB.3: A FRAMEWORK FOR DENSE OPTICAL FLOW FROM .....................................................837MULTIPLE SPARSE HYPOTHESESTimothy Smith, David Redmill, Nishan Canagarajah, David Bull, University of Bristol, United Kingdom
MP-PB.4: GRADIENT - BASED OPTICAL FLOW FOR SUB-PIXEL ....................................................841REGISTRATION OF SPECKLE IMAGE SEQUENCES USING A SPATIAL/TEMPORAL POSTPROCESSING TECHNIQUECorneliu Cofaru, Wilfried Philips, Wim Van Paepegem, Ghent University, Belgium
MP-PB.5: OPTICAL FLOW BASED TRACKING AND RETEXTURING OF .......................................845GARMENTSAnna Hilsmann, Peter Eisert, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany
MP-PB.6: RELIABLE REJECTION OF MISMATCHING CANDIDATES FOR ...................................849EFFICIENT ZNCC TEMPLATE MATCHINGStefano Mattoccia, Federico Tombari, Luigi Di Stefano, University of Bologna, Italy
MP-PB.7: FACE TRACKING USING RAO-BLACKWELLIZED PARTICLE ......................................853FILTER AND POSE-DEPENDENT PROBABILISTIC PCATiesheng Wang, Shanghai Jiao Tong University, China; Irene Y.H Gu, Andrew Backhouse, Chalmers University of Technology, Sweden; Pengfei Shi, Shanghai Jiao Tong University, China
MP-PB.8: MULTIVARIATE ORTHOGONAL POLYNOMIALS TO EXTRACT .................................857SINGULAR POINTSOlivier Kihl, Benoit Tremblais, Bertrand Augereau, XLIM UMR CNRS 6172 University of Poitiers, France
MP-PB.9: ANOTHER WAY OF LOOKING AT MONOCULAR CIRCLE POSE ..................................861ESTIMATIONYinqiang Zheng, Wenjuan Ma, Yuncai Liu, Shanghai Jiao Tong University, China
MP-PB.10: SPEEDING UP SUPPORT VECTOR MACHINE (SVM) IMAGE ........................................865CLASSIFICATION BY A KERNEL SERIES EXPANSIONTarek Habib, Jordi Inglada, Centre National d’Etudes Spatiales (CNES), France; Gregoire Mercier, GET-Telecom Bretagne, France; Jocelyn Chanussot, Gipsa-Lab, France
MP-PB.11: RELIABLE INTEREST POINT DETECTION UNDER LARGE ..........................................869ILLUMINATION VARIATIONSMurat Gevrekci, Bahadir Gunturk, Louisiana State University, United States
MP-PB.12: MOTION DETECTION WITH FALSE DISCOVERY RATE ...............................................873CONTROLJ. Mike McHugh, Janusz Konrad, Venkatesh Saligrama, Boston University, United States; Pierre-Marc Jodoin, Universite de Sherbrooke, Canada; David Castanon, Boston University, United States
MP-PC: INTERPOLATION
MP-PC.1: SKELETONIZATION OF GRAY-SCALE IMAGES FROM ...................................................877INCOMPLETE BOUNDARIESQuannan Li, Xiang Bai, Wenyu Liu, Huazhong University of Science and Technology, China
MP-PC.2: SEGMENTED IMAGE INTERPOLATION USING EDGE .....................................................881DIRECTION AND TEXTURE SYNTHESISXiaojun Feng, Jan Allebach, Purdue University, United States
MP-PC.3: DEMOSAICING APPROACH BASED ON EXTENDED COLOR .........................................885TOTAL-VARIATION REGULARIZATIONTakahiro Saito, Takashi Komatsu, Kanagawa University, Japan
MP-PC.4: A MOTION ADAPTIVE DEINTERLACING METHOD WITH .............................................889HIERARCHICAL MOTION DETECTION ALGORITHMElham Shahinfard, Maher A. Sid-Ahmed, Majid Ahmadi, University of Windsor, Canada
MP-PC.5: KALMAN FILTERED COMPRESSED SENSING ....................................................................893Namrata Vaswani, Iowa State University, United States
MP-PC.6: GRAPH-BASED DEINTERLACING ...........................................................................................897Jerome Roussel, STMicroelectronics, France; Pascal Bertolino, Grenoble Institute of Technology, France
MP-PC.7: IMAGE INTERPOLATION USING CLASSIFICATION AND ...............................................901STITCHINGNickolaus Mueller, Truong Nguyen, University of California, San Diego, United States
MP-PC.8: IMAGE-PROCESSING APPROACH VIA NONLINEAR ........................................................905IMAGE-DECOMPOSITION FOR A DIGITAL COLOR CAMERATakahiro Saito, Yuki Ishii, Haruya Aizawa, Daisuke Yamada, Takashi Komatsu, Kanagawa University, Japan
MP-PC.9: SPATIAL AND TEMPORAL CORRELATION BASED FRAME RATE ..............................909UP-CONVERSIONYang Ling, Shanghai Jiao Tong University, China; Jin Wang, Yunqiang Liu, Philips Research Asia - Shanghai, China; Wenjun Zhang, Shanghai Jiao Tong University, China
MP-PC.10: FULLY REVERSIBLE IMAGE ROTATION BY 1-D FILTERING ......................................913Laurent Condat, Helmholtz Zentrum München - German Research Center for Environmental Health (GmbH), Germany; Dimitri Van De Ville, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
MP-PC.11: NON-CONVEX SPARSE OPTIMIZATION THROUGH .......................................................917DETERMINISTIC ANNEALING AND APPLICATIONSLuis Mancera, Universidad de Granada, Spain; Javier Portilla, Consejo Superior de Investigaciones Científicas, Spain
MP-PD: IMAGE/VIDEO RETRIEVAL II
MP-PD.1: LOCALIZED CONTENT BASED IMAGE RETRIEVAL BY .................................................921MULTIPLE INSTANCE ACTIVE LEARNINGDan Zhang, Fei Wang, Zhenwei Shi, Changshui Zhang, Tsinghua University, China
MP-PD.2: INCREMENTAL PARSING FOR LATENT SEMANTIC INDEXING ..................................925OF IMAGESSoo Hyun Bae, Biing-Hwang Juang, Georgia Institute of Technology, United States
MP-PD.3: LONG TERM LEARNING FOR IMAGE RETRIEVAL OVER .............................................929NETWORKSDavid Picard, Arnaud Revel, ETIS ENSEA/UCP/CNRS 8051, France; Matthieu Cord, LIP6 UPMC Paris 6, France
MP-PD.4: IMAGE SIMILARITY MEASUREMENT BY KULLBACK-LEIBLER ................................933DIVERGENCES BETWEEN COMPLEX WAVELET SUBBAND STATISTICS FOR TEXTURE RETRIEVALRoland Kwitt, Andreas Uhl, University of Salzburg, Austria
MP-PD.5: TEXTURE CLASSIFICATION AND RESOLUTION CONTROL .........................................937FOR 3D URBAN MAPSatoshi Ueno, University of Kitakyushu, Japan; Hiroyuki Inatsuka, Zenrin Co., Ltd, Japan; Makoto Uchino, NHK, Japan; Masahiro Okuda, University of Kitakyushu, Japan
MP-PD.6: LOCAL PATTERNS CONSTRAINED IMAGE HISTOGRAMS FOR ..................................941IMAGE RETRIEVALZhi-Gang Fan, Jilin Li, Bo Wu, Yadong Wu, Advanced R&D Center of Sharp Electronics (Shanghai) Corporation, China
MP-PD.7: AN ADAPTIVE COLOR IMAGE RETRIEVAL FRAMEWORK USING .............................945GAUSS MIXTURESSangoh Jeong, Samsung Information Systems America, United States; Chee Sun Won, Dongguk University, Republic of Korea; Robert M. Gray, Stanford University, United States
MP-PD.8: A SUPERVISED NONLINEAR NEIGHBORHOOD EMBEDDING ......................................949OF COLOR HISTOGRAM FOR IMAGE INDEXINGXian-Hua Han, Ritsumeikan University, Japan and Central South University of Forestry and Technology, China; Yen-Wei Chen, Ritsumeikan University, Japan; Takeshi Sukegawa, Remixpoint Co. LTD., Japan
MP-PD.9: A NOVEL CURVATURE-BASED SHAPE FOURIER DESCRIPTOR ...................................953Akrem El-ghazal, Otman Basir, University of Waterloo, Canada; Saeid Belkasim, Georgia State University, United States
MP-PD.10: INDEXING AND RETRIEVAL OF COMPOUND COLOR ..................................................957OBJECTS USING CO-OCCURRENCE HISTOGRAMS OF COLOR AND WAVELET FEATURESAli Hesson, Dimitrios Androutsos, Ryerson University, Canada
MP-PD.11: RETRIEVAL OF 2D VECTOR IMAGES BY MATCHING ..................................................961WEIGHTED FEATURE POINTSTakahiro Hayashi, Tatsuya Kiyono, University of Electro-Communications, Japan; Koji Abe, Kinki University, Japan; Rikio Onai, University of Electro-Communications, Japan
MP-PD.12: KERNEL PCA-BASED SEMANTIC FEATURE ESTIMATION ..........................................965APPROACH FOR SIMILAR IMAGE RETRIEVALTakahiro Ogawa, Miki Haseyama, Hokkaido University, Japan
MP-PE: IMAGE/VIDEO RETRIEVAL III
MP-PE.1: FAST AND EFFECTIVE TEXT DETECTION ...........................................................................969Xiaojun Li, Weiqiang Wang, Chinese Academy of Sciences, China; Shuqiang Jiang, Institute of Computing Technology, Chinese Academy of Sciences, China; Qingming Huang, Chinese Academy of Sciences, China; Wen Gao, Institute of Computing Technology, Chinese Academy of Sciences, China
MP-PE.2: ON HISTOGRAMS AND SPATIOGRAMS - INTRODUCTION OF ......................................973THE MAPOGRAMMikael Nilsson, Josef Ström Bartunek, Jörgen Nordberg, Ingvar Claesson, Blekinge Institute of Technology, Sweden
MP-PE.3: IMPROVING IMAGE CLUSTERING: AN UNSUPERVISED ................................................977FEATURE WEIGHT LEARNING FRAMEWORKXinxin Bai, IBM China Research Lab, China; Gang Chen, IBM China Research Lab and Tsinghua University, China; Zhonglin Lin, Wenjun Yin, Jin Dong, IBM China Research Lab, China
MP-PE.4: SPARSE NON-NEGATIVE PATTERN LEARNING FOR IMAGE ........................................981REPRESENTATIONDian Gong, University of California, Riverside, United States; Xuemei Zhao, Tsinghua University, China; Qiong Yang, Katholieke Universiteit Leuven, Belgium
MP-PE.5: INTEGRAL CORRELOGRAMS AND PROBABILISTIC DIFFUSION ................................985FOR IMAGE TAGGINGChristian Bauckhage, Deutsche Telekom Laboratories, Germany
MP-PE.6: DOMINANT TEXTURE DESCRIPTORS FOR IMAGE ..........................................................989CLASSIFICATION AND RETRIEVALAleksey Fadeev, Hichem Frigui, University of Louisville, United States
MP-PE.7: MULTI-GRAPH SIMILARITY REINFORCEMENT FOR IMAGE ......................................993ANNOTATION REFINEMENTJimin Jia, Nenghai Yu, Xiaoguang Rui, Mingjing Li, University of Science and Technology of China, China
MP-PE.8: MEDICAL IMAGE SEARCH AND RETRIEVAL USING LOCAL .......................................997BINARY PATTERNS AND KLT FEATURE POINTSDevrim Unay, Ahmet Ekin, Radu Jasinschi, Philips Research Europe, Netherlands
MP-PF: DOCUMENT IMAGE PROCESSING AND ANALYSIS
MP-PF.1: MODEL-BASED CHARACTER RECOGNITION IN LOW ..................................................1001RESOLUTIONAnnika Kuhl, Tele Tan, Svetha Venkatesh, Curtin University of Technology, Australia
MP-PF.2: A CONNECTED PATH APPROACH FOR STAFF DETECTION ON A .............................1005MUSIC SCOREJaime S. Cardoso, Artur Capela, Ana Rebelo, Universidade do Porto, Portugal; Carlos Guedes, Escola Superior de Musica e Artes do Espectaculo, Portugal
MP-PF.3: ITERATIVE PRE- AND POST-PROCESSING FOR MRC LAYERS ..................................1009OF SCANNED DOCUMENTSAlexandre Zaghetto, Ricardo L. de Queiroz, Universidade de Brasilia, Brazil
MP-PF.4: FAST ALGORITHM FOR ISE-BOUNDED POLYGONAL ...................................................1013APPROXIMATIONAlexander Kolesnikov, University of Joensuu, Finland
MP-PF.5: RAPID IMAGE BINARIZATION WITH MORPHOLOGICAL ...........................................1017OPERATORSErica Cooksey, Pegasus Imaging Corporation, United States; Wm. Douglas Withers, United States Naval Academy, United States
MP-PF.6: LOCAL-SPECTRUM-BASED DISTINCTION BETWEEN ...................................................1021HANDWRITTEN AND MACHINE-PRINTED CHARACTERSJumpei Koyama, Akira Hirose, University of Tokyo, Japan; Masahiro Kato, Fuji Xerox Co., Ltd., Japan
MP-PF.7: CAMERA-BASED DOCUMENT DIGITIZATION USING MULTIPLE .............................1025IMAGESJinho Kim, Hyung Il Koo, Nam Ik Cho, Seoul National University, Republic of Korea
MP-PG: IMAGE CODING II
MP-PG.1: A LOW-COMPLEXITY PALETTE RE-INDEXING TECHNIQUE ....................................1029BASED ON SAMPLING-SWAPPINGWei-Hong Chuang, University of Maryland, United States; Soo-Chang Pei, National Taiwan University, Taiwan
MP-PG.2: LOSSLESS IMAGE COMPRESSION USING 2D ALLPASS ................................................1033FILTERSXi Zhang, Kosuke Ohno, University of Electro-Communications, Japan
MP-PG.3: LOSSY TO LOSSLESS IMAGE COMPRESSION BASED ON ............................................1037REVERSIBLE INTEGER DCTLei Wang, Jiaji Wu, Licheng Jiao, Li Zhang, Guangming Shi, Institute of Intelligent Information Processing, Xidian University, China
MP-PG.4: AN EVALUATION OF SEVERAL MESH-GENERATION METHODS .............................1041USING A SIMPLE MESH-BASED IMAGE CODERMichael Adams, University of Victoria, Canada
MP-PG.5: GEOMETRY COMPRESSION FOR TIME-VARYING MESHES ......................................1045USING COARSE AND FINE LEVELS OF QUANTIZATION AND RUN-LENGTH ENCODINGSeung-Ryong Han, Toshihiko Yamasaki, Kiyoharu Aizawa, University of Tokyo, Japan
MP-PG.6: 3D WEATHER RADAR IMAGE COMPRESSION USING ..................................................1049MULTISCALE RECURRENT PATTERNSAthayde Frauche, Murilo Carvalho, Universidade Federal Fluminense, Brazil; Eduardo Silva, Universidade Federal do Rio de Janeiro, Brazil
MP-PG.7: MIXED CONTENT IMAGE COMPRESSION BY GRADIENT ...........................................1053FIELD INTEGRATIONPeter Ilbery, Canon Information Systems Research Australia, Australia; David Taubman, University of New South Wales, Australia; Andrew Bradley, University of Queensland, Australia
MP-PG.8: ENCODING OF IMAGES CONTAINING NO-DATA REGIONS ........................................1057WITHIN JPEG2000 FRAMEWORKJorge González-Conejero, Joan Serra-Sagristà, Universitat Autònoma de Barcelona, Spain; Carles Rubies-Feijoo, Lluis Donoso-Bach, Corporació Sanitària Parc Taulí, Spain
MP-PG.9: A NEAR OPTIMAL CODER FOR IMAGE GEOMETRY WITH ........................................1061ADAPTIVE PARTITIONINGArian Maleki, Morteza Shahram, Gunnar Carlsson, Stanford University, United States
MP-PH: IMAGE SEGMENTATION III
MP-PH.1: DETECTION OF CORONAL MASS EJECTIONS .................................................................1065Norberto Goussies, Marta Mejail, Julio Jacobo, University of Buenos Aires, Argentina; Guillermo Stenborg, Catholic University of America, Argentina
MP-PH.2: MOMENT BASED LEVEL SET METHOD FOR IMAGE ....................................................1069SEGMENTATIONJuan Zhou, Lixiu Yao, Jie Yang, Shanghai Jiao Tong University, China; Chunming Li, Vanderbilt University, United States
MP-PH.3: A FAST LEVEL SET ALGORITHM FOR SHAPE-BASED ..................................................1073SEGMENTATION WITH MULTIPLE SELECTIVE PRIORSRachid Fahmi, University Of Louisville, United States; Aly Farag, University of Louisville, United States
MP-PH.4: IIR FILTERING OF SURFACE MESHES FOR THE ............................................................1077REGULARIZATION OF DEFORMABLE MODELSJerome Velut, Hugues Benoit-Cattin, Christophe Odet, CREATIS CNRS UMR5220, INSERM U630, France
MP-PH.5: ACTIVE SURFACE MODELING AT CT RESOLUTION LIMITS .....................................1081WITH MICRO CT GROUND TRUTHAndrew Bradshaw, Michael Todd, Royal Prince Alfred Hospital, Australia; David Taubman, University of New South Wales, Australia
MP-PH.6: LEVEL SET SEGMENTATION WITH OUTLIER REJECTION .........................................1085Margarida Silveira, Jacinto Nascimento, Jorge Marques, Instituto Superior Técnico, Portugal
MP-PH.7: ILLUMINATION INVARIANT ACTIVE CONTOUR-BASED ............................................1089SEGMENTATION USING COMPLEX-VALUED WAVELETSAlexander Wong, University of Waterloo, Canada
MP-PH.8: ROBUST SNAKE CONVERGENCE BASED ON DYNAMIC ..............................................1092PROGRAMMINGAkshaya Kumar Mishra, Paul Fieguth, David. A Clausi, Vision and Image Processing Research Group, Canada
MP-PH.9: GEODESIC ACTIVE REGIONS FOR SEGMENTATION AND ..........................................1096TRACKING OF HUMAN GESTURES IN SIGN LANGUAGE VIDEOSOlga Diamanti, Petros Maragos, National Technical University of Athens, Greece
MP-PH.10: VOTING-BASED ACTIVE CONTOUR SEGMENTATION OF .........................................1100FMRI IMAGES OF THE BRAINGowri Srinivasa, Vivek Oak, Siddharth Garg, Carnegie Mellon University, United States; Matthew Fickus, Air Force Institute of Technology, United States; Jelena Kovacevic, Carnegie Mellon University, United States
MP-PH.11: A SUPERVISED TEXTURE-BASED ACTIVE CONTOUR MODEL ................................1104WITH LINEAR PROGRAMMINGJulien Olivier, Cédric Mocquillon, Jean-Jacques Rousselle, Romuald Boné, Hubert Cardot, Université François Rabelais de Tours, France
MP-PH.12: ARTICULATED REGISTRATION OF 3D HUMAN GEOMETRY TO ............................1108X-RAY IMAGEN. Sang Le, Jayashree Karlekar, Anthony Fang, National University of Singapore, Singapore
MP-PI: DISTRIBUTED SOURCE CODING I
MP-PI.1: WYNER-ZIV CODING OF MULTIVIEW IMAGES WITH ...................................................1112UNSUPERVISED LEARNING OF DISPARITY AND GRAY CODEDavid Chen, David Varodayan, Markus Flierl, Bernd Girod, Information Systems Laboratory, Stanford University, United States
MP-PI.2: DESIGN AND PERFORMANCE OF A NOVEL LOW-DENSITY .........................................1116PARITY-CHECK CODE FOR DISTRIBUTED VIDEO CODINGJoão Ascenso, ISEL - IT, Portugal; Catarina Brites, Fernando Pereira, IST - IT, Portugal
MP-PI.3: DECODER SIDE MOTION VECTOR DERIVATION FOR INTER .....................................1120FRAME VIDEO CODINGSteffen Kamp, Michael Evertz, Mathias Wien, RWTH Aachen University, Germany
MP-PI.4: PARAMETER ESTIMATION FOR AN H.264-BASED DISTRIBUTED ..............................1124VIDEO CODERBruno Macchiavello, Ricardo L. de Queiroz, Universidade de Brasilia, Brazil; Debargha Mukherjee, Hewlett-Packard Laboratories, United States
MP-PI.5: DECODER-DRIVEN ADAPTIVE DISTRIBUTED ARITHMETIC ......................................1128CODINGMarco Grangetto, Università degli Studi di Torino, Italy; Enrico Magli, Gabriella Olmo, Politecnico di Torino, Italy
MP-PI.6: RATE-DISTORTION BASED SELECTIVE DECODING FOR .............................................1132PIXEL-DOMAIN DISTRIBUTED VIDEO CODINGWei-Jung Chien, Lina Karam, Arizona State University, United States; Glen Abousleman, General Dynamics C4 Systems, United States
MP-PI.7: A LOW-COMPLEXITY ITERATIVE MODE SELECTION ..................................................1136ALGORITHM FOR WYNER-ZIV VIDEO COMPRESSIONLimin Liu, Purdue University, United States; Dake He, Ashish Jagmohan, Ligang Lu, IBM T.J. Watson Research Laboratory, United States; Edward J. Delp, Purdue University, United States
MP-PI.8: FEEDBACK FREE DVC ARCHITECTURE USING MACHINE ..........................................1140LEARNINGJose Luis Martinez Martinez, Gerardo Fernandez-Escribano, Universidad de Castilla-La Mancha, Spain; Hari Kalva, Florida Atlantic University, United States; W.A.R.J Weerakkody, W.A.C. Fernando, University of Surrey, United Kingdom; Antonio Garrido, Universidad de Castilla-La Mancha, Spain
TA-L1: LANDMARK SHAPE SEQUENCE ANALYSIS FOR VIDEO AND VOLUME IMAGE SEQUENCE PROCESSING
TA-L1.1: MODELING SPATIAL PATTERNS OF SHAPES ....................................................................1144Anuj Srivastava, Wei Liu, Florida State University, United States; Shantanu Joshi, University of California, Los Angeles, United States
TA-L1.2: EDGE DETECTION AND PROCESSING USING SHEARLETS ...........................................1148Sheng Yi, Demetrio Labate, North Carolina State University, United States; Glenn R. Easley, University of Maryland, United States; Hamid Krim, North Carolina State University, United States
TA-L1.3: BAYESIAN BASED 3D SHAPE RECONSTRUCTION FROM VIDEO .................................1152Nirmalya Ghosh, Bir Bhanu, University of California, Riverside, United States
TA-L1.4: GEOMETRIC INVARIANTS FOR CLASSIFICATION OF CORTICAL ............................1156SULCIMonica K. Hurdal, Juan B. Gutierrez, Christian Laing, Aaron D. Kline, Deborah A. Smith, Florida State University, United States
TA-L1.5: SUPER-RESOLUTION OF DEFORMED FACIAL IMAGES IN VIDEO..............................1160Jiangang Yu, Bir Bhanu, University of California, Riverside, United States
TA-L1.6: EFFECTS OF CURVATURE ON THE ANALYSIS OF LANDMARK .................................1164SHAPE MANIFOLDSMario Micheli, Brown University, United States
TA-L1.7: MODEL-BASED COMPRESSION OF NONSTATIONARY ..................................................1168LANDMARK SHAPE SEQUENCESSamarjit Das, Namrata Vaswani, Iowa State University, United States
TA-L2: IMAGE QUALITY ASSESSMENT II
TA-L2.1: AN IMAGE QUALITY ASSESSMENT METRIC BASED ......................................................1172CONTOURLETWen Lu, Xinbo Gao, Xidian University, China; Xuelong Li, University of London, United Kingdom; Dacheng Tao, Hong Kong Polytechnic University, Hong Kong SAR of China
TA-L2.2: MEASURING THE GLOBAL PHASE COHERENCE OF AN IMAGE .................................1176Gwendoline Blanchet, Centre National d’Etudes Spatiales (CNES), France; Lionel Moisan, Université Paris Descartes, France; Bernard Rouge, Centre National d’Etudes Spatiales (CNES), France
TA-L2.3: WHICH SEMI-LOCAL VISUAL MASKING MODEL FOR WAVELET .............................1180BASED IMAGE QUALITY METRIC?Alexandre Ninassi, Olivier Le Meur, Thomson Corporate Research, France; Patrick Le Callet, Dominique Barba, IRCCyN UMR 6597 CNRS, France
TA-L2.4: A NO-REFERENCE SPATIAL ALIASING MEASURE FOR DIGITAL ..............................1184IMAGE RESIZINGAmy Reibman, AT&T Labs - Research, United States; Shan Suthaharan, University of North Carolina at Greensboro, United States
TA-L2.5: UNDERSTANDING AND SIMPLIFYING THE STRUCTURAL ...........................................1188SIMILARITY METRICDavid Rouse, Sheila Hemami, Cornell University, United States
TA-L2.6: GENERAL-PURPOSE REDUCED-REFERENCE IMAGE QUALITY ................................1192ASSESSMENT BASED ON PERCEPTUALLY AND STATISTICALLY MOTIVATED IMAGE REPRESENTATIONQiang Li, University of Texas at Arlington, United States; Zhou Wang, University of Waterloo, Canada
TA-L2.7: STRUCTURAL TEXTURE SIMILARITY METRICS FOR ...................................................1196RETRIEVAL APPLICATIONSXiaonan Zhao, Northwestern University, United States; Matthew Reyes, University of Michigan, United States; Thrasyvoulos Pappas, Northwestern University, United States; David Neuhoff, University of Michigan, United States
TA-L2.8: UNIFYING ANALYSIS OF FULL REFERENCE IMAGE QUALITY ..................................1200ASSESSMENTKalpana Seshadrinathan, Alan Bovik, University of Texas at Austin, United States
TA-L3: SPATIAL SCALABILITY
TA-L3.1: ON THE CODING GAIN OF SEPARABLE 2D WAVELET FILTER ...................................1204BANKSMichael Adams, University of Victoria, Canada
TA-L3.2: EFFICIENT SPATIAL RESOLUTION REDUCTION TRANSCODING .............................1208FOR H.264/AVCJan De Cock, Stijn Notebaert, Kenneth Vermeirsch, Peter Lambert, Rik Van de Walle, Ghent University - IBBT, Belgium
TA-L3.3: ADAPTIVE ENHANCEMENT LAYER MOTION COMPENSATION .................................1212FOR VIDEO SPATIAL SCALABILITYRong Zhang, Mary Comer, Purdue University, United States
TA-L3.4: SCALABLE VIDEO COMPRESSION AND SPATIOTEMPORAL .......................................1216SCALABILITY WITH LIFTED PYRAMID AND ANTIALIASED DWT SCHEMESRaymond Leung, David Taubman, University of New South Wales, Australia
TA-L3.5: JOINT RATE-DISTORTION OPTIMIZATION OF TRANSFORM .....................................1220COEFFICIENTS FOR SPATIAL SCALABLE VIDEO CODING USING SVCMartin Winken, Heiko Schwarz, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany; Thomas Wiegand, Technical University of Berlin, Germany
TA-L3.6: IMPROVING THE RESOLUTION SCALABILITY OF .........................................................1224ORIENTATION ADAPTIVE WAVELETSJonathan Gan, David Taubman, University of New South Wales, Australia
TA-L3.7: MULTIPLE DESCRIPTION VIDEO DECODING USING MAP ............................................1228Marie Andree Agostini, Marc Antonini, Laboratory I3S - UNSA - CNRS, France
TA-L3.8: WAVELET-BASED MULTI-VIEW VIDEO CODING WITH JOINT ..................................1232BEST BASIS WAVELET PACKETSJens-Uwe Garbas, University of Erlangen-Nuremberg, Germany; Béatrice Pesquet-Popescu, Maria Trocan, Ecole Nationale Supérieure des Télécommunications, France; André Kaup, University of Erlangen-Nuremberg, Germany
TA-L4: INTERPOLATION AND SUPER-RESOLUTION
TA-L4.1: A PRACTICAL AND ADAPTIVE FRAMEWORK FOR ........................................................1236SUPER-RESOLUTIONHeng Su, Tsinghua University, China; Liang Tang, Hewlett-Packard Laboratories, China; Daniel Tretter, Hewlett-Packard Company, United States; Jie Zhou, Tsinghua University, China
TA-L4.2: A BLOCK-BASED SUPER-RESOLUTION ALGORITHM FOR ..........................................1240VIDEO SEQUENCESRyan Prendergast, Truong Nguyen, University of California, San Diego, United States
TA-L4.3: CORRELATION-BASED MOTION VECTOR PROCESSING FOR ....................................1244MOTION COMPENSATED FRAME INTERPOLATIONAi-Mei Huang, Truong Nguyen, University of California, San Diego, United States
TA-L4.4: SUPER-RESOLUTION ON SMALL MOVING OBJECTS ......................................................1248Adam van Eekeren, Klamer Schutte, TNO Defence, Security and Safety, Netherlands; Lucas van Vliet, Delft University of technology, Netherlands
TA-L4.5: EDGE-PRESERVATION RESOLUTION ENHANCEMENT WITH ....................................1252ORIENTED WAVELETSVladan Velisavljevic, Deutsche Telekom Laboratories, Germany
TA-L4.6: NEW OPTIMIZED SPLINE FUNCTIONS FOR INTERPOLATION ...................................1256ON THE HEXAGONAL LATTICELaurent Condat, Helmholtz Zentrum München - German Research Center for Environmental Health (GmbH), Germany; Dimitri Van De Ville, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
TA-L4.7: AN EFFICIENT, SELECTIVE, PERCEPTUAL-BASED ........................................................1260SUPER-RESOLUTION ESTIMATORRony Ferzli, Arizona State University, United States; Zoran Ivanovski, Ss Cyril and Methodius University, The former Yugoslav Republic of Macedonia; Lina Karam, Arizona State University, United States
TA-L4.8: FACE HALLUCINATION VIA SPARSE CODING ..................................................................1264Jianchao Yang, Hao Tang, Yi Ma, Thomas Huang, University of Illinois at Urbana-Champaign, United States
TA-L5: STEGANOGRAPHY & STEGANALYSIS I
TA-L5.1: PERFORMANCE ANALYSIS OF LOCALITY PRESERVING IMAGE ..............................1268HASHSujoy Roy, Qibin Sun, Institute for Infocomm Research, Singapore; Ton Kalker, Hewlett-Packard Laboratories, United States
TA-L5.2: RATE INSENSITIVE STEGANALYSIS OF ±1 EMBEDDING IN ........................................1272IMAGESCharles Boncelet, University of Delaware, United States; Lisa Marvel, Brian Henz, U.S. Army Research Laboratory, United States
TA-L5.3: GAME-THEORETIC ANALYSIS OF MAXIMUM-PAYOFF ................................................1276MULTIUSER COLLUSIONH. Vicky Zhao, University of Alberta, Canada; W. Sabrina Lin, K. J. Ray Liu, University of Maryland, United States
TA-L5.4: ADAPTIVE DECODING FOR HALFTONE ORIENTATION-BASED ................................1280DATA HIDINGOrhan Bulan, Gaurav Sharma, University of Rochester, United States; Vishal Monga, Xerox Company, United States
TA-L5.5: WATERMARKING FOR IMAGE-BASED RENDERING VIA .............................................1284HOMOGRAPHY-BASED VIRTUAL CAMERA LOCATION ESTIMATIONAlper Koz, Delft University of Technology, Netherlands; Cevahir Cigla, A. Aydin Alatan, Middle East Technical University, Turkey
TA-L5.6: DETECTION OF +/-1 LSB STEGANOGRAPHY BASED ON THE ......................................1288AMPLITUDE OF HISTOGRAM LOCAL EXTREMAGiacomo Cancelli, Universita di Siena, Italy; Gwenael Doerr, Ingemar Cox, University College London, United Kingdom; Mauro Barni, Universita di Siena, Italy
TA-L5.7: ESTIMATION OF OPTIMUM CODING REDUNDANCY AND ...........................................1292FREQUENCY DOMAIN ANALYSIS OF ATTACKS FOR YASS - A RANDOMIZED BLOCK BASED HIDING SCHEMEAnindya Sarkar, Lakshmanan Nataraj, B. S. Manjunath, Upamanyu Madhow, University of California, Santa Barbara, United States
TA-L5.8: USING SENSOR PATTERN NOISE FOR CAMERA MODEL ..............................................1296IDENTIFICATIONTomas Filler, Jessica Fridrich, Miroslav Goljan, State University of New York at Binghamton, United States
TA-PA: IMAGE/VIDEO MODELING II
TA-PA.1: A GRADIENT-BASED HYBRID IMAGE FUSION SCHEME USING .................................1300OBJECT EXTRACTIONMilad Ghantous, Soumik Ghosh, Magdy Bayoumi, University of Louisiana at Lafayette, United States
TA-PA.2: MOTION BLUR FREE HDR IMAGE ACQUISITION USING .............................................1304MULTIPLE EXPOSURESTakao Jinno, Masahiro Okuda, University of Kitakyushu, Japan
TA-PA.3: COMPRESSIVE IMAGE FUSION..............................................................................................1308Tao Wan, Nishan Canagarajah, Alin Achim, University of Bristol, United Kingdom
TA-PA.4: STATISTICAL FUSION AND SAMPLING OF SCIENTIFIC IMAGES ...............................1312Azadeh Mohebi, Paul Fieguth, University of Waterloo, Canada
TA-PA.5: FEATURE SPACE VIDEO STREAM CONSISTENCY ESTIMATION ...............................1316FOR DYNAMIC STREAM WEIGHTING IN AUDIO-VISUAL SPEECH RECOGNITIONLouis Terry, Derek Shiell, Aggelos K. Katsaggelos, Northwestern University, United States
TA-PA.6: VECTOR QUANTIZATION WITH MEMORY AND .............................................................1320MULTI-LABELING FOR ISOLATED VIDEO-ONLY AUTOMATIC SPEECH RECOGNITIONLouis Terry, Derek Shiell, Aggelos K. Katsaggelos, Northwestern University, United States
TA-PA.7: STOCHASTIC FUSION OF MULTI-VIEW GRADIENT FIELDS ........................................1324Aswin Sankaranarayanan, Rama Chellappa, University of Maryland, United States
TA-PA.8: MODULAR BDPCA BASED VISUAL FEATURE REPRESENTATION ............................1328FOR LIP-READINGGuanyong Wu, Jie Zhu, Shanghai Jiao Tong University, China
TA-PA.9: IMAGE ENHANCEMENT FOR IMPROVING FACE DETECTION ..................................1332UNDER NON-UNIFORM LIGHTING CONDITIONSNuman Unaldi, Praveen Sankaran, K. Vijayan Asari, Zia-ur Rahman, Old Dominion University, United States
TA-PA.10: A TEMPORAL JUST-NOTICEABLE DISTORTION PROFILE FOR ..............................1336VIDEO IN DCT DOMAINZhenyu Wei, King Ngi Ngan, Chinese University of Hong Kong, Hong Kong SAR of China
TA-PA.11: ROBUST BAYESIAN PCA WITH STUDENT’S T-DISTRIBUTION: ................................1340THE VARIATIONAL INFERENCE APPROACHJiading Gai, Yong Li, Robert L. Stevenson, University of Notre Dame, United States
TA-PA.12: IMAGE REPRESENTATION BY COMPRESSED SENSING ..............................................1344Bing Han, University of Florida, United States; Feng Wu, Microsoft Research Asia, China; Dapeng Wu, University of Florida, United States
TA-PB: VIDEO SURVEILLANCE
TA-PB.1: PEOPLE RE-DETECTION USING ADABOOST WITH SIFT AND ....................................1348COLOR CORRELOGRAMLei Hu, Shuqiang Jiang, Qingming Huang, Chinese Academy of Sciences, China; Wen Gao, Peking University, China
TA-PB.2: FEATURE-BASED OBJECT MODELLING FOR VISUAL ...................................................1352SURVEILLANCEGary Baugh, Anil Kokaram, Trinity College Dublin, Ireland
TA-PB.3: ENHANCEMENT OF UNUSUAL COLOR IN AERIAL VIDEO ...........................................1356SEQUENCES FOR ASSISTING WILDERNESS SEARCH AND RESCUENathan Rasmussen, Daniel Thornton, Bryan Morse, Brigham Young University, United States
TA-PB.4: CODING AND ENCRYPTION OF VISUAL OBJECTS FOR ................................................1360PRIVACY PROTECTED SURVEILLANCEKarl Martin, Konstantinos N. Plataniotis, University of Toronto, Canada
TA-PB.5: ROBUST AUTOMATED GROUND PLANE RECTIFICATION BASED ............................1364ON MOVING VEHICLES FOR TRAFFIC SCENE SURVEILLANCEZhaoxiang Zhang, Min Li, Kaiqi Huang, Tieniu Tan, National Laboratory of Pattern Recognition, China
TA-PB.6: FEATURE EXTRACTION TECHNIQUES FOR ABANDONED ..........................................1368OBJECT CLASSIFICATION IN VIDEO SURVEILLANCEAhmed Fawzi Otoom, Hatice Gunes, Massimo Piccardi, University of Technology, Sydney (UTS), Australia
TA-PB.7: A DISCRETE WAVELET TRANSFORM BASED RECOVERABLE ..................................1372IMAGE PROCESSING FOR PRIVACY PROTECTIONGuangzhen Li, Yoshimichi Ito, Xiaoyi Yu, Naoko Nitta, Noboru Babaguchi, Osaka University, Japan
TA-PB.8: RELIABLE SMOKE DETECTION SYSTEM IN THE DOMAINS OF ................................1376IMAGE ENERGY AND COLORPaolo Piccinini, Simone Calderara, Rita Cucchiara, University of Modena and Reggio Emilia, Italy
TA-PC: IMPLEMENTATION OF IMAGE AND VIDEO PROCESSING SYSTEMS
TA-PC.1: REAL-TIME LIGHT FALL-OFF STEREO...............................................................................1380Miao Liao, Liang Wang, Ruigang Yang, University of Kentucky, United States; Minglun Gong, Memorial University of Newfoundland, Canada
TA-PC.2: A 100 MHZ 1920X1080 HD-PHOTO 20 FRAMES/SEC JPEG XR ........................................1384ENCODER DESIGNChing-Yen Chien, Sheng-Chieh Huang, Shih-Hsiang Lin, Yu-Chieh Huang, Yi-Cheng Chen, Lei-Chun Chou, National Chiao Tung University, Taiwan; Tzu-Der Chuang, Yu-Wei Chang, Chia-Ho Pan, Liang-Gee Chen, National Taiwan University, Taiwan
TA-PC.3: PANORAMIC MOSAIC SYSTEM FOR MOBILE DEVICES ................................................1388Seong Jong Ha, Sang Hwa Lee, Yu Ri Ahn, Nam Ik Cho, Seoul National University, Republic of Korea
TA-PC.4: EVENT BASED VISION SENSING AND PROCESSING .......................................................1392Jose Antonio Perez Carrasco, Instituto de Microelectrónica de Sevilla (IMSE-CNM-CSIC), Spain; Carmen Serrano, Begoña Acha, Universidad de Sevilla, Spain; Teresa Serrano-Gotarredona, Bernabe Linares-Barranco, Instituto de Microelectrónica de Sevilla (IMSE-CNM-CSIC), Spain
TA-PC.5: NEW SIMD INSTRUCTIONS SET FOR IMAGE PROCESSING .........................................1396APPLICATIONS ENHANCEMENTFrancisco J. Jaime, Javier Hormigo, Julio Villalba, Emilio L. Zapata, University of Málaga, Spain
TA-PC.6: DESIGN OPTIMIZATION OF A GLOBAL/LOCAL TONE MAPPING .............................1400PROCESSOR ON ARM SOC PLATFORM FOR REAL-TIME HIGH DYNAMIC RANGE VIDEOChing-Te Chiu, Tsun-Hsien Wang, Wei-Ming Ke, Chen-Yu Chuang, Jhih-Rong Chen, Rong Yang, Ren-Song Tsay, National Tsing Hua University, Taiwan
TA-PC.7: N-MEANDER SCANNING TRACE A METHOD FOR THE ON-CHIP ..............................1404BANDWIDTH REDUCTIONRadomir Jakovljevic, University of Belgrade, Yugoslavia; Aleksandar Beric, Silicon Hive, Netherlands
TA-PC.8: SOFTWARE SYNTHESIS OF CAL ACTORS FOR THE MPEG .........................................1408RECONFIGURABLE VIDEO CODING FRAMEWORKGhislain Roquier, Matthieu Wipliez, Mickaël Raulet, Jean-François Nezan, Olivier Déforges, Institut d’Electronique et de Télécommunications de Rennes, France
TA-PC.9: VLSI ARCHITECTURE DESIGN OF MOTION VECTOR ...................................................1412PROCESSOR FOR H.264/AVCKiwon Yoo, Samsung Electronics, Republic of Korea; Jae-Hun Lee, Samsung Eletronics Co. Ltd., Republic of Korea; Kwanghoon Sohn, Yonsei University, Republic of Korea
TA-PC.10: POWER ANALYSIS OF THE HUFFMAN DECODING TREE ...........................................1416Jason McNeely, Yasser Ismail, Magdy Bayoumi, University of Louisiana at Lafayette, United States; Peiyi Zhao, Chapman University, United States
TA-PC.11: A CAMERA-BASED POINTING INTERFACE FOR MOBILE ..........................................1420DEVICESOrazio Gallo, Sonia Arteaga, James Davis, University of California, Santa Cruz, United States
TA-PC.12: HIGH THROUGHPUT JPEG2000 COMPATIBLE ENCODER FOR ................................1424HIGH DYNAMIC RANGE IMAGESFiras Hassan, Joan Carletta, University of Akron, United States
TA-PD: BIOMEDICAL IMAGING I
TA-PD.1: DYNAMIC STRUCTURAL-IMAGE-GUIDED NONINVASIVE 3D .....................................1428CARDIAC ELECTROPHYSIOLOGICAL MAPPINGLinwei Wang, Ken C.L. Wong, Thomas Golisano College of Computing and Information Science, Rochester Institute of Technology, United States; Heye Zhang, University of Auckland, New Zealand; Pengcheng Shi, Thomas Golisano College of Computing and Information Science, Rochester Institute of Technology, United States
TA-PD.2: APPEARANCE-BASED OBJECT DETECTION IN COLOUR RETINAL ..........................1432IMAGESJeetinder Singh, Gopal Datt Joshi, IIIT-Hyderabad, India; Jayanthi Sivaswamy, IIIT-hyderabad, India
TA-PD.3: SEED PRUNING USING A MULTI-RESOLUTION APPROACH FOR ..............................1436AUTOMATED SEGMENTATION OF BREAST CANCER TISSUERohit Philip, Jeffrey Rodriguez, University of Arizona, United States; Robert Gillies, University of Arizona / Arizona Cancer Center, United States
TA-PD.4: BREAST CONTOUR DETECTION WITH SHAPE PRIORS .................................................1440Ricardo Sousa, Jaime S. Cardoso, INESC Porto, Portugal; Joaquim Pinto da Costa, Faculdade de Ciências, Portugal; Maria João Cardoso, Faculdade de Medicina, Portugal
TA-PD.5: MICROARRAY IMAGE GRIDDING VIA AN EVOLUTIONARY ......................................1444ALGORITHMEleni Zacharia, Dimitris Maroulis, University of Athens, Greece
TA-PD.6: QUANTITATIVE ANALYSIS OF DIFFUSION TENSOR IMAGES ....................................1448ACROSS SUBJECTS USING PROBABILISTIC TRACTOGRAPHYDarshan Pai, Otto Muzik, Jing Hua, Wayne State University, United States
TA-PD.7: AUTOMATIC LATTICE DETECTION IN NEAR-REGULAR .............................................1452HISTOLOGY ARRAY IMAGESBrian Canada, Penn State University, United States; Georgia Thomas, Keith Cheng, Penn State College of Medicine, United States; James Z. Wang, Yanxi Liu, Penn State University, United States
TA-PD.8: A REGION BASED DECORRELATION STRETCHING METHOD: ..................................1456APPLICATION TO MULTISPECTRAL CHROMOSOME IMAGE CLASSIFICATIONPetros Karvelis, Dimitrios Fotiadis, University of Ioannina, Greece
TA-PD.9: SUPERVISED METHODS FOR PERFECT SEGMENTATION IN ......................................1460MEDICAL IMAGESTony Shepherd, Daniel C. Alexander, University College London, United Kingdom
TA-PE: BIOMETRICS II
TA-PE.1: PEDESTRIAN DETECTION VIA LOGISTIC MULTIPLE INSTANCE .............................1464BOOSTINGJunbiao Pang, Qingming Huang, Shuqiang Jiang, Institute of Computing Technology, Chinese Academy of Sciences, China; Wen Gao, Institute of Digital Media, Peking University, China
TA-PE.2: USING COLOR BIN IMAGES FOR CROWD DETECTIONS ...............................................1468Chern-Horng Sim, Ekambaram Rajmadhan, Surendra Ranganath, National University of Singapore, Singapore
TA-PE.3: LOCAL BINARY PATTERNS FOR LIP MOTION ANALYSIS ............................................1472Ralph Kricke, Thorsten Gernoth, Rolf-Rainer Grigat, Hamburg University of Technology, Germany
TA-PE.4: OMNIDIRECTIONAL TRACKING AND RECOGNITION OF ............................................1476PERSONS IN PLANAR VIEWSSascha Schreiber, Andre Stoermer, Gerhard Rigoll, Technische Universität München, Germany
TA-PE.5: EYE STATES DETECTION BY BOOSTING LOCAL BINARY ...........................................1480PATTERN HISTOGRAM FEATURESCui Xu, Ying Zheng, Zengfu Wang, University of Science and Technology of China, China
TA-PE.6: UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR ................................1484DANCING AVATAR ANIMATIONFerda Ofli, Engin Erzin, Yucel Yemez, A. Murat Tekalp, Koç University, Turkey; Cigdem E. Erdem, A. Tanju Erdem, Tolga Abaci, Mehmet K. Ozkan, Momentum A. S., Turkey
TA-PE.7: A NOVEL FINGERPRINT MATCHING METHOD USING A .............................................1488CURVATURE-BASED MINUTIA SPECIFIERJin Qi, University of Electronic Science and Technology, China; Mei Xie, University of Electronic and Science Technoloy of China, China; Weixing Wang, University of Electronic and Science Technology of China, China
TA-PE.8: A ROBUST TECHNIQUE FOR LATENT FINGERPRINT IMAGE .....................................1492SEGMENTATION AND ENHANCEMENTShahryar Karimi-Ashtiani, C.-C. Jay Kuo, University of Southern California, United States
TA-PF: STEREO AND 3D III
TA-PF.1: AFFECTS OF ILLUMINATION ON 3D SHAPE RECOVERY ..............................................1496Mannan Saeed Muhammad, Aamir Saeed Malik, Tae-Sun Choi, Gwangju Institute of Science and Technology, Republic of Korea
TA-PF.2: PHOTOMETRIC STEREO THROUGH AN ADAPTED ALTERNATION ..........................1500APPROACHCarme Julià, Angel D Sappa, Felipe Lumbreras, Joan Serrat, Antonio López, Computer Vision Center, Universitat Autònoma de Barcelona, Spain
TA-PF.3: LUNAR TERRAIN RECONSTRUCTION USING PDES .........................................................1504Ji Liu, Yang Cong, Xiaomao Li, Yuechao Wang, Yandong Tang, Shenyang Institue of Automation, Chinese Academy of Sciences, China; Chuan Zhou, Shenyang Institute of Automation, China
TA-PF.4: VIRTUAL VIEW SYNTHESIS WITH HEURISTIC SPATIAL .............................................1508MOTIONWenfeng Li, Baoxin Li, Arizona State University, United States
TA-PF.5: SALIENT POINT CHARACTERIZATION FOR LOW RESOLUTION ..............................1512MESHESNicolas Walter, Olivier Aubreton, Olivier Laligant, Laboratoire Le2i, UMR CNRS 5158, France
TA-PF.6: ROBUST DEPTH ESTIMATION FOR EFFICIENT 3D FACE .............................................1516RECONSTRUCTIONYing Zheng, Zengfu Wang, University of Science and Technology of China, China
TA-PF.7: REGULARIZED DEPTH FROM DEFOCUS.............................................................................1520Vinay Namboodiri, KU Leuven, Belgium; Subhasis Chaudhuri, Indian Institute of Technology, Bombay, India; Sunil Hadap, Adobe Systems Incorporated, United States
TA-PF.8: ONE-SHOT RANGE SCANNER USING COPLANARITY ....................................................1524CONSTRAINTSRyo Furukawa, Hiroshima City University, Japan; Huynh Quang Huy Viet, Hiroshi Kawasaki, Saitama University, Japan; Ryusuke Sagawa, Yasushi Yagi, Osaka University, Japan
TA-PF.9: THEORETICAL MODEL AND OPTIMAL PREFILTER FOR VIEW ................................1528INTERPOLATIONKeita Takahashi, Takeshi Naemura, University of Tokyo, Japan
TA-PF.10: SURFACE COMPLETION BY MINIMIZING ENERGY BASED ON ...............................1532SIMILARITY OF SHAPENorihiko Kawai, Tomokazu Sato, Naokazu Yokoya, Nara Institute of Science and Technology, Japan
TA-PG: VIDEO SEGMENTATION AND TRACKING I
TA-PG.1: A NOVEL SCENE CHANGE DETECTION ALGORITHM BASED ON .............................1536THE 3D WAVELET TRANSFORMZhi Li, Guizhong Liu, Xi’an Jiaotong University, China
TA-PG.2: LEVEL SET TRACKING WITH DYNAMICAL SHAPE PRIORS........................................1540Xue Zhou, Xi Li, Weiming Hu, National Laboratory of Pattern Recognition, China
TA-PG.3: REAL-TIME SEGMENTATION OF OBJECTS FROM VIDEO ..........................................1544SEQUENCES WITH NON-STATIONARY BACKGROUNDS USING SPATIO-TEMPORAL COHERENCEJae-Kyun Ahn, Chang-Su Kim, Korea University, Republic of Korea
TA-PG.4: TRACKING NON-RIGID STRUCTURES IN COMPUTER ..................................................1548SIMULATIONSAbel Gezahegne, Chandrika Kamath, Lawrence Livermore National Laboratory, United States
TA-PG.5: SPATIO-TEMPORAL SEGMENTATION AND REGIONS TRACKING ...........................1552OF HIGH DEFINITION VIDEO SEQUENCES BASED ON A MARKOV RANDOM FIELD MODELOlivier Brouard, Fabrice Delannay, Vincent Ricordel, Dominique Barba, University of Nantes, France
TA-PG.6: DYNAMIC BACKGROUND MODELING AND SUBTRACTION .......................................1556USING SPATIO-TEMPORAL LOCAL BINARY PATTERNSShengping Zhang, Hongxun Yao, Shaohui Liu, Harbin Institute of Technology, China
TA-PG.7: WAVELET DOMAIN PROCESSING FOR TRAJECTORY .................................................1560EXTRACTIONAlexia Briassouli, Dimitra Matsiki, Ioannis Kompatsiaris, Informatics and Telematics Institute, Greece
TA-PG.8: PATCH-BASED ADAPTIVE TRACKING USING SPATIAL AND ......................................1564APPEARANCE INFORMATIONJunqiu Wang, Yasushi Yagi, Institute of Scientific and Industrial Research, Osaka University, Japan
TA-PG.9: OBJECT TRACKING USING INCREMENTAL 2D-LDA LEARNING ..............................1568AND BAYES INFERENCEGuorong Li, Dawei Liang, Qingming Huang, Chinese Academy of Sciences, China; Shuqiang Jiang, Key Lab of Intell. Info. Process., Chinese Academy of Sciences, China; Wen Gao, Institute of Digital Media, Peking University, China
TA-PG.10: BACKGROUND MODELING FROM A FREE-MOVING CAMERA ...............................1572BY MULTI-LAYER HOMOGRAPHY ALGORITHMYuxin Jin, Linmi Tao, Huijun Di, Naveed I Rao, Guangyou Xu, Tsinghua University, China
TA-PG.11: LIVE VIDEO OBJECT TRACKING AND SEGMENTATION USING .............................1576GRAPH CUTSZachary Garrett, Hideo Saito, Keio University, Japan
TA-PG.12: MULTITARGET TRACKING USING GAUSSIAN PROCESS ...........................................1580DYNAMICAL MODEL PARTICLE FILTERJing Wang, Hong Man, Yafeng Yin, Stevens Institute of Technology, United States
TA-PH: VIDEO CODING I
TA-PH.1: THRESHOLD-FREE PATTERN-BASED LOW BIT RATE VIDEO ....................................1584CODINGManoranjan Paul, Manzur Murshed, Monash University, Australia
TA-PH.2: VIDEO CODING USING MOTION CLASSIFICATION ........................................................1588Marc Bosch, Fengqing Zhu, Edward J. Delp, Purdue University, United States
TA-PH.3: FAST, DYNAMIC CONFIGURATION OF TRANSFORMS FOR ........................................1592VIDEO CODINGChaminda Sampath Kannangara, Iain Richardson, Robert Gordon University, United Kingdom; Maja Bystrom, Boston University, United States; Manuel de Frutos, Universidad Carlos III de Madrid, Spain
TA-PH.4: HOMOGRAPHY BASED DISTRIBUTED VIDEO CODING FOR A ...................................1596NETWORK OF CAMERASAshok Veeraraghavan, Mahesh Ramachandran, University of Maryland, College Park, United States; Manohar Mareboyana, Bowie State University, United States
TA-PH.5: COMPRESSION OF HALFTONE VIDEO FOR ELECTRONIC ..........................................1600PAPERChao-Yung Hsu, Academia Sinica and National Taiwan University, Taiwan; Chun-Shien Lu, Academia Sinica, Taiwan; Soo-Chang Pei, National Taiwan University, Taiwan
TA-PH.6: CAPTURING LIGHT FIELD TEXTURES FOR VIDEO CODING .......................................1604William Mantzel, Justin Romberg, Georgia Institute of Technology, United States
TA-PH.7: DYNAMIC TEXTURE SYNTHESIS FOR H.264/AVC INTER .............................................1608CODINGAleksandar Stojanovic, Mathias Wien, Jens-Rainer Ohm, RWTH Aachen University, Germany
TA-PH.8: A NOVEL INCREMENTAL RATE CONTROL SCHEME FOR H.264 ...............................1612VIDEO CODINGYu Sun, Yimin Zhou, University of Central Arkansas, United States; Zhidan Feng, Acxiom Corporation, United States; Zhihai He, University of Missouri-Columbia, United States
TA-PH.9: IMPROVED DYNAMIC RATE SHAPING FOR H.264/AVC VIDEO ..................................1616STREAMSStijn Notebaert, Jan De Cock, Kenneth Vermeirsch, Peter Lambert, Rik Van de Walle, Ghent University - IBBT, Belgium
TA-PH.10: HIGH PRECISION EDGE PREDICTION FOR INTRA CODING ......................................1620Virginie Drugeon, Thomas Wedi, Torsten Palfner, Panasonic R&D Center Germany, Germany
TA-PH.11: A DIRECTION-ADAPTIVE IN-LOOP DEARTIFACTING FILTER .................................1624FOR VIDEO CODINGCamilo C. Dorea, Oscar Divorra Escoda, Peng Yin, Cristina Gomila, Thomson, United States
TA-PH.12: SYNTHESIS-BASED TEXTURE CODING FOR VIDEO ....................................................1628COMPRESSION WITH SIDE INFORMATIONByung Tae Oh, University of Southern California, United States; Yeping Su, Andrew Segall, Sharp Laboratories of America, Inc., United States; C.-C. Jay Kuo, University of Southern California, United States
TA-PI: FACE DETECTION, RECOGNITION AND CLASSIFICATION I
TA-PI.1: REAL-TIME FACE ALIGNMENT WITH TRACKING IN VIDEO .......................................1632Yanchao Su, Haizhou Ai, Tsinghua University, China; Shihong Lao, Omron Corporation, Japan
TA-PI.2: HOG-EBGM VS. GABOR-EBGM ................................................................................................1636David Monzo, Alberto Albiol, Jorge Sastre, Antonio Albiol, Universidad Politécnica de Valencia, Spain
TA-PI.3: PARALLEL ADABOOST ALGORITHM FOR GABOR WAVELET ....................................1640SELECTION IN FACE RECOGNITIONUlas Bagci, Li Bai, University of Nottingham, United Kingdom
TA-PI.4: AN ACCURATE ALGORITHM FOR HEAD DETECTION BASED ON ..............................1644XYZ AND HSV HAIR AND SKIN COLOR MODELSZui Zhang, Hatice Gunes, Massimo Piccardi, University of Technology, Sydney (UTS), Australia
TA-PI.5: FACIAL AGING SIMULATION BASED ON SUPER-RESOLUTION IN ............................1648TENSOR SPACEFangyuan Jiang, Yunhong Wang, Beihang University, China
TA-PI.6: SINGLE VIEW HEAD POSE ESTIMATION .............................................................................1652Pedro Martins, Jorge Batista, Unversity of Coimbra, Portugal
TA-PI.7: IMPROVING GENERALIZATION FOR GENDER CLASSIFICATION ..............................1656Xue Ming Leng, Chinese Academy of Sciences, China; Yi Ding Wang, North China University of Technology, China
TA-PI.8: GABOR-BASED MULTI-SCALE ILLUMINATION NORMALIZATION ...........................1660MODEL FOR FACE RECOGNITIONJiying Wu, Gaoyun An, Qiuqi Ruan, Beijing Jiaotong University, China
TA-PI.9: SIGNIFICANT JET POINT FOR FACIAL IMAGE REPRESENTATION ...........................1664AND RECOGNITIONSanqiang Zhao, Yongsheng Gao, Griffith University, Australia
TP-L1: PRIVACY PROTECTION FOR VISUAL INFORMATION
TP-L1.1: DISCRETE COSINE TRANSFORM OF ENCRYPTED IMAGES ..........................................1668Tiziano Bianchi, Alessandro Piva, University of Firenze, Italy; Mauro Barni, University of Siena, Italy
TP-L1.2: PRIVACY PROTECTING VISUAL PROCESSING FOR SECURE ......................................1672VIDEO SURVEILLANCEXiaoyi Yu, Kenta Chinomi, Takashi Koshimizu, Naoko Nitta, Yoshimichi Ito, Noboru Babaguchi, Graduate School of Engineering, Osaka University, Japan
TP-L1.3: MANAGING PRIVACY DATA IN PERVASIVE CAMERA NETWORKS ...........................1676Sen-ching Cheung, Jithendra Paruchuri, University of Kentucky, United States; Thinh Nguyen, Oregon State University, United States
TP-L1.4: PRIVACY ENABLEMENT IN A SURVEILLANCE SYSTEM ................................................1680Andrew Senior, IBM Research, United States
TP-L1.5: PRIVACY PRESERVING PATTERN CLASSIFICATION ......................................................1684Shai Avidan, Adobe, United States; Ariel Elbaz, Tal Malkin, Columbia University, United States
TP-L1.6: H.264/AVC VIDEO SCRAMBLING FOR PRIVACY PROTECTION ....................................1688Frederic Dufaux, Touradj Ebrahimi, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
TP-L1.7: ON PRIVACY AND SECURITY IN DISTRIBUTED VISUAL ...............................................1692SENSOR NETWORKSAlexandra Czarlinska, William Luh, Deepa Kundur, Texas A&M University, United States
TP-L2: IMAGE/VIDEO CLASSIFICATION, RETRIEVAL AND BROWSING
TP-L2.1: CORRELATION EMBEDDING ANALYSIS..............................................................................1696Yun Fu, Thomas Huang, University of Illinois at Urbana-Champaign, United States
TP-L2.2: COMPLEX DISCRIMINANT FEATURES FOR OBJECT .....................................................1700CLASSIFICATIONSunhyoung Han, Nuno Vasconcelos, University of California, San Diego, United States
TP-L2.3: LEARNING ACTION DICTIONARIES FROM VIDEO ..........................................................1704Pavan Turaga, Rama Chellappa, University of Maryland, United States
TP-L2.4: EFFICIENT CLUSTERING OF FACE SEQUENCES WITH .................................................1708APPLICATION TO CHARACTER-BASED MOVIE BROWSINGJi Tao, Yap-Peng Tan, Nanyang Technological University, Singapore
TP-L2.5: A MASTER-SLAVE APPROACH FOR OBJECT DETECTION AND ..................................1712MATCHING WITH FIXED AND MOBILE CAMERASAlexandre Alahi, David Marimon, Michel Bierlaire, Murat Kunt, Swiss Federal Institute of Technology (EPFL), Switzerland
TP-L2.6: LOCAL FEATURE EXTRACTION FOR VIDEO COPY DETECTION ...............................1716IN A DATABASEEhsan Maani, Sotirios Tsaftaris, Aggelos K. Katsaggelos, Northwestern University, United States
TP-L2.7: A SYSTEMATIC STUDY OF THE ROLE OF CONTEXT ON IMAGE ................................1720CLASSIFICATIONNikhil Rasiwasia, Nuno Vasconcelos, University of California, San Diego, United States
TP-L2.8: CHAOS AND MPEG-7 BASED FEATURE VECTOR FOR VIDEO ......................................1724OBJECT CLASSIFICATIONHanif Azhar, Aishy Amer, Concordia University, Canada
TP-L3: ENHANCEMENT AND DENOISING II
TP-L3.1: PRINCIPAL COMPONENTS FOR NON-LOCAL MEANS IMAGE .....................................1728DENOISINGTolga Tasdizen, University of Utah, United States
TP-L3.2: EFFICIENT NONLOCAL-MEANS DENOISING USING THE SVD .....................................1732Jeff Orchard, Mehran Ebrahimi, Alexander Wong, University of Waterloo, Canada
TP-L3.3: COMBINED NON-LOCAL AVERAGING AND INTERSECTION OF ................................1736CONFIDENCE INTERVALS FOR IMAGE DE-NOISINGRadu Ciprian Bilcu, Markku Vehvilainen, Nokia Research Center, Finland
TP-L3.4: HARDWARE-FRIENDLY DESCREENING ..............................................................................1740Hasib Siddiqui, Mireille Boutin, Charles A. Bouman, Purdue University, United States
TP-L3.5: EM-BASED ESTIMATION OF SPATIALLY VARIANT CORRELATED ...........................1744IMAGE NOISEBart Goossens, Aleksandra Pizurica, Wilfried Philips, Ghent University, Belgium
TP-L3.6: VARIATIONAL BAYESIAN IMAGE PROCESSING ON STOCHASTIC ...........................1748FACTOR GRAPHSXin Li, West Virginia University, United States
TP-L3.7: JND-BASED ENHANCEMENT OF PERCEPTIBILITY FOR DIM ......................................1752IMAGESTai-Hsiang Huang, Chia-Kai Liang, Su-Ling Yeh, Homer.H Chen, National Taiwan University, Taiwan
TP-L3.8: DENOISING OF MEDICAL IMAGES CORRUPTED BY POISSON ....................................1756NOISEIsabel Rodrigues, Instituto de Sistemas e Robótica / Instituto Superior de Engenharia de Lisboa, Portugal; João Sanches, Instituto de Sistemas e Robótica / Instituto Superior Técnico, Portugal; José Bioucas-Dias, Instituto de Telecomunicações / Instituto Superior de Engenharia de Lisboa, Portugal
TP-L4: STEREO AND 3D IV
TP-L4.1: 2D/3D FREEVIEW VIDEO GENERATION FOR 3DTV SYSTEM .........................................1760Dongbo Min, Donghyun Kim, Kwanghoon Sohn, Yonsei University, Republic of Korea
TP-L4.2: TWO OPTIMIZATIONS OF THE MPEG-4 FAMC STANDARD FOR ................................1764ENHANCED COMPRESSION OF ANIMATED 3D MESHESKhaled Mamou, Titus Zaharia, Françoise Prêteux, Institut TELECOM & Management SudParis, France; Aymen Kamoun, Frédéric Payan, Marc Antonini, Université de Nice - Sophia Antipolis, France
TP-L4.3: JOINT ENCODING OF THE DEPTH IMAGE BASED ...........................................................1768REPRESENTATION USING SHAPE-ADAPTIVE WAVELETSMatthieu Maitre, Minh Do, University of Illinois at Urbana-Champaign, United States
TP-L4.4: 3D MIRROR SYMMETRY DETECTION USING HOUGH ...................................................1772TRANSFORMDavid Cailliere, Orange Labs, France; Florence Denis, CNRS, LIRIS UMR 5205, France; Danielle Pele, Orange Labs, France; Atilla Baskurt, CNRS, LIRIS UMR 5205, France
TP-L4.5: VIEWPOINT SWITCHING IN MULTIVIEW VIDEOS USING ............................................1776SP-FRAMESKi-Kit Lai, Yui-Lam Chan, Chang-Hong Fu, Wan-Chi Siu, Hong Kong Polytechnic University, Hong Kong SAR of China
TP-L4.6: SPARSE STEREO MATCHING USING BELIEF PROPAGATION ......................................1780Michel Sarkis, Klaus Diepold, Technische Universität München, Germany
TP-L4.7: COOPERATIVE DISPARITY AND OBJECT BOUNDARY ...................................................1784ESTIMATIONRamya Narasimha, Institut National de Recherche en Informatique et Automatique Rhone-alpes, France; Elise Arnaud, Universite Joseph Fourier/INRIA Rhone-alpes, France; Florence Forbes, Radu Horaud, Institut National de Recherche en Informatique et Automatique Rhone-alpes, France
TP-L4.8: BELIEF PROPAGATION ON RIEMANNIAN MANIFOLD FOR .........................................1788STEREO MATCHINGQuanquan Gu, Jie Zhou, Tsinghua University, China
TP-L5: BIOIMAGE ANALYSIS
TP-L5.1: COMPUTATIONALLY EFFICIENT MUTUAL INFORMATION ........................................1792ESTIMATION FOR NON-RIGID IMAGE REGISTRATIONAli Gholipour, Nasser Kehtarnavaz, University of Texas at Dallas, United States
TP-L5.2: FEATURE-AIDED PARTICLE TRACKING .............................................................................1796Nicolas Chenouard, Unite d’Analyse Quantitative d’Images, France; Isabelle Bloch, Département Traitement Signal et Images, ENST, France; Jean-Christophe Olivo-Marin, Unite d’Analyse Quantitative d’Images, France
TP-L5.3: SEMIAUTOMATIC NON-RIGID 3-D IMAGE REGISTRATION FOR ................................1800MR-GUIDED LIVER CANCER SURGERYYen-Wei Chen, Central South University of Forestry and Technology, China and Ritsumeikan University, Japan; Katsumu Tsubokawa, Rui Xu, Ritsumeikan University, Japan; Shigehiro Morikawa, Yoshimasa Kurumi, Shiga University of Medical Science, Japan
TP-L5.4: CELL SEGMENTATION USING HESSIAN-BASED DETECTION .....................................1804AND CONTOUR EVOLUTION WITH DIRECTIONAL DERIVATIVESIlker Ersoy, Filiz Bunyak, University of Missouri-Columbia, United States; Michael A. Mackey, University of Iowa, United States; Kannappan Palaniappan, University of Missouri-Columbia, United States
TP-L5.5: FOCUSED ATLAS-BASED IMAGE REGISTRATION FOR .................................................1808RECOGNITIONJonathan Rohrer, IBM Zurich Research Laboratory, Switzerland; Leiguang Gong, IBM T.J. Watson Research Laboratory, United States
TP-L5.6: A NOVEL IMAGE ANALYSIS APPROACH FOR ACCURATE ...........................................1812IDENTIFICATION OF ACUTE RENAL REJECTIONAyman El-Baz, University of Louisville, United States; Georgy Gimel’farb, University of Auckland, New Zealand; Mohamed El-Ghar, University of Mansoura, Egypt
TP-L5.7: EVALUATION AND BENCHMARK FOR BIOLOGICAL IMAGE ......................................1816SEGMENTATIONElisa Drelie Gelasca, Jiyun Byun, Boguslaw Obara, B. S. Manjunath, University of California, Santa Barbara, United States
TP-L5.8: A NEW CAD SYSTEM FOR EARLY DIAGNOSIS OF DYSLEXIC .....................................1820BRAINSAyman El-Baz, Manuel Casanova, University of Louisville, United States; Georgy Gimel’farb, University of Auckland, New Zealand; Meghan Mott, Andrew Switala, Eric Vanbogaert, Russ McCracken, University of Louisville, United States
TP-PA: IMAGING APPLICATIONS
TP-PA.1: AN AUTOMATIC FRAMEWORK FOR STANDARDIZATION OF ....................................1824DROSOPHILA EMBRYONIC IMAGESQi Li, Guangming Xing, Art Shindhelm, Western Kentucky University, United States
TP-PA.2: A NOVEL PSEUDO-LIKELIHOOD EQUATION FOR POTTS MRF ..................................1828MODEL PARAMETER ESTIMATION IN IMAGE ANALYSISAlexandre Levada, Universidade de São Paulo, Brazil; Nelson Mascarenhas, Universidade Federal de São Carlos, Brazil; Alberto Tannús, Universidade de São Paulo, Brazil
TP-PA.3: INVERSE IMAGE PROBLEM OF DESIGNING PHASE SHIFTING ..................................1832MASKS IN OPTICAL LITHOGRAPHYStanley Chan, University of California, San Diego, United States; Edmund Lam, University of Hong Kong, Hong Kong SAR of China
TP-PA.4: VOLATILE ORGANIC COMPOUND PLUME DETECTION USING .................................1836WAVELET ANALYSIS OF VIDEO Behcet Ugur Toreyin, A. Enis Cetin, Bilkent Universitesi, Turkey
TP-PA.5: ON THE ESTIMATION OF GEODESIC PATHS ON SAMPLED ........................................1840MANIFOLDS UNDER RANDOM PROJECTIONSMona Mahmoudi, University of Minnesota, United States; Pierre Vandergheynst, Matteo Sorci, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
TP-PA.6: BOOSTED INTERACTIVELY DISTRIBUTED PARTICLE FILTER .................................1844FOR AUTOMATIC MULTI-OBJECT TRACKINGYi Wu, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China; Xiaofeng Tong, Yimin Zhang, Intel China Research Center, China; Hanqing Lu, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China
TP-PA.7: THE TRADEOFF BETWEEN SNR AND EXPOSURE-SET SIZE IN ...................................1848HDR IMAGINGNeil Barakat, Thomas E. Darcie, Andrew N. Hone, University of Victoria, Canada
TP-PA.8: COMPARING SIFT DESCRIPTORS AND GABOR TEXTURE ...........................................1852FEATURES FOR CLASSIFICATION OF REMOTE SENSED IMAGERYYi Yang, Shawn Newsam, University of California, Merced, United States
TP-PA.9: A GENERALIZED LIKELIHOOD RATIO TEST FOR DETECTING .................................1856TARGETS IN MULTIPLE-BAND SPECTRAL IMAGES WITH IMPROPER COMPLEX GAUSSIAN NOISEGhaith Matalkah, James Sabatier, Mustafa Matalgah, University of Mississippi, United States
TP-PA.10: EP PRINTER JITTER CHARACTERIZATION USING 2D GABOR .................................1860FILTER AND SPECTRAL ANALYSISAhmed Eid, Mohamed Ahmed, Edward Rippetoe, Lexmark International Inc., United States
TP-PB: IMAGING FOR GEOSCIENCE APPLICATIONS
TP-PB.1: A NONLINEAR KERNEL-BASED JOINT FUSION/DETECTION OF ................................1864ANOMALIES USING HYPERSPECTRAL AND SAR IMAGERYNasser M. Nasrabadi, U.S. Army Research Laboratory, United States
TP-PB.2: A CFAR ALGORITHM FOR ANOMALY DETECTION AND ..............................................1868DISCRIMINATION IN HYPERSPECTRAL IMAGESAlexis Huck, Mireille Guillaume, Institut Fresnel, France
TP-PB.3: A TWO DIMENSION OVERLAPPED SUBAPERTURE POLAR .........................................1872FORMAT ALGORITHM BASED ON STEPPED-CHIRP SIGNALXinhua Mao, Daiyin Zhu, Ling Wang, Zhaoda Zhu, Nanjing University of Aeronautics and Astronautics, China
TP-PB.4: AUTOMATIC TONAL HARMONIZATION FOR MULTI-SPECTRAL .............................1876MOSAICSPouya Tafti, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland; Xiaolin Wu, McMaster University, Canada
TP-PB.5: A ROBUST FRAMEWORK FOR GEOTIME CUBE ...............................................................1880Vincent Toujas, Marc Donias, Dominique Jeantet, Université Bordeaux 1, France; Sebastien Guillon, TOTAL, France; Yannick Berthoumieu, Université Bordeaux 1, France
TP-PB.6: ADAPTIVE PIXEL NEIGHBORHOOD DEFINITION FOR THE ........................................1884CLASSIFICATION OF HYPERSPECTRAL IMAGES WITH SUPPORT VECTOR MACHINES AND COMPOSITE KERNELMathieu Fauvel, Jocelyn Chanussot, GIPSA-lab, INPG, France; Jon Atli Benediktsson, University of Iceland, Iceland
TP-PB.7: SAR INTERFEROGRAM FILTERING IN THE WAVELET DOMAIN ..............................1888USING A COHERENCE MAP MASKRiadh Abdelfattah, Aymen Bouzid, URISA/SUPCOM, Tunisia
TP-PB.8: SHAPE NORMALIZED SUBSPACE ANALYSIS FOR UNDERWATER ............................1892MINE DETECTIONPayam Saisan, Shubha Kadambe, HRL Laboratories, United States
TP-PB.9: WATER/LAND SEGMENTATION IN SAR IMAGES USING LEVEL ................................1896SETSMargarida Silveira, Sandra Heleno, Instituto Superior Técnico, Portugal
TP-PB.10: TERRAIN MODELING FROM LIDAR DATA: HIERARCHICAL ....................................1900K-MEANS FILTERING AND MARKOVIAN REGULARIZATIONNesrine Chehata, IGN(Institut Géographique National) / University of Bordeaux, France; Frédéric Bretar, IGN (Institut Géographique National), France
TP-PC: FACE DETECTION, RECOGNITION AND CLASSIFICATION II
TP-PC.1: FACE RECOGNITION BASED ON GRADIENT GABOR FEATURE..................................1904Baochang Zhang, Yongsheng Gao, Griffith University, Australia; Yu Qiao, University of Tokyo, Japan
TP-PC.2: FACE RECOGNITION USING A PICTORIAL-EDIT DISTANCE .......................................1908William Hulbert, Christine Podilchuk, Star Technologies, A DSCI Company, United States; Richard Mammone, Rutgers University, United States
TP-PC.3: LEARNING STRUCTURALLY DISCRIMINANT FEATURES IN 3D ................................1912FACESSreenivas Sukumar, Hamparsum Bozdogan, David Page, Andreas Koschan, Mongi Abidi, University of Tennessee, Knoxville, United States
TP-PC.4: ENHANCED FACE RECOGNITION USING TENSOR .........................................................1916NEIGHBORHOOD PRESERVING DISCRIMINANT PROJECTIONSJiwen Lu, Yap-peng Tan, Nanyang Technological University, Singapore
TP-PC.5: MATCHING TEXTURE UNITS FOR FACE RECOGNITION ..............................................1920Bangpeng Yao, Haizhou Ai, Tsinghua University, China; Shihong Lao, Omron Corporation, Japan
TP-PC.6: DISCRIMINANT SPECTRAL ANALYSIS FOR FACIAL EXPRESSION ...........................1924RECOGNITIONRuicong Zhi, Qiuqi Ruan, Beijing Jiaotong University, China
TP-PC.7: LEARNING EFFICIENT CODES FOR 3D FACE RECOGNITION ......................................1928Cheng Zhong, Zhenan Sun, Tieniu Tan, Chinese Academy of Sciences, China
TP-PC.8: FACE INDEXING AND SEARCHING FROM VIDEOS ..........................................................1932Jiangwei Li, Yunhong Wang, Beihang University, China
TP-PD: STEREO AND 3D V
TP-PD.1: PRACTICAL PTZ CAMERA CALIBRATION USING GIVENS ..........................................1936ROTATIONSImran Junejo, INRIA, France; Hassan Foroosh, University of Central Florida, United States
TP-PD.2: OPTIMAL SPECTRAL AND SPATIAL WEIGHTS FOR ......................................................1940PHOTOMETRIC STEREO FOR ACCURATE SHAPE RECONSTRUCTIONOsamu Ikeda, Takushoku University, Japan; Ye Duan, university of missouri, United States
TP-PD.3: PICTURE-LEVEL ADAPTIVE FILTER FOR ASYMMETRIC ............................................1944STEREOSCOPIC VIDEOYing Chen, Tampere University of Technology, Finland; Ye-Kui Wang, Miska M. Hannuksela, Nokia Inc., Finland; Moncef Gabbouj, Tampere University of Technology, Finland
TP-PD.4: DECOMPOSITION OF BRANCHING VOLUME DATA BY TIP .........................................1948DETECTIONWei Ma, Key Laboratory of Machine Perception (Ministry of Education), Peking University, China; Bo Xiang, Xiaopeng Zhang, LIAMA-NLPR, CAS Institute of Automation, China; Hongbin Zha, Key Laboratory of Machine Perception (Ministry of Education), Peking University, China
TP-PD.5: FINDING BEST FOCUSED POINTS USING INTERSECTION OF .....................................1952TWO LINESAamir Malik, Tae-Sun Choi, Gwangju Institute of Science and Technology, Republic of Korea
TP-PD.6: GRID POINT EXTRACTION EXPLOITING POINT SYMMETRY ....................................1956IN A PSEUDO-RANDOM COLOR PATTERNZhan Song, Ronald Chung, Chinese University of Hong Kong, Hong Kong SAR of China
TP-PD.7: MULTI-SCALE CREASES DETECTION ON NOISY MESHES ...........................................1960Tao Luo, Hongbin Zha, Peking University, China
TP-PD.8: DEALING WITH DEGENERACY IN ESSENTIAL MATRIX ..............................................1964ESTIMATIONPeter Decker, Dietrich Paulus, University of Koblenz-Landau, Germany; Tobias Feldmann, University of Karlsruhe (TH), Germany
TP-PD.9: CALIBRATION OF TIME-OF-FLIGHT RANGE IMAGING CAMERAS ...........................1968Olivier Steiger, ABB Switzerland Inc., Switzerland; Judith Felder, Stephan Weiss, Swiss Federal Institute of Technology (ETH), Switzerland
TP-PD.10: A REAL-TIME AUGMENTED VIEW SYNTHESIS SYSTEM FOR ...................................1972TRANSPARENT CAR PILLARSYu-Lin Chang, Yi-Min Tsai, Liang-Gee Chen, National Taiwan University, Taiwan
TP-PD.11: A LIGHTWEIGHT MULTIVIEW TRACKED PERSON .....................................................1976DESCRIPTOR FOR CAMERA SENSOR NETWORKSMichael Quinn, Thomas Kuo, B. S. Manjunath, University of California, Santa Barbara, United States
TP-PE: MOTION DETECTION AND ESTIMATION III
TP-PE.1: ON MODELING GENETIC PATTERN SEARCH FOR BLOCK ..........................................1980MOTION ESTIMATIONJang-Jer Tsai, Hsueh-Ming Hang, National Chiao-Tung University, Taiwan
TP-PE.2: AN EFFECTIVE SUCCESSIVE ELIMINATION ALGORITHM FOR ................................1984FAST OPTIMAL BLOCK-MATCHING MOTION ESTIMATIONHwal-Suk Lee, Jik-Han Jung, Dong-Jo Park, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
TP-PE.3: A MOTION VECTOR DIFFERENCE BASED SELF-INCREMENTAL ..............................1988ADAPTIVE SEARCH RANGE ALGORITHM FOR VARIABLE BLOCK SIZE MOTION ESTIMATIONZhenxing Chen, Qin Liu, Takeshi Ikenaga, Satoshi Goto, Waseda University, Japan
TP-PE.4: EFFICIENT MOTION ESTIMATION UNDER VARYING ...................................................1992ILLUMINATIONYilei Xu, Amit Roy-Chowdhury, University of California, Riverside, United States
TP-PE.5: FAST MOTION ESTIMATION ALGORITHM USING UNEQUAL .....................................1996SEARCH EFFORT FOR H.264|MPEG-4 AVC ENCODERYinqing Zhao, Krit Panusopone, Limin Wang, Motorola, Inc., United States
TP-PE.6: FAST DISPARITY MOTION ESTIMATION IN MVC BASED ON ......................................2000RANGE PREDICTIONXiaozhong Xu, Yun He, Tsinghua University, China
TP-PE.7: EFFICIENT IMAGE MATCHING USING CONCENTRIC ...................................................2004SAMPLING FEATURES AND BOOSTING PROCESSPing Wu, JunWei Hsieh, Yuan Ze University, Taiwan
TP-PE.8: ON-BOARD ROBUST VEHICLE DETECTION AND TRACKING .....................................2008USING ADAPTIVE QUALITY EVALUATIONJon Arróspide, Luis Salgado, Marcos Nieto, Fernando Jaureguizar, Universidad Politécnica de Madrid, Spain
TP-PE.9: ADAPTIVE FEATURE-SPATIAL REPRESENTATION FOR ..............................................2012MEAN-SHIFT TRACKERYing Shi, Hong Liu, Yi Liu, Hongbin Zha, Key Laboratory of Machine Perception and Intelligent, Peking University, China
TP-PF: IMAGE & VIDEO COMMUNICATIONS I
TP-PF.1: ERROR RESILIENT JPEG2000 DECODING FOR WIRELESS ...........................................2016APPLICATIONSSimone Zezza, Politecnico di Torino, Italy; Saeid Nooshabadi, Gwangju Institute of Science and Technology, Republic of Korea; Maurizio Martina, Guido Masera, Politecnico di Torino, Italy
TP-PF.2: LAYERED WIRELESS VIDEO MULTICAST USING ...........................................................2020DIRECTIONAL RELAYSOzgu Alay, Thanasis Korakis, Yao Wang, Shivendra Panwar, Polytechnic University, United States
TP-PF.3: ENHANCING VIDEO QUALITY FOR MULTIPLE-DESCRIPTION ..................................2024MIMO TRANSMISSION THROUGH UNEQUAL POWER ALLOCATION BETWEEN EIGEN-MODESMilos Tesanovic, David Bull, Angela Doufexi, University of Bristol, United Kingdom
TP-PF.4: VIDEO STREAMING OVER WIRELESS DCCP......................................................................2028Burak Görkemli, M. Oguz Sunay, A. Murat Tekalp, Koç University, Turkey
TP-PF.5: RATE-DISTORTION ANALYSIS OF WEIGHTED PREDICTION ......................................2032FOR ERROR RESILIENCEYuxin (Zoe) Liu, Hewlett-Packard Company, United States; Ragip Kurceren, Nokia Inc., United States; Debargha Mukherjee, Hewlett-Packard Company, United States
TP-PF.6: INVISIBLE BARCODE WITH OPTIMIZED ERROR ............................................................2036CORRECTIONKoichi Kamijo, Noboru Kamijo, Zhang Gang, IBM, Japan
TP-PF.7: MULTIPLE DESCRIPTION BASED IMAGE TRANSMISSION WITH ..............................2040LOW DENSITY PARITY CHECK CODESGrigorios Tsagkatakis, Rochester Institute of Technology, United States; Michalis Zervakis, Technical University of Crete, Greece; Andreas Savakis, Rochester Institute of Technology, United States
TP-PF.8: LOW COMPLEXITY M-CHANNEL MULTIPLE DESCRIPTION ......................................2044CODING WITH TWO-RATE PREDICTIVE CODING AND STAGGERED QUANTIZATIONUpul Samarawickrama, Jie Liang, Simon Fraser University, Canada
TP-PF.9: 3GPP MBMS MOBILE-TV SERVICES USING H.264/AVC ...................................................2048TEMPORAL SCALABILITY AND LAYERED TRANSMISSIONCornelius Hellge, Thomas Schierl, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany; Joerg Huschke, Thomas Rusert, Markus Kampmann, Ericsson GmbH, Germany; Thomas Wiegand, Technical University Berlin/Fraunhofer HHI, Germany
TP-PF.10: FAST INDEX ASSIGNMENT FOR ROBUST MULTIPLE ...................................................2052DESCRIPTION CODINGRui Ma, Fabrice Labeau, McGill University, Canada
TP-PF.11: MULTIPLE DISTORTION MEASURES FOR VIDEO WITH .............................................2056TEMPORAL SCALABILITYCarri Chan, Stanford University, United States; Susie Wee, Hewlett-Packard Company, United States; John Apostolopoulos, Hewlett-Packard Laboratories, United States
TP-PF.12: PROPOSAL OF NEW QOE ASSESSMENT APPROACH FOR ...........................................2060QUALITY MANAGEMENT OF IPTV SERVICESKeishiro Watanabe, Kazuhisa Yamagishi, Jun Okamoto, Akira Takahashi, NTT, Japan
TP-PG: STEGANOGRAPHY & STEGANALYSIS II
TP-PG.1: BLIND IMAGE STEGANALYSIS BASED ON RUN-LENGTH ............................................2064HISTOGRAM ANALYSISJing Dong, Tieniu Tan, Institute of Automation, Chinese Academy of Sciences, China
TP-PG.2: UNIVERSAL JPEG STEGANALYSIS BASED ON MICROSCOPIC ...................................2068AND MACROSCOPIC CALIBRATIONFangjun Huang, Bin Li, Jiwu Huang, Sun Yat-Sen University, China
TP-PG.3: A FURTHER STUDY ON STEGANALYSIS OF LSB MATCHING .....................................2072BY CALIBRATIONXiaolong Li, Peking University, China; Tieyong Zeng, Ecole Normale Superieure de Cachan, France; Bin Yang, Peking University, China
TP-PG.4: MULTI-CLASS STEGANALYSIS FOR JPEG STEGO ALGORITHMS ..............................2076Ping Wang, Fenlin Liu, Guodong Wang, Yifeng Sun, Daofu Gong, Institute of Information Science and Technology, China
TP-PG.5: AN EFFICIENT PRINT-SCANNING RESILIENT DATA HIDING .....................................2080SCHEME BASED ON A NOVEL LPMXiangui Kang, Xiong Zhong, Jiwu Huang, Sun Yat-sen University, China; Wenjun Zeng, University of Missouri-Columbia, United States
TP-PG.6: A STUDY ON SECURITY PERFORMANCE OF YASS ..........................................................2084Fangjun Huang, Sun Yat-Sen University, China; Yun Q. Shi, New Jersey Institute of Technology, United States; Jiwu Huang, Sun Yat-Sen University, China
TP-PG.7: CREATING A FACE MODEL FROM AN UNKNOWN SKULL ..........................................2088BASED ON THE TISSUE MAPYuru Pei, Hongbin Zha, Peking University, China; Zhongbiao Yuan, Guangzhou Police Station, China
TP-PG.8: LOCALIZATION OF SPARSE IMAGE TAMPERING VIA RANDOM ..............................2092PROJECTIONSMarco Tagliasacchi, Giuseppe Valenzise, Stefano Tubaro, Politecnico di Milano, Italy
TP-PH: VIDEO COMPRESSION STANDARDS I
TP-PH.1: PARALLEL CABAC FOR LOW POWER VIDEO CODING .................................................2096Vivienne Sze, Massachusetts Institute of Technology, United States; Madhukar Budagavi, Texas Instruments, United States; Anantha Chandrakasan, Massachusetts Institute of Technology, United States; Minhua Zhou, Texas Instruments, United States
TP-PH.2: AN ENHANCED RATE CONTROL SCHEME WITH MOTION .........................................2100ASSISTED SLICE GROUPING FOR LOW BIT RATE CODING IN H.264Avin Kumar Kannur, Baoxin Li, Arizona State University, United States
TP-PH.3: RATE-VISUAL-DISTORTION OPTIMIZED EXTRACTION WITH ..................................2104QUALITY LAYERS FOR SCALABLE CODING OF STEREO VIDEOSNukhet Ozbek, Yasar University, Turkey; A. Murat Tekalp, Koç University, Turkey
TP-PH.4: DYNAMIC TRANSFORM REPLACEMENT IN AN H.264 CODEC .....................................2108Iain Richardson, Robert Gordon University, United Kingdom; Maja Bystrom, Boston University, United States; Manuel de-Frutos-Lopez, Universidad Carlos III de Madrid, Spain; Chaminda Sampath Kannangara, Robert Gordon University, United Kingdom
TP-PH.5: AN H.264 WEIGHTED PREDICTION PARAMETER ESTIMATION ................................2112METHOD FOR FADE EFFECTS IN VIDEO SCENESHirofumi Aoki, Yoshihiro Miyamoto, NEC Corporation, Japan
TP-PH.6: IMPROVED H.264 INTRA CODING BASED ON BI-DIRECTIONAL ................................2116INTRA PREDICTION, DIRECTIONAL TRANSFORM, AND ADAPTIVE COEFFICIENT SCANNINGYan Ye, Marta Karczewicz, Qualcomm Inc., United States
TP-PH.7: A REDUCED RESOLUTION UPDATE METHOD ON TRANSFORM ...............................2120DOMAIN FOR H.264/AVCJeehong Lee, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea; Byeong-Moon Jeon, LG Electronics Inc., Republic of Korea; HyunWook Park, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
TP-PH.8: ENCODER DESIGN FOR H.264/AVC BASED ON CONTRAST ..........................................2124SENSITIVITY CONSIDERING SPATIO-TEMPORAL DIRECTION DEPENDENCYYukihiro Bandoh, Kazuya Hayase, Seishi Takamura, Kazuto Kamikura, Yoshiyuki Yashima, NTT, Japan
TP-PH.9: EXTENDING H.264/AVC WITH A BACKGROUND SPRITE ..............................................2128PREDICTION MODEMatthias Kunter, Philipp Krey, Andreas Krutz, Thomas Sikora, Technische Universität Berlin, Germany
TP-PH.10: ERROR RESILIENT MACROBLOCK RATE CONTROL FOR ........................................2132H.264/AVC VIDEO CODINGPaulo Nunes, Luis Soares, Instituto Superior de Ciências do Trabalho e da Empresa, Portugal; Fernando Pereira, Instituto Superior Técnico, Portugal
TP-PH.11: CODING-GAIN-BASED COMPLEXITY CONTROL FOR H.264 ......................................2136VIDEO ENCODERMing-Chen Chien, Zong-Yi Chen, Pao-Chi Chang, National Central University, Taiwan
TP-PH.12: MOTION ESTIMATION WITH ENTROPY CODING .........................................................2140CONSIDERATIONS IN H.264/AVCZhen Li, Alexis Tourapis, Dolby Laboratories, Inc., United States
TP-PI: IMAGE/VIDEO RETRIEVAL IV
TP-PI.1: SOBEL-LBP .....................................................................................................................................2144Sanqiang Zhao, Yongsheng Gao, Baochang Zhang, Griffith University, Australia
TP-PI.2: MULTI-CONCEPT LEARNING WITH LARGE-SCALE ........................................................2148MULTIMEDIA LEXICONSLexing Xie, Rong Yan, IBM Research, United States; Jun Yang, Carnegie Mellon University, United States
TP-PI.3: STRATEGY OF COMBINING RANDOM SUBSPACE AND ..................................................2152DIVERSIFIED ACTIVE LEARNING IN CBIRFang Wang, Zhenfeng Zhu, Yao Zhao, Beijing Jiaotong University, China
TP-PI.4: ROBUST VIDEO FINGERPRINTING BASED ON 2D-OPCA OF .........................................2156AFFINE COVARIANT REGIONSSunil Lee, Chang D. Yoo, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
TP-PI.5: MRS-MIL: MINIMUM REFERENCE SET BASED MULTIPLE ...........................................2160INSTANCE LEARNING FOR AUTOMATIC IMAGE ANNOTATIONYufeng Zhao, Yao Zhao, Zhenfeng Zhu, Beijing Jiaotong University, China; Jeng-Shyang Pan, Kaohsiung University of Applied Sciences, Taiwan
TP-PI.6: EFFICIENT INITIALIZATION OF MIXTURES OF EXPERTS FOR ..................................2164HUMAN POSE ESTIMATIONHuazhong Ning, Yuxiao Hu, Thomas Huang, University of Illinois at Urbana-Champaign, United States
TP-PI.7: GLOBAL-TO-LOCAL ORIENTED PERCEPTION ON BLURRY .........................................2168VISUAL INFORMATIONLe Dong, Ebroul Izquierdo, Queen Mary, University of London, United Kingdom
TP-PI.8: A NOVEL WARPING DISTANCE MEASURE ..........................................................................2172Yasser Ebrahim, Maher Ahmed, Siu-Cheung Chau, Wegdan Abdelsalam, Wilfrid Laurier University, Canada
WA-L1: CONNECTIVITY AND CONNECTED FILTERS
WA-L1.1: CONNECTED OPERATORS BASED ON REGION-TREES .................................................2176Philippe Salembier, Technical University of Catalonia, Spain
WA-L1.2: CONNECTED FILTERING BY RECONSTRUCTION: BASIS AND ..................................2180NEW RESULTSMichael H. F. Wilkinson, University of Groningen, Netherlands
WA-L1.3: EXTENDING CONNECTED OPERATORS TO COLOUR IMAGES ..................................2184Adrian N. Evans, David Gimenez, University of Bath, United Kingdom
WA-L1.4: OIL SAND IMAGE SEGMENTATION USING THE INCLUSION .....................................2188FILTERNilanjan Ray, Baidya Nath Saha, University of Alberta, Canada; Scott T. Acton, University of Virginia, United States
WA-L1.5: CONNECTIVE SEGMENTATION ............................................................................................2192Jean Serra, University of Paris-Est, France
WA-L1.6: RAISING IN WATERSHED LATTICES...................................................................................2196Jean Cousty, INRIA, France; Laurent Najman, Jean Serra, Université Paris-Est, France
WA-L1.7: A PDE FORMULATION FOR VISCOUS MORPHOLOGICAL ..........................................2200OPERATORS WITH EXTENSIONS TO INTENSITY-ADAPTIVE OPERATORSPetros Maragos, National Technical University of Athens, Greece; Corinne Vachier, CMLA, ENS Cachan, France
WA-L2: DISTRIBUTED SOURCE CODING II
WA-L2.1: LOCALIZATION OF TAMPERING IN CONTRAST AND ..................................................2204BRIGHTNESS ADJUSTED IMAGES USING DISTRIBUTED SOURCE CODING AND EXPECTATION MAXIMIZATIONYao-Chung Lin, David Varodayan, Stanford University, United States; Torsten Fink, Erwin Bellers, NXP Semiconductors, United States; Bernd Girod, Stanford University, United States
WA-L2.2: RESOLUTION-PROGRESSIVE COMPRESSION OF ENCRYPTED ................................2208GRAYSCALE IMAGESWei Liu, Wenjun Zeng, Lina Dong, Qiuming Yao, University of Missouri, United States
WA-L2.3: DISTRIBUTED IMAGE CODING FOR IMFORMATION ...................................................2212RECOVERY FROM THE PRINT-SCAN CHANNELDebargha Mukherjee, Ramin Samadani, Hewlett-Packard Laboratories, United States
WA-L2.4: SECURE COLLABORATION USING SLEPIAN-WOLF CODES ........................................2216Dake He, Ashish Jagmohan, Ligang Lu, IBM T.J. Watson Research Laboratory, United States
WA-L2.5: GEOMETRY-BASED DISTRIBUTED CODING OF MULTI-VIEW ..................................2220OMNIDIRECTIONAL IMAGESIvana Tosic, Pascal Frossard, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
WA-L2.6: COMPLEXITY REDUCTION USING POWER-LAW BASED ............................................2224SCHEDULING FOR EXPLOITING SPATIAL CORRELATION IN DISTRIBUTED VIDEO CODINGKiran Misra, Shirish Karande, Keyur Desai, Hayder Radha, Michigan State University, United States
WA-L2.7: IMPROVED SIDE INFORMATION GENERATION WITH ................................................2228ITERATIVE DECODING AND FRAME INTERPOLATION FOR DISTRIBUTED VIDEO CODINGShuiming Ye, Mourad Ouaret, Frederic Dufaux, Touradj Ebrahimi, Swiss Federal Institute of Technology, Lausanne (EPFL), Switzerland
WA-L2.8: A CONCEALMENT BASED APPROACH TO DISTRIBUTED VIDEO .............................2232CODINGNantheera Anantrasirichai, Dimitris Agrafiotis, David Bull, University of Bristol, United Kingdom
WA-L3: MAGNETIC RESONANCE IMAGING
WA-L3.1: COMBINATION OF MR SURFACE COIL IMAGES USING ..............................................2236WEIGHTED CONSTRAINED LEAST SQUARESSevket Derin Babacan, Xiaoming Yin, Andrew C. Larson, Aggelos K. Katsaggelos, Northwestern University, United States
WA-L3.2: SAMPLING STRATEGIES FOR SUPER-RESOLUTION IN ...............................................2240MULTI-SLICE MRIRichard Shilling, Georgia Institute of Technology, United States; Senthil Ramamurthy, Children’s Healthcare of Atlanta, United States; Marijn Brummer, Emory University, United States
WA-L3.3: AUTOMATED MAGNETIC RESONANCE ASSISTED ........................................................2244ECHOCARDIOGRAPHIC MOTION ANALYSISAndrew D. Gilliam, John A. Hossack, Frederick H. Epstein, Brent A. French, Scott T. Acton, University of Virginia, United States
WA-L3.4: CORONARY ARTERY EXTRACTION AND ANALYSIS FOR ..........................................2248DETECTION OF SOFT PLAQUES IN MDCT IMAGESFélix Renard, Laboratoire des Sciences de l’Images, de l’Informatique et de la Télédétection, France; Yongyi Yang, Illinois Institute of Technology, United States
WA-L3.5: SHAPE ANALYSIS OF BRAIN VENTRICLES FOR IMPROVED ......................................2252CLASSIFICATION OF ALZHEIMER’S PATIENTSJingnan Wang, Ahmet Ekin, Gerard de Haan, Philips Research, Netherlands
WA-L3.6: AUTOMATIC LIVER TUMOR DIAGNOSIS WITH .............................................................2256DYNAMIC-CONTRAST ENHANCED MRILiliana Caldeira, Isabela Silva, João Sanches, Instituto de Sistemas e Robótica / Instituto Superior Técnico, Portugal
WA-L3.7: EVALUATION OF IMAGE QUALITY METRICS FOR COMPARISON ..........................2260OF SYNCHRONIZATION ALGORITHMS FOR CARDIAC CINE MRIGrace M. Nijm, Steven Swiryn, Andrew C. Larson, Alan V. Sahakian, Northwestern University, United States
WA-L3.8: VELOCITY GUIDED SEGMENTATION OF PHASE CONTRAST ....................................2264MAGNETIC RESONANCE ANGIOGRAPHYRobert L. Janiczek, Frederick H. Epstein, Scott T. Acton, University of Virginia, United States
WA-L4: IMAGE SEGMENTATION IV
WA-L4.1: A COVARIANCE ADJUSTMENT METHOD IN COMPRESSED .......................................2268DOMAIN FOR NOISY IMAGE SEGMENTATIONKyungsuk Pyun, Hewlett-Packard Company, United States; Johan Lim, Yonsei University, Republic of Korea; Robert M. Gray, Stanford University, United States
WA-L4.2: REGION-BASED IMAGE SEGMENTATION VIA GRAPH CUTS ......................................2272Cevahir Cigla, A. Aydin Alatan, Middle East Technical University, Turkey
WA-L4.3: FREQUENTIAL AND COLOR ANALYSIS FOR HAIR MASK ...........................................2276SEGMENTATIONCedric Rousset, Pierre Yves Coulon, GIPSA-Lab, France
WA-L4.4: AN AUTOMATED SEGMENTATION FOR NICKEL-BASED ............................................2280SUPERALLOYHsiao-Chiang Chuang, Landis Huffman, Mary Comer, Purdue University, United States; Jeff Simmons, Air Force Research Laboratory, United States; Ilya Pollak, Purdue University, United States
WA-L4.5: SHAPE PRIOR BASED ON STATISTICAL MAP FOR ACTIVE ........................................2284CONTOUR SEGMENTATIONNawal Houhou, Alia Lemkaddem, Valerie Duay, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland; Abdelkarim Allal, HUG, Switzerland; Jean-Philippe Thiran, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
WA-L4.6: STOCHASTIC IMAGE SEGMENTATION BY COMBINING .............................................2288REGION AND EDGE CUESOlfa Besbes, URISA-SUPCOM and IMEDIA-INRIA, Tunisia; Nozha Boujemaa, IMEDIA-INRIA, France; Ziad Belhadj, URISA-SUPCOM, Tunisia
WA-L4.7: AUGMENTED TREE PARTITIONING FOR INTERACTIVE IMAGE .............................2292SEGMENTATIONYangqing Jia, Tsinghua University, China; Jingdong Wang, Microsoft Research Asia, China; Changshui Zhang, Tsinghua University, China; Xian-Sheng Hua, Microsoft Research Asia, China
WA-L5: IMAGE & VIDEO COMMUNICATIONS II
WA-L5.1: PEER-TO-PEER MULTICAST LIVE VIDEO STREAMING WITH ..................................2296INTERACTIVE VIRTUAL PAN/TILT/ZOOM FUNCTIONALITYAditya Mavlankar, Jeonghun Noh, Pierpaolo Baccichet, Bernd Girod, Stanford University, United States
WA-L5.2: ENHANCING PEER-TO-PEER LIVE MULTICAST QUALITY .........................................2300USING HELPERSJiajun Wang, Kannan Ramchandran, University of California, Berkeley, United States
WA-L5.3: RECEIVER DRIVEN LAYERED MULTICAST WITH ........................................................2304LAYER-AWARE FORWARD ERROR CORRECTIONCornelius Hellge, Thomas Schierl, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany; Thomas Wiegand, Technical University Berlin/Fraunhofer HHI, Germany
WA-L5.4: MACROBLOCK-BASED RETRANSMISSION FOR .............................................................2308ERROR-RESILIENT VIDEO STREAMINGJochen Christian Schmidt, Kenneth Rose, University of California, Santa Barbara, United States
WA-L5.5: RATE-DISTORTION OPTIMIZED DELIVERY OF JPEG2000 ..........................................2312COMPRESSED VIDEO WITH HIERARCHICAL MOTION SIDE INFORMATIONAous Naman, David Taubman, University of New South Wales, Australia
WA-L5.6: DYNAMIC CHANNEL SELECTION FOR MULTI-USER VIDEO .....................................2316STREAMING OVER COGNITIVE RADIO NETWORKSHsien-Po Shiang, Mihaela Van der Schaar, University of California, Los Angeles, United States
WA-L5.7: NETWORK-ADAPTIVE TRANSPORT OF MOTION-COMPENSATED ..........................2320FINE GRANULARITY SCALABILITY VIDEO USING MULTIPLE ASYMMETRIC PATHSDian Fan, University of Miami, United States; Yee Sin Chan, Verizon Wireless, United States; Xunqi Yu, Microsoft, United States; James W. Modestino, University of Miami, United States
WA-L5.8: NO-REFERENCE MODELING OF THE CHANNEL INDUCED ........................................2324DISTORTION AT THE DECODER FOR H.264/AVC VIDEO CODINGMatteo Naccari, Marco Tagliasacchi, Politecnico di Milano, Italy; Fernando Pereira, Instituto Superior Técnico, Portugal; Stefano Tubaro, Politecnico di Milano, Italy
WA-PA: MULTIRESOLUTION PROCESSING
WA-PA.1: 2-D ANISOTROPIC DUAL-TREE COMPLEX WAVELET PACKETS .............................2328AND ITS APPLICATION TO IMAGE DENOISINGJingyu Yang, Wenli Xu, Tsinghua University, China; Yao Wang, Polytechnic University, United States; Qionghai Dai, Tsinghua University, China
WA-PA.2: PHOTON-LIMITED IMAGE DENOISING BY INFERENCE ON ......................................2332MULTISCALE MODELSStamatios Lefkimmiatis, George Papandreou, Petros Maragos, National Technical University of Athens, Greece
WA-PA.3: AN EFFECTIVE DETECTION METHOD OF ROTATIONAL AND .................................2336DIVERGENT STRUCTURES IN STILL IMAGES BASED ON HELMHOLTZ DECOMPOSITIONNorihiro Kakukou, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan
WA-PA.4: VIDEO DENOISING USING 3-D HYBRID WAVELETS AND ...........................................2340DIRECTIONAL FILTER BANKSRamin Eslami, University of Rochester, United States; Xiaolin Wu, McMaster University, Canada
WA-PA.5: IMPROVED PRECISION OF FIXED-POINT ALGORITHMS BY .....................................2344MEANS OF COMMON FACTORSYuriy Reznik, Stanford University, United States; Arianne Hinds, Joan Mitchell, InfoPrint Solutions Company, United States
WA-PA.6: CORRELATED NON-LINEAR WAVELET SHRINKAGE ...................................................2348Mehdi Amiri, Zohreh Azimifar, Shiraz University, Iran; Paul Fieguth, University of Waterloo, Canada
WA-PB: OBJECT RECOGNITION
WA-PB.1: EDGE-BASED SYNTHETIC DISCRIMINANT FUNCTION FOR ......................................2352DISTORTION INVARIANT OBJECT RECOGNITIONHaidong Yuan, Huadong Ma, Xiaodong Huang, Beijing University of Posts and Telecommunications, China
WA-PB.2: LASIC: A MODEL INVARIANT FRAMEWORK FOR ........................................................2356CORRESPONDENCEBernardo Rodrigues Pires, José M. F. Moura, Carnegie Mellon University, United States; João Xavier, Technical University of Lisbon, Portugal
WA-PB.3: CLASSIFICATION OF UNLABELED POINT SETS USING ANSIG ..................................2360José Rodrigues, João Xavier, Pedro Aguiar, Institute for Systems and Robotics, Portugal
WA-PB.4: OBJECT DETECTION FOR DYNAMIC ADAPTATION OF ..............................................2364INTERCONNECTIONS IN INKJET PRINTED ELECTRONICSHeikki Huttunen, Pekka Ruusuvuori, Tapio Manninen, Kalle Rutanen, Tampere University of Technology, Finland; Risto Rönkkä, Nokia Research Center, Finland; Ari Visa, Tampere University of Technology, Finland
WA-PB.5: PROBABILISTIC GRAPH MATCHING BY CANONICAL .................................................2368DECOMPOSITIONHaytham Yaghi, Hamid Krim, North Carolina State University, United States
WA-PB.6: DETECTING POLYGONS OF VARIABLE DIMENSION IN ..............................................2372OVERHEAD IMAGES WITH PARTICLE FILTERSSiddharth Manay, David Paglieroni, Lawrence Livermore National Laboratory, United States
WA-PB.7: LOCALIZATION OF DETECTED OBJECTS IN MULTI-CAMERA ................................2376NETWORKRoland Miezianko, Honeywell, United States; Dragoljub Pokrajac, Delaware State University, United States
WA-PB.8: USING LOCAL REGRESSION KERNELS FOR STATISTICAL .......................................2380OBJECT DETECTIONHae Jong Seo, Peyman Milanfar, University of California, Santa Cruz, United States
WA-PB.9: MOBILE OBJECT RECOGNITION USING MULTI-SENSOR ...........................................2384INFORMATION FUSION IN URBAN ENVIRONMENTSKatrin Amlacher, Patrick Luley, Gerald Fritz, Alexander Almer, Lucas Paletta, Joanneum Research, Austria
WA-PB.10: IMPLICIT SPATIAL INFERENCE WITH SPARSE LOCAL ............................................2388FEATURESDeirdre O’Regan, Anil Kokaram, Trinity College Dublin, Ireland
WA-PB.11: VISUAL PEDESTRIAN RECOGNITION IN WEAK CLASSIFIER ..................................2392SPACE USING NONLINEAR PARAMETRIC MODELSLaetitia Leyrit, Thierry Chateau, Christophe Tournayre, Jean-Thierry Lapresté, LASMEA, UMR 6602 CNRS & Blaise Pascal University, France
WA-PB.12: ROBUST MULTIPLE LANE ROAD MODELING BASED ON .........................................2396PERSPECTIVE ANALYSISMarcos Nieto, Luis Salgado, Fernando Jaureguizar, Jon Arróspide, Universidad Politécnica de Madrid, Spain
WA-PC: REGISTRATION
WA-PC.1: ELASTIC REGISTRATION FOR STENT ENHANCEMENT IN ........................................2400X-RAY IMAGE SEQUENCESVincent Bismuth, Régis Vaillant, GE Healthcare, France
WA-PC.2: IMAGE REGISTRATION USING SUBPIXEL-SHIFTED IMAGES ...................................2404FOR SUPER-RESOLUTIONHidenori Takeshima, Toshimitsu Kaneko, Toshiba corporation, Japan
WA-PC.3: FAST FLUID EXTENSIONS FOR IMAGE REGISTRATION .............................................2408ALGORITHMSJens-Peer Kuska, University Leipzig, Germany; Patrick Scheibe, Translational Centre for Regenerative Medicine, Germany; Ulf-Dietrich Braumann, University Leipzig, Germany
WA-PC.4: EXPLOITING LOCAL AUTO-CORRELATION FUNCTION FOR ...................................2412FAST VIDEO TO REFERENCE IMAGE ALIGNMENTArif Mahmood, Sohaib Khan, Lahore University of Management Sciences, Pakistan
WA-PC.5: IMAGE REGISTRATION USING ADAPTIVE POLAR TRANSFORM .............................2416Rittavee Matungka, Yuan F. Zheng, The Ohio State University, United States; Robert L. Ewing, Air Force Research Laboratory, United States
WA-PC.6: IMPROVEMENT OF ACCURACY IN DEFORMABLE .......................................................2420REGISTRATION IN RADIATION THERAPYXiaojing Ye, Yunmei Chen, University of Florida, United States
WA-PD: STEREO AND 3D VI
WA-PD.1: INTER-VIEW CODING FOR STEREOSCOPIC DIGITAL CINEMA ................................2424Guillaume Boisson, Patrick Lopez, Thomson R&D France, France
WA-PD.2: RATE-DISTORTION PERFORMANCE OF MULTI-VIEW IMAGE .................................2428CODING WITH SUBSAMPLING OF VIEWPOINTSMasato Ishii, Keita Takahashi, Takeshi Naemura, University of Tokyo, Japan
WA-PD.3: DISTRIBUTED 3D DYNAMIC MESH CODING ....................................................................2432M. Oguz Bici, Gozde Bozdagi Akar, Middle East Technical University, Turkey
WA-PD.4: DISPLAY DEPENDENT CODING FOR 3D VIDEO ON .......................................................2436AUTOMULTISCOPIC DISPLAYSVikas Ramachandra, Matthias Zwicker, Truong Nguyen, University of California, San Diego, United States
WA-PD.5: COMPRESSION OF 2-D WIDE MULTI-VIEW VIDEO .......................................................2440SEQUENCES USING VIEW INTERPOLATIONTaeyoung Chung, Kwanwoong Song, Chang-su Kim, Korea University, Republic of Korea
WA-PD.6: PSEUDO DISPARITY BASED STEREO IMAGE CODING .................................................2444Xiaoyan Yu, Xianwei Rong, Harbin Normal University, China
WA-PD.7: INTERMEDIATE VIEW INTERPOLATION BASED ON ...................................................2448MULTIVIEW VIDEO PLUS DEPTH FOR ADVANCED 3D VIDEO SYSTEMSAljoscha Smolic, Karsten Müller, Kristina Dix, Philipp Merkle, Peter Kauff, Thomas Wiegand, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany
WA-PD.8: MOTION COMPENSATION BASED ON IMPLICIT BLOCK ............................................2452SEGMENTATIONJae Hoon Kim, Antonio Ortega, University of Southern California, United States; Peng Yin, Purvin Pandit, Cristina Gomila, Thomson, United States
WA-PD.9: ADAPTIVE REFERENCE FILTERING FOR BIDIRECTIONAL ......................................2456DISPARITY COMPENSATION WITH FOCUS MISMATCHESPoLin Lai, Antonio Ortega, University of Southern California, United States; Purvin Pandit, Peng Yin, Cristina Gomila, Thomson Corporate Research, United States
WA-PE: VIDEO COMPRESSION STANDARDS II
WA-PE.1: AN EFFICIENT FREQUENCY DOMAIN INTRA PREDICTION FOR .............................2460H.264/AVCMohsen Shaaban, Magdy Bayoumi, University of Louisiana at Lafayette, United States
WA-PE.2: FAST ADAPTIVE EARLY TERMINATION FOR MODE SELECTION ...........................2464IN H.264 SCALABLE VIDEO CODINGJianfeng Ren, Nasser Kehtarnavaz, University of Texas at Dallas, United States
WA-PE.3: JOINT CODING OF MULTI-VIEW VIDEO AND .................................................................2468CORRESPONDING DEPTH MAPSang-Tae Na, Kwan-Jung Oh, Yo-Sung Ho, Gwangju Institute of Science and Technology (GIST), Republic of Korea
WA-PE.4: ADVANCED BITSTREAM REWRITING FROM H.264/AVC TO SVC ..............................2472Jan De Cock, Stijn Notebaert, Peter Lambert, Rik Van de Walle, Ghent University - IBBT, Belgium
WA-PE.5: MULTIDIMENSIONAL SVC BITSTREAM ADAPTATION AND ......................................2476EXTRACTION FOR RATE-DISTORTION OPTIMIZED HETEROGENEOUS MULTICASTING AND PLAYBACKWen-Hsiao Peng, John Zao, Hsueh-Ting Huang, Tse-Wei Wang, National Chiao Tung University, Taiwan; Lun-Chia Kuo, Industrial Technology Research Institute, Taiwan
WA-PE.6: ON OPTIMAL ROYALTY COSTS FOR VIDEO COMPRESSION .....................................2480Ankur Saxena, University of California, Santa Barbara, United States; Onur Guleryuz, Reha Civanlar, DoCoMo Communication Laboratories USA, Inc., United States
WA-PE.7: BUFFER CONSTRAINED RATE CONTROL FOR LOW BITRATE .................................2484DUAL-FRAME VIDEO CODINGMayank Tiwari, Theodore Groves, Pamela Cosman, University of California, San Diego, United States
WA-PE.8: THREE-DIMENSIONAL POSITION AND AMPLITUDE VLC ..........................................2488CODING IN H.264/AVCJunlin Li, Ghassan AlRegib, Georgia Institute of Technology, United States; Dihong Tian, Pi Sheng Chang, Wen H. Chen, Cisco Systems, Inc., United States
WA-PE.9: ATOMIC DECOMPOSOTION DEDICATED TO AVC AND SPATIAL ............................2492SVC PREDICTIONAurélie Martin, IRISA / Thomson, France; Jean-Jacques Fuchs, Christine Guillemot, IRISA, France; Dominique Thoreau, Thomson, France
WA-PE.10: A NEW SOURCE MODEL AND ACCURATE RATE CONTROL ....................................2496ALGORITHM WITH QP AND ROUNDING OFFSET ADAPTATIONQian Xu, Thomson, United States; Yali Liu, University of California, Davis, United States; Xiaoan Lu, Cristina Gomila, Thomson, United States
WA-PE.11: SEPARABLE ADAPTIVE INTERPOLATION FILTER FOR VIDEO ..............................2500CODINGSteffen Wittmann, Thomas Wedi, Panasonic R&D Center Germany, Germany
WA-PE.12: COMPLEXITY MODELING OF SPATIAL AND TEMPORAL ........................................2504COMPENSATIONS IN H.264/AVC DECODINGSzu-Wei Lee, C.-C. Jay Kuo, University of Southern California, United States
WA-PF: IMAGE/VIDEO RETRIEVAL V
WA-PF.1: SHOT CLASSIFICATION FOR ACTION MOVIES BASED ON .........................................2508MOTION CHARACTERISTICSShuhui Wang, Shuqiang Jiang, QingMing Huang, Key Lab of Intell. Info. Process., Chinese Academy of Sciences, China; Wen Gao, Institute of Computing Technology, Chinese Academy of Sciences, China
WA-PF.2: SHOT-BASED SIMILARITY MEASURE FOR CONTENT-BASED ...................................2512VIDEO SUMMARIZATIONYue Gao, Qionghai Dai, Tsinghua University, China
WA-PF.3: FLEXIBLE GENERATION OF VIDEO SUMMARIES FROM ............................................2516LAYERED VIDEO BIT-STREAMSJanko Calic, Marta Mrak, Ahmet Kondoz, University of Surrey, United Kingdom
WA-PF.4: ROBUST DETECTION OF KEY CAPTIONS FOR SPORTS VIDEO .................................2520UNDERSTANDINGCheolkon Jung, Suyoung Lee, Joongkyu Kim, Sungkyunkwan University, Republic of Korea
WA-PF.5: MARKOV CHAIN LOCAL BINARY PATTERN AND ITS ..................................................2524APPLICATION TO VIDEO CONCEPT DETECTIONWeixin Wu, Jianguo Li, Tao Wang, Yimin Zhang, Intel China Research Center, China
WA-PF.6: MOVIE SUMMARIZATION BASED ON AUDIOVISUAL SALIENCY .............................2528DETECTIONGeorgios Evangelopoulos, Konstantinos Rapantzikos, National Technical University of Athens, Greece; Alexandros Potamianos, Technical University of Crete, Greece; Petros Maragos, Nancy Zlatintsi, Yannis Avrithis, National Technical University of Athens, Greece
WA-PF.7: AN EXPERIMENTAL STUDY ON DISCRIMINATIVE CONCEPT ...................................2532CLASSIFIER COMBINATION FOR TRECVID HIGH-LEVEL FEATURE EXTRACTIONByungki Byun, Chengyuan Ma, Chin-Hui Lee, Georgia Institute of Technology, United States
WA-PF.8: SCENE CATEGORIZATION USING BAG OF TEXTONS ON ...........................................2536SPATIAL HIERARCHYSebastiano Battiato, Giovanni Maria Farinella, Giovanni Gallo, Daniele Ravì, University of Catania, Italy
WA-PF.9: SUPPORT VECTOR MACHINES FOR ROBUST TRAJECTORY .....................................2540CLUSTERINGClaudio Piciarelli, Christian Micheloni, GianLuca Foresti, University of Udine, Italy
WA-PF.10: GENERATION OF SCALABLE SUMMARIES BASED ON ..............................................2544ITERATIVE GOP RANKINGLuis Herranz, José María Martínez, Universidad Autónoma de Madrid, Spain
WA-PF.11: A TV-LOGO CLASSIFICATION AND LEARNING SYSTEM ...........................................2548Pablo Nieto, Julian R. Cozar, Jose Maria Gonzalez-Linares, Nicolas Guil, University of Málaga, Spain
WA-PG: IMAGE/VIDEO MODELING III
WA-PG.1: CONDITIONAL ITERATIVE DECODING OF TWO ...........................................................2552DIMENSIONAL HIDDEN MARKOV MODELSMehmet Emre Sargin, Alphan Altinok, Kenneth Rose, B. S. Manjunath, University of California, Santa Barbara, United States
WA-PG.2: MARKOV MODEL OF H.264 VIDEO SOURCES PERFORMING ....................................2556BIT-RATE SWITCHINGStefania Colonnese, Gianpiero Panci, Stefano Rinauro, Gaetano Scarano, “Sapienza”, Università di Roma, Italy
WA-PG.3: SALIENCY BASED OBJECTIVE QUALITY ASSESSMENT OF .......................................2560DECODED VIDEO AFFECTED BY PACKET LOSSESXin Feng, Chongqing University, China; Tao Liu, Polytechnic University, United States; Dan Yang, Chongqing University, China; Yao Wang, Polytechnic University, United States
WA-PG.4: RATE AND DISTORTION MODELING OF MEDIUM GRAIN .........................................2564SCALABLE VIDEO CODINGHassan Mansour, Vikram Krishnamurthy, Panos Nasiopoulos, University of British Columbia, Canada
WA-PG.5: ASYMMETRICAL TEMPORAL MASKING NEAR VIDEO SCENE ................................2568CHANGEQuan Huynh-Thu, Psytechnics Ltd, United Kingdom; Mohammed Ghanbari, University of Essex, United Kingdom
WA-PG.6: CAN VISUAL FIXATION PATTERNS IMPROVE IMAGE FIDELITY ............................2572ASSESSMENT?Eric Larson, Cuong Vu, Damon Chandler, Oklahoma State University, United States
WA-PG.7: A SCALABLE COMPLEXITY SPECIFICATION FOR VIDEO .........................................2576APPLICATIONSNicholas Mastronarde, Mihaela van der Schaar, University of California, Los Angeles, United States
WA-PG.8: NON-GAUSSIAN MIXTURE IMAGE MODELS PREDICTION .........................................2580Nizar Bouguila, Concordia University, Canada
WA-PG.9: A BAYESIAN APPROACH TO PREDICTING THE PERCEIVED ....................................2584INTEREST OF OBJECTSSrivani Pinneli, Damon Chandler, Oklahoma State University, United States
WA-PG.10: A MODEL FOR IMAGE PATCH-BASED ALGORITHMS ................................................2588Karl Ni, Truong Nguyen, University of California, San Diego, United States
WA-PG.11: DETECTING IMAGE POINTS OF DIVERSE IMBALANCE ............................................2592Qi Li, Zhonghang Xia, Western Kentucky University, United States
WA-PG.12: SHAPE MATCHING USING MORPHOLOGICAL STRUCTURAL ................................2596SHAPE COMPONENTSJianning Xu, Rowan University, United States
WA-PH: RESTORATION III
WA-PH.1: A NONLOCAL-MEANS APPROACH TO EXEMPLAR-BASED ........................................2600INPAINTINGAlexander Wong, Jeff Orchard, University of Waterloo, Canada
WA-PH.2: BLIND SEPARATION OF IMAGES OBTAINED BY ...........................................................2604SPATIALLY-VARYING MIXING SYSTEMRan Kaftory, Yehoshua Zeevi, Technion - Israel Institute of Technology, Israel
WA-PH.3: ADAPTIVE TOTAL VARIATION DERINGING METHOD FOR ......................................2608IMAGE INTERPOLATIONAndrey Krylov, Andrey Nasonov, Moscow Lomonosov State University, Russian Federation
WA-PH.4: MAP-MRF APPROACH FOR BINARIZATION OF DEGRADED .....................................2612DOCUMENT IMAGEJung Gap Kuk, Nam Ik Cho, Kyoun Mu Lee, Seoul National University, Republic of Korea
WA-PH.5: AN INPAINTING SYSTEM FOR AUTOMATIC IMAGE STRUCTURE ..........................2616- TEXTURE RESTORATION WITH TEXT REMOVALEftychios Pnevmatikakis, Columbia University, United States; Petros Maragos, National Technical University of Athens, Greece
WA-PH.6: FAST DISAMBIGUATION OF SUPERIMPOSED IMAGES FOR ......................................2620INCREASED FIELD OF VIEWRoummel Marcia, Changsoon Kim, Jungsang Kim, David Brady, Rebecca Willett, Duke University, United States
WA-PH.7: NONCONVEX COMPRESSIVE SENSING AND ...................................................................2624RECONSTRUCTION OF GRADIENT-SPARSE IMAGES: RANDOM VS. TOMOGRAPHIC FOURIER SAMPLINGRick Chartrand, Los Alamos National Laboratory, United States
WA-PH.8: AUTOMATIC CONTEXT-AWARE DUST AND SCRATCH REMOVAL .........................2628IN SCANNED IMAGESPavel Kisilev, Hewlett-Packard Laboratories, Israel
WA-PI: VIDEO SEGMENTATION AND TRACKING III
WA-PI.1: OBJECT TRACKING BASED ON AREA WEIGHTED CENTROIDS ................................2632SHIFTING WITH SPATIALITY CONSTRAINTSSuk-Ho Lee, Euncheol Choi, Moon Gi Kang, Yonsei University, Republic of Korea
WA-PI.2: VISUAL TRACKING USING HIGH-ORDER MONTE CARLO ..........................................2636MARKOV CHAINPan Pan, Dan Schonfeld, University of Illinois at Chicago, United States
WA-PI.3: MULTI-OBJECT TRACKING USING BINARY MASKS ......................................................2640Sami Huttunen, Janne Heikkilä, University of Oulu, Finland
WA-PI.4: PARTICLE FILTERING AND SPARSE SAMPLING FOR ...................................................2644MULTI-PERSON 3D TRACKINGCristian Canton-Ferrer, Rossella Sblendido, Josep R. Casas, Montse Pardas, Technical University of Catalonia, Spain
WA-PI.5: A FUZZY APPROACH FOR BACKGROUND SUBTRACTION ...........................................2648Fida El Baf, Thierry Bouwmans, Bertrand Vachon, University of La Rochelle, France
WA-PI.6: ROBUST SEGMENTATION FOR OUTDOOR TRAFFIC .....................................................2652SURVEILLANCEGonçalo Monteiro, João Marcos, Miguel Ribeiro, Jorge Batista, University of Coimbra, Portugal
WA-PI.7: ROBUST 3D PEOPLE TRACKING AND POSITIONING SYSTEM ...................................2656IN A SEMI-OVERLAPPED MULTI-CAMERA ENVIRONMENTRaúl Mohedano, Carlos R. del-Blanco, Fernando Jaureguizar, Luis Salgado, Narciso García, Universidad Politécnica de Madrid, Spain
WA-PI.8: A BI-SUBSPACE MODEL FOR ROBUST VISUAL TRACKING..........................................2660Jialue Fan, Ming Yang, Ying Wu, Northwestern University, United States
WA-PI.9: AN ADAPTIVE BACKGROUND MODEL INITIALIZATION .............................................2664ALGORITHM WITH OBJECTS MOVING AT DIFFERENT DEPTHSChia-Chih Chen, J. K. Aggarwal, University of Texas at Austin, United States
WA-PI.10: MPEG VIDEO OBJECT SEGMENTATION UNDER CAMERA ........................................2668MOTION AND MULTIMODAL BACKGROUNDSMarcos Escudero, Fabrizio Tiburzi, Jesús Bescós, Universidad Autónoma de Madrid, Spain
WA-PI.11: AN EM ALGORITHM FOR ROBUST BAYESIAN PCA WITH .........................................2672STUDENT’S T-DISTRIBUTIONJiading Gai, Yong Li, Robert L. Stevenson, University of Notre Dame, United States
WP-L1: 3D GRAPHICS COMPRESSION AND STREAMING
WP-L1.1: FAMC: THE MPEG-4 STANDARD FOR ANIMATED MESH .............................................2676COMPRESSIONKhaled Mamou, Titus Zaharia, Françoise Prêteux, Institut TELECOM & Management SudParis, France
WP-L1.2: EFFICIENT REPRESENTATION AND CODING OF PREDICTION .................................2680RESIDUALS AND PARAMETERS IN FRAME-BASED ANIMATED MESH COMPRESSIONDetlev Marpe, Heiner Kirchhoffer, Karsten Mueller, Thomas Wiegand, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany
WP-L1.3: STATIC 3D TRIANGLE MESH COMPRESSION OVERVIEW ...........................................2684Marcos Avilés, Francisco Morán, Universidad Politécnica de Madrid, Spain
WP-L1.4: A MPEG-4 AFX COMPLIANT PLATFORM FOR 3D CONTENTS ....................................2688DISTRIBUTION IN PEER-TO-PEER.Romain Cavagna, (No Affiliation), France; Christian Bouville, IRISA, France; Patrick Gioia, Jerome Royan, Orange Labs, France
WP-L1.5: 3D MODEL COMPRESSION IN MPEG....................................................................................2692Eun-Young Chang, Namho Hur, Electronics and Telecommunications Research Institute, Republic of Korea; Euee S. Jang, Hanyang University, Republic of Korea
WP-L1.6: SPATIALLY AND TEMPORALLY SCALABLE COMPRESSION OF ...............................2696ANIMATED 3D MESHES WITH MPEG-4/FAMCNikolce Stefanoski, Jörn Ostermann, Leibniz Universität Hannover, Germany
WP-L1.7: MYMULTIMEDIAWORLD.COM: A BENCHMARK PLATFORM ...................................2700FOR 3D COMPRESION ALGORITHMSBenoit Le Bonhomme, Marius Preda, Françoise Prêteux, Institut TELECOM / TELECOM & Management SudParis, France
WP-L1.8: LOW DELAY STREAMING OF COMPUTER GRAPHICS ..................................................2704Peter Eisert, Philipp Fechteler, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany
WP-L2: VIDEO SEGMENTATION AND TRACKING II
WP-L2.1: ENHANCED BACKGROUND SUBTRACTION USING GLOBAL .....................................2708MOTION COMPENSATION AND MOSAICINGMichael Unger, Mark Asbach, Peter Hosten, RWTH Aachen University, Germany
WP-L2.2: REGION-BASED MEAN SHIFT TRACKING: APPLICATION TO ....................................2712FACE TRACKINGVeronica Vilaplana, Ferran Marques, Technical University of Catalonia (UPC), Spain
WP-L2.3: SEGMENTATION AND TRACKING OF STATIC AND MOVING .....................................2716OBJECTS IN VIDEO SURVEILLANCE SCENARIOSJaime Gallego, Montse Pardàs, Universitat Politècnica de Catalunya (UPC), Spain; Jose-Luis Landabaso, Telefónica I+D, Spain
WP-L2.4: HYBRID TRACKING APPROACH USING OPTICAL FLOW AND ..................................2720POSE ESTIMATIONMuriel Pressigout, IETR Image group / INSA de Rennes, France; Eric Marchand, INRIA / IRISA, France; Etienne Mémin, Université de Rennes 1/ IRISA, France
WP-L2.5: OBJECT SEGMENTATION IN MULTI-VIEW VIDEO VIA ................................................2724COLOR, DEPTH AND MOTION CUESCevahir Cigla, A. Aydin Alatan, Middle East Technical University, Turkey
WP-L2.6: KERNEL-BASED HIGH-DIMENSIONAL HISTOGRAM .....................................................2728ESTIMATION FOR VISUAL TRACKINGPeter Karasev, James Malcolm, Allen Tannenbaum, Georgia Institute of Technology, United States
WP-L2.7: A PRECISE AND STABLE FOREGROUND SEGMENTATION .........................................2732USING FINE-TO-COARSE APPROACH IN TRANSFORM DOMAINHiroaki Tezuka, Takao Nishitani, Tokyo Metropolitan University, Japan
WP-L2.8: GENERALIZED ELL FOR DETECTING AND TRACKING ...............................................2736THROUGH ILLUMINATION MODEL CHANGESAmit Kale, Siemens Corporate Technology India, India; Namrata Vaswani, Iowa State University, United States
WP-L3: FACE DETECTION, RECOGNITION AND CLASSIFICATION III
WP-L3.1: SINGLE IMAGE PER PERSON FACE RECOGNITION WITH ..........................................2740IMAGES SYNTHESIZED BY NON-LINEAR APPROXIMATIONAngshul Majumdar, Rabab K. Ward, University of British Columbia, Canada
WP-L3.2: FACE RECOGNITION VIA ADAPTIVE DISCRIMINANT ..................................................2744CLUSTERINGMarios Kyperountas, Anastasios Tefas, Ioannis Pitas, Aristotle University of Thessaloniki, United States
WP-L3.3: A MULTI-STEP ALIGNMENT SCHEME FOR FACE ..........................................................2748RECOGNITION IN RANGE IMAGESAndre Störmer, Gerhard Rigoll, Technische Universität München, Germany
WP-L3.4: MOTIVATING CLASS-SPECIFIC NONLINEAR PROJECTIONS .....................................2752FOR SINGLE AND MULTIPLE VIEW FACE VERIFICATIONGeorgios Goudelis, Stefanos Zafeiriou, Anastasios Tefas, Aristotle University of Thessaloniki, Greece; Nikos Nikolaidis, Aristotle University of Thessaloniki / Informatics and Telematics Institute, Greece; Ioannis Pitas, Aristotle University of Thessaloniki, Greece
WP-L3.5: SPECTRAL RANGE SELECTION FOR FACE RECOGNITION ........................................2756UNDER VARIOUS ILLUMINATIONSHong Chang, Yi Yao, Andreas Koschan, Besma Abidi, Mongi Abidi, University of Tennessee, Knoxville, United States
WP-L3.6: MULTI-MODAL (2-D AND 3-D) FACE MODELING AND ...................................................2760RECOGNITION USING ATTRIBUTED RELATIONAL GRAPHMohammad H. Mahoor, A-Nasser Ansari, Mohamed Abdel-Mottaleb, University of Miami, United States
WP-L3.7: FACE DETECTION FROM FEW TRAINING EXAMPLES ..................................................2764Chunhua Shen, Sakrapee Paisitkriangkrai, Jian Zhang, NICTA, Australia
WP-L3.8: AUTOMATED FACIAL FEATURE DETECTION AND FACE ...........................................2768RECOGNITION USING GABOR FEATURES ON RANGE AND PORTRAIT IMAGESSina Jahanbin, University of Texas at Austin, United States; Hyohoon Choi, Sealed Air Corporation, United States; Rana Jahanbin, Alan Bovik, University of Texas at Austin, United States
WP-L4: VIDEO CODING STANDARDS
WP-L4.1: SUBJECTIVE PERFORMANCE EVALUATION OF THE SVC ..........................................2772EXTENSION OF H.264/AVCTobias Oelbaum, Technische Universität München, Germany; Heiko Schwarz, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany; Mathias Wien, RWTH Aachen University, Germany; Thomas Wiegand, Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Germany
WP-L4.2: BIT-STREAM REWRITING FOR SVC-TO-AVC CONVERSION........................................2776Andrew Segall, Jie Zhao, Sharp Laboratories of America, Inc., United States
WP-L4.3: PERCEPTUAL IMPACT OF BURSTY VERSUS ISOLATED PACKET .............................2780LOSSES IN H.264 COMPRESSED VIDEOTing-Lan Lin, Pamela Cosman, University of California, San Diego, United States; Amy Reibman, AT&T Labs - Research, United States
WP-L4.4: COMPLEXITY MODELING OF H.264 ENTROPY DECODING .........................................2784Zhan Ma, Zhongbo Zhang, Yao Wang, Polytechnic University, United States
WP-L4.5: SPATIO-TEMPORAL PREDICTION IN VIDEO CODING BY ...........................................2788SPATIALLY REFINED MOTION COMPENSATIONJürgen Seiler, André Kaup, University of Erlangen-Nuremberg, Germany
WP-L4.6: RATE CONTROL FOR VIDEO CODING WITH SLICE TYPE ..........................................2792DEPENDENCIESAthanasios Leontaris, Alexis Tourapis, Dolby Laboratories, Inc., United States
WP-L4.7: EXPLOITING MPEG-7 TEXTURE DESCRIPTORS FOR FAST ........................................2796H.264 MODE DECISIONNawat Kamnoonwatana, Dimitris Agrafiotis, Nishan Canagarajah, University of Bristol, United Kingdom
WP-L4.8: STATISTICAL LEARNING BASED INTRA PREDICTION IN H.264 .................................2800Cheolhong An, Truong Nguyen, University of California, San Diego, United States
WP-L5: MULTIDIMENSIONAL WAVELETS AND FILTER BANKS
WP-L5.1: THE MARR WAVELET PYRAMID ..........................................................................................2804Dimitri Van De Ville, Michael Unser, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland
WP-L5.2: COMPACT IMAGE REPRESENTATION USING WAVELET ............................................2808LIFTING ALONG ARBITRARY TREESGodwin Shen, Antonio Ortega, University of Southern California, United States
WP-L5.3: LIFTING-BASED LAPLACIAN PYRAMID RECONSTRUCTION .....................................2812SCHEMESLijie Liu, Johns Hopkins University, United States; Lu Gan, Brunel University, United Kingdom; Trac D. Tran, The Johns Hopkins University, United States
WP-L5.4: A NEW MULTIRESOLUTION GENERALIZED DIRECTIONAL ......................................2816FILTER BANK DESIGN AND APPLICATION IN IMAGE ENHANCEMENTVishal Patel, Glenn R. Easley, Dennis Healy, University of Maryland, United States
WP-L5.5: A NEW COMBINATION OF 1D AND 2D FILTER BANKS FOR ........................................2820EFFECTIVE MULTIRESOLUTION IMAGE REPRESENTATIONYuichi Tanaka, Masaaki Ikehara, Keio University, Japan; Truong Nguyen, University of California, San Diego, United States
WP-L5.6: A FAST ALGORITHM FOR PRESERVING NOISE WHILE ...............................................2824REDUCING IMAGE SIZERamin Samadani, Hewlett-Packard Laboratories, United States
WP-L5.7: WAVELET-BASED HYBRID MULTILINEAR MODELS FOR ...........................................2828MULTIDIMENSIONAL IMAGE APPROXIMATIONQing Wu, University of Illinois at Urbana-Champaign, United States; Chun Chen, Zhejiang University, China; Yizhou Yu, University of Illinois at Urbana-Champaign, United States
WP-L5.8: CURVELET DECOMPOSITION FOR DETECTION OF ......................................................2832CYLINDRICAL TARGETSFrank Crosby, Naval Surface Warfare Center - Panama City, United States
WP-PA: VIDEO CODING II
WP-PA.1: ACCURATE PARAMETER ESTIMATION AND EFFICIENT FADE ...............................2836DETECTION FOR WEIGHTED PREDICITON IN H.264 VIDEO COMPRESSIONRui Zhang, Cisco Systems, Inc., United States; Guy Cote, Apple Computer, United States
WP-PA.2: AN IMPROVED COEFF_TOKEN VARIABLE LENGTH DECODING .............................2840MEHOD FOR LOW POWER DESIGN OF H.264/AVC CAVLC DECODERYong Ho Moon, Gyeongsang National University, Republic of Korea; Il Ku Eom, Pusan National University, Republic of Korea; Suk Woon Ha, Gyeongsang National University, Republic of Korea
WP-PA.3: DISTORTION ESTIMATION AND BIT ALLOCATION FOR MCTF ...............................2844BASED 3-D WAVELET VIDEO CODINGCho-Chun Cheng, Guan-Ju Peng, Wen-Liang Hwang, Academia Sinica, Taiwan
WP-PA.4: APPLICATION OF MOTION SHARPENING EFFECT IN VIDEO ...................................2848CODINGAkira Fujibayashi, Choong Seng Boon, NTT DoCoMo,Inc, Japan
WP-PA.5: TRANSCODING WITH QUALITY ENHANCEMENT AND ...............................................2852IRREGULAR SAMPLINGMaria Pantoja, Nam Ling, Santa Clara University, United States
WP-PA.6: OPTIMAL DELIVERY OF MOTION JPEG2000 OVER JPIP WITH .................................2856BLOCK-WISE TRUNCATION OF QUALITY LAYERSFrancesc Auli-Llinas, David Taubman, University of New South Wales, Australia
WP-PA.7: WINDOWING TECHNIQUE FOR THE DCT BASED RETINEX .......................................2860ALGORITHM TO HANDLE VIDEOS WITH BRIGHTNESS VARIATIONS CODED USING THE H.264Hoi-Kok Cheung, Sydney University, Australia; Wan-Chi Siu, Hong Kong Polytechnic University, Hong Kong SAR of China; Dagan Feng, Zhiyong Wang, Sydney University, Australia
WP-PA.8: TEMPORAL PROPAGATION ANALYSIS FOR SMALL ERRORS IN A .........................2864SINGLE-FRAME IN H.264 VIDEOWai-tian Tan, Bo Shen, Andrew Patti, Gene Cheung, Hewlett-Packard Company, United States
WP-PA.9: EFFECTIVE FLICKER REMOVAL FROM PERIODIC INTRA ........................................2868FRAMES AND ACCURATE FLICKER MEASUREMENTHua Yang, Jill Boyce, Alan Stein, Thomson Inc., United States
WP-PA.10: JOINT MOTION AND GEOMETRY MODELING WITH .................................................2872QUAD-TREE LEAF MERGINGReji Mathew, National ICT Australia, Australia; David Taubman, University of New South Wales, Australia
WP-PB: IMAGE CODING III
WP-PB.1: EFFECTIVE VISUAL MASKING TECHNIQUES IN JPEG2000 .........................................2876Thomas Richter, University of Stuttgart, Germany
WP-PB.2: A NOVEL DESIGN OF CRITICALLY SAMPLED CONTOURLET ...................................2880TRANSFORM AND ITS APPLICATION TO IMAGE CODINGShizuka Higaki, Seisuke Kyochi, Yuichi Tanaka, Masaaki Ikehara, Keio University, Japan
WP-PB.3: IMAGE CODING USING SHORT WAVELET-BASED ........................................................2884CONTOURLET TRANSFORMChao-Hsiung Hung, National Chiao-Tung University, Taiwan; Hsueh-Ming Hang, National Taipei University of Technology, Taiwan
WP-PB.4: VISUAL QUALITY IMPROVEMENT TECHNIQUES OF ...................................................2888HDPHOTO/JPEG-XRThomas Richter, University of Stuttgart, Germany
WP-PB.5: UNSUPERVISED IMAGE COMPRESSION-BY-SYNTHESIS .............................................2892WITHIN A JPEG FRAMEWORKJames Byrne, Stephen Ierodiaconou, David Bull, David Redmill, Paul Hill, University of Bristol, United Kingdom
WP-PB.6: BEST POST-TRANSFORMS SELECTION IN A ....................................................................2896RATE-DISTORTION SENSEXavier Delaunay, TéSA/CNES/NOVELTIS, France; Emmanuel Christophe, Carole Thiebaut, Centre National d’Etudes Spatiales (CNES), France; Vincent Charvillat, IRIT/ENSEEIHT, France
WP-PB.7: EXPLOITING PATTERNS OF DATA MAGNITUDE FOR ..................................................2900EFFICIENT IMAGE CODINGAmir Said, Debargha Mukherjee, Hewlett-Packard Laboratories, United States
WP-PB.8: GENERALISED BLIND SAMPLING OF IMAGES ................................................................2904Zvi Devir, Michael Lindenbaum, Technion - Israel Institute of Technology, Israel
WP-PB.9: A SPIHT-LIKE IMAGE CODER BASED ON THE CONTOURLET ..................................2908TRANSFORMSara Parrilli, Luisa Verdoliva, Giovanni Poggi, Università Federico II di Napoli, Italy
WP-PB.10: A FRAMEWORK FOR EVALUATING THE IMPACT OF ................................................2912COMPRESSION ON REGISTRATION ALGORITHMS WITHOUT GOLD STANDARDTristan Glatard, CNRS I3S / INRIA Sophia-Antipolis, France; Johan Montagnat, CNRS I3S, France; Xavier Pennec, INRIA Sophia-Antipolis, France
WP-PB.11: EFFICIENT BLOCK-BASED INTRA PREDICTION FOR IMAGE ..................................2916CODING WITH 2D GEOMETRICAL MANIPULATIONSYunyang Dai, Qi Zhang, University of Southern California, United States; Alexis Tourapis, Dolby Laboratories, Inc., United States; C.-C. Jay Kuo, University of Southern California, United States
WP-PB.12: REDUNDANT IMAGE REPRESENTATION VIA MULTI-SCALE ..................................2920DIGITAL RADON PROJECTIONSAndrew Kingston, Australian National University, Australia; Benoit Parrein, Florent Autrusseau, IRCCyN–IVC, France
WP-PC: BIOMEDICAL IMAGING II
WP-PC.1: 3-D KNEE CARTILAGE SEGMENTATION USING A SMOOTHING ..............................2924B-SPLINE ACTIVE SURFACEXian Du, Jerome Velut, Radu Bolbos, Olivier Beuf, Christophe Odet, Hugues Benoit-Cattin, CREATIS CNRS UMR5220 INSERM U630, France
WP-PC.2: A COMPLETE 3D WOUND ASSESSMENT TOOL FOR ACCURATE ..............................2928TISSUE CLASSIFICATION AND MEASUREMENTHazem Wannous, Yves Lucas, Sylvie Treuillet, University of Orleans, France; Benjamin Albouy, University of Clermont, France
WP-PC.3: RED LESIONS DETECTION IN DIGITAL FUNDUS IMAGES ...........................................2932S. Balasubramanian, Sandip Pradhan, V. Chandrasekaran, Sri Sathya Sai University, India
WP-PC.4: AN IMPROVED SUPER-SHORT-SCAN RECONSTRUCTION FOR .................................2936FAN-BEAM COMPUTED TOMOGRAPHYJianhua Ma, Lingjian Chen, Jing Huang, Wufan Chen, Southern Medical University, China
WP-PC.5: 3D CONE-BEAM GENERALIZED PSEUDO-LAMBDA ......................................................2940TOMOGRAPHY BASED ON FDKLingjian Chen, Jianhua Ma, Wufan Chen, Southern Medical University, China
WP-PC.6: 4D RECONSTRUCTION OF CARDIAC IMAGES USING ...................................................2944TEMPORAL FOURIER BASIS FUNCTIONSXiaofeng Niu, Yongyi Yang, Miles N. Wernick, Medical Imaging Research Center, United States
WP-PC.7: STATISTICAL IMAGE RECONSTRUCTION FOR MUON ................................................2948TOMOGRAPHY USING GAUSSIAN SCALE MIXTURE MODELGuobao Wang, Jinyi Qi, University of Carlifornia, Davis, United States
WP-PC.8: IMPROVING PHYSICAL BEHAVIOR IN IMAGE REGISTRATION ................................2952Guillaume Janssens, Jonathan Orban de Xivry, Université catholique de Louvain, Belgium; Hugo Aerts, Geert Bosmans, Andre Dekker, University Hospital Maastricht, Netherlands; Benoit Macq, Université catholique de Louvain, Belgium
WP-PC.9: FSM: A NEW FINITE SPHERE-BASED METHOD FOR .....................................................2956MODELING 3D GEOMETRY OF THE PROSTATEAmjad Zaim, University of Texas at Brownsville, United States
WP-PD: BIOMEDICAL IMAGING III
WP-PD.1: ROBUST BRAIN ACTIVATION DETECTION IN FUNCTIONAL ....................................2960MRIDavid Afonso, João Sanches, Instituto de Sistemas e Robótica / Instituto Superior Técnico, Portugal; Martin Lauterbach, Instituto de Medicina Molecular / Faculdade de Medicina de Lisboa, Portugal
WP-PD.2: PARALLEL IMAGE RECONSTRUCTION USING A SINGLE ..........................................2964SIGNAL IN MAGNETIC RESONANCE IMAGINGSatoshi Ito, Yoshifumi Yamada, Utsunomiya University, Japan
WP-PD.3: AUTOMATED LINE FLATTENING OF ATOMIC FORCE ................................................2968MICROSCOPY IMAGESSotirios Tsaftaris, Jana Zujovic, Aggelos K. Katsaggelos, Northwestern University, United States
WP-PD.4: MACHINE VISION DETECTION OF ISOLATED AND ......................................................2972OVERLAPPED NEMATODE WORMS USING SKELETON ANALYSISNikzad Babaii Rizvandi, Aleksandra Pizurica, Wilfried Philips, Ghent university, Belgium
WP-PD.5: IMPROVING LIGHT PROPAGATION MONTE CARLO ...................................................2976SIMULATIONS WITH ACCURATE 3D MODELING OF SKIN TISSUEVincent Paquit, Jeffery Price, Oak Ridge National Laboratory, United States; Fabrice Mériaudeau, Le2i - University of Burgundy, France; Kenneth Tobin, Oak Ridge National Laboratory, United States
WP-PD.6: A DYNAMIC PROGRAMMING SOLUTION TO TRACKING AND .................................2980ELASTICALLY MATCHING LEFT VENTRICULAR WALLS IN CARDIAC CINE MRISotirios Tsaftaris, Valentin Andermatt, Andre Schlege, Aggelos K. Katsaggelos, Debiao Li, Rohan Dharmakumar, Northwestern University, United States
WP-PD.7: SPECT IMAGE RESTORATION VIA RECURSIVE INVERSE ..........................................2984FILTERING CONSTRAINED BY A PROBABILISTIC MRI ATLASSaid Benameur, Max Mignotte, Jean Paul Soucy, Jean Meunier, University of Montreal, Canada
WP-PD.8: GAUSSIAN CURVATURE FLOW MODEL FOR COLONIC POLYP ...............................2988DETECTION IN CT COLONOGRAPHYDongqing Chen, Aly Farag, University of Louisville, United States; Robert Falk, Jewish Hospital, United States; Gerald Dryden, University of Louisville, United States
WP-PD.9: RECONSTRUCTION OF MACROMOLECULAR ENVELOPES .......................................2992FROM CRYSTAL X-RAY DIFFRACTION AMPLITUDESVictor Lo, Rick Millane, University of Canterbury, New Zealand; Richard Kingston, University of Auckland, New Zealand
WP-PD.10: A NEW PERSPECTIVE ON TERAHERTZ IMAGE ............................................................2996RECONSTRUCTION BASED ON LINEAR SPECTRAL UNMIXINGYang Bai, Hairong Qi, University of Tennessee, United States
WP-PD.11: COMPUTER-AIDED DIAGNOSIS AND VISUALIZATION BASED ................................3000ON CLUSTERING AND INDEPENDENT COMPONENT ANALYSIS FOR BREAST MRIAnke Meyer-Baese, Oliver Lange, Thomas Schlossbauer, Axel Wismueller, Florida State University, United States
WP-PD.12: AN INTEGRATED TECHNIQUE FOR VOLUME ESTIMATION ....................................3004OF SPOTS IN 3-D HUMAN CELL CULTURES: WATERSNAKESNarasimhan Rajagopalan, Jeffrey Rodriguez, Kathleen Dixon, University of Arizona, United States
WP-PE: IMAGE SEGMENTATION V
WP-PE.1: MULTI-POLARITY TEXT SEGMENTATION USING GRAPH .........................................3008THEORYJia Li, Chinese Academy of Sciences, China; Yonghong Tian, Tiejun Huang, Wen Gao, Peking University, China
WP-PE.2: MARKOVIAN METHOD FOR 2D, 3D AND 4D SEGMENTATION ...................................3012OF MRIPierre-Marc Jodoin, Université de Sherbrooke, Canada; Alain Lalande, Yvon Voisin, Olivier Bouchot, Eric Steinmetz, Université de Bourgogne, France
WP-PE.3: GENERAL REGION MERGING APPROACHES BASED ON ............................................3016INFORMATION THEORY STATISTICAL MEASURESFelipe Calderero, Ferran Marques, Technical University of Catalonia (UPC), Spain
WP-PE.4: MAXIMUM LIKELIHOOD NEURAL NETWORK BASED ON THE ................................3020CORRELATION BETWEEN NEIGHBORING PIXELS FOR NOISY IMAGE SEGMENTATIONThanh Nguyen, Jonathan Wu, University of Windsor, Canada
WP-PE.5: DENSITY ESTIMATION USING A NEW AIC-TYPE CRITERION ...................................3024AND THE EM ALGORITHM FOR A LINEAR COMBINATION OF GAUSSIANSAsem Ali, Aly Farag, University of Louisville, United States
WP-PE.6: RANDOM FEATURE SUBSET SELECTION IN A ................................................................3028NONSTATIONARY ENVIRONMENT: APPLICATION TO TEXTURED IMAGE SEGMENTATIONXiyan He, Pierre Beauseroy, André Smolarz, Université de Technologie de Troyes, France
WP-PE.7: OBJECT DISCOVERY WITH PERCEPTUAL GROUPING .................................................3032David Liu, Tsuhan Chen, Carnegie Mellon University, United States
WP-PE.8: GENERAL FRAMEWORK FOR UNSUPERVISED EVALUATION ..................................3036OF QUALITY OF SEGMENTATION RESULTSOlga Kubassova, Image Analysis Ltd, United Kingdom; Mikael Boesen, Parker Institute, Denmark; Henning Bliddal, Frederiksberg Hospital, Denmark
WP-PE.9: BACKGROUND ESTIMATION FOR MICROSCOPIC CELLULAR .................................3040IMAGESNezamoddin N. Kachouie, Paul Fieguth, University of Waterloo, Canada
WP-PE.10: INTERACTIVE IMAGE SEGMENTATION VIA MULTI-CUE ........................................3044DYNAMIC INTEGRATIONJieyu Zhao, Ningbo University, China; Xiaowei Geng, Chinese Academy of Sciences, China
WP-PE.11: SIMULTANEOUS ESTIMATION OF THE MARKOV RANDOM ....................................3048FIELD PARAMETERS AND THE CLASSES FOR IMAGE SEGMENTATIONXin Liu, Imam Samil Yetik, Miles N. Wernick, Illinois Institute of Technology, United States
WP-PE.12: REFERENCE-BASED PROBABILISTIC SEGMENTATION AS ......................................3052NON-RIGID REGISTRATION USING THIN PLATE SPLINESLuca Bertelli, Pratim Ghosh, B. S. Manjunath, Frederic Gibou, University of California, Santa Barbara, United States
WP-PF: IMAGE & VIDEO COMMUNICATIONS III
WP-PF.1: LOW-COMPLEXITY TEMPORAL ERROR CONCEALMENT BY ...................................3056MOTION VECTOR PROCESSING FOR MOBILE VIDEO APPLICATIONSGokce Dane, Yan Ye, Yen-Chi Lee, Qualcomm Inc., United States
WP-PF.2: IMPROVED RESILIENCE FOR VIDEO OVER PACKET LOSS ........................................3060NETWORKS WITH MDC AND OPTIMIZED PACKETIZATIONMoyruesh Biswas, Michael Frater, John Arnold, Mark Pickering, University of New South Wales, Australia
WP-PF.3: EFFICIENT ERROR CONCEALMENT FOR THE WHOLE-FRAME ...............................3064LOSS BASED ON H.264/AVCBo Yan, Fudan University, China; Hamid Gharavi, National Institute of Standards and Technology, United States
WP-PF.4: A NEW UNEQUAL ERROR PROTECTION SCHEME BASED ON ...................................3068FMOJhong-Yu Shih, Wen-Jiin Tsai, National Chiao Tung University, Taiwan
WP-PF.5: A LOW-COMPLEXITY PACKET CLASSIFICATION ALGORITHM ..............................3072FOR MULTIPLE DESCRIPTION VIDEO STREAMING OVER IEEE802.11E NETWORKSSimone Milani, Giancarlo Calvagno, University of Padova, Italy; Riccardo Bernardini, Roberto Rinaldo, University of Udine, Italy
WP-PF.6: INFORMATION-DRIVEN RESOURCE NEGOTIATION ....................................................3076STRATEGIES FOR MULTIMEDIA APPLICATIONSHyunggon Park, Mihaela van der Schaar, University of California, Los Angeles, United States
WP-PF.7: A NEW THEORETIC FRAMEWORK FOR CROSS-LAYER ..............................................3080OPTIMIZATIONFangwen Fu, Mihaela van der Schaar, University of California, Los Angeles, United States
WP-PF.8: EFFICIENT SCALABLE VIDEO TRANSMISSION BASED ON .........................................3084TWO- DIMENSIONAL ERROR PROTECTION SCHEMENaeem Ramzan, Ebroul Izquierdo, Queen Mary, University of London, United Kingdom
WP-PF.9: MULTI-VIEW VIDEO STREAMING OVER P2P NETWORKS ..........................................3088WITH LOW START-UP DELAYEngin Kurutepe, Thomas Sikora, Technische Universität Berlin, Germany
WP-PF.10: SUBJECTIVE EVALUATION OF MULTI-USER RATE ....................................................3092ALLOCATION FOR STREAMING HETEROGENEOUS VIDEO CONTENTS OVER WIRELESS NETWORKSXiaoqing Zhu, Bernd Girod, Stanford University, United States
WP-PF.11: RATE-DISTORTION-AUTHENTICATION OPTIMIZED ..................................................3096STREAMING WITH GENERALIZED BUTTERFLY GRAPH AUTHENTICATIONZhishou Zhang, Qibin Sun, Institute for Infocomm Research, Singapore; John Apostolopoulos, Hewlett-Packard Laboratories, United States; Wai-Choong Wong, National University of Singapore, Singapore
WP-PF.12: MULTI BEARER CHANNEL RESOURCE ALLOCATION FOR .....................................3100OPTIMISED TRANSMISSION OF VIDEO OBJECTSSabih Nasir, Stewart Worrall, Marta Mrak, Ahmet Kondoz, University of Surrey, United Kingdom
WP-PG: SECURITY AND AUTHENTICATION II
WP-PG.1: ENTROPIC HASHING OF 3D OBJECTS USING ..................................................................3104LAPLACE-BELTRAMI OPERATORMohammadreza Ghaderpanah, Abdullah Abbas, Abdessamad Ben Hamza, Concordia University, Canada
WP-PG.2: GAIT AUTHENTICATION USING DISTRIBUTED SOURCE ...........................................3108CODINGSavvas Argyropoulos, Dimitrios Tzovaras, Dimosthenis Ioannidis, Michael G. Strintzis, Informatics and Telematics Institute, Greece
WP-PG.3: BLIND FORENSICS OF CONTRAST ENHANCEMENT IN ...............................................3112DIGITAL IMAGESMatthew Stamm, K. J. Ray Liu, University of Maryland, College Park, United States
WP-PG.4: HIERARCHICAL ENCRYPTION USING SHORT ENCRYPTION ...................................3116KEYS FOR SCALABLE ACCESS CONTROL OF JPEG 2000 CODED IMAGESNoriaki Hashimoto, Tokyo Metropolitan University, Japan; Shoko Imaizumi, Industrial Research Institute of Niigata Prefecture, Japan; Masaaki Fujiyoshi, Hitoshi Kiya, Tokyo Metropolitan University, Japan
WP-PG.5: JOINT SECURITY AND PERFORMANCE ENHANCEMENT FOR .................................3120SECURE ARITHMETIC CODINGJiantao Zhou, Oscar C. Au, Xiaopeng Fan, Peter H.W. Wong, Hong Kong University of Science and Technology, Hong Kong SAR of China
WP-PG.6: ON THE SECURITY OF NON-FORGEABLE ROBUST HASH ..........................................3124FUNCTIONSQiming Li, Sujoy Roy, Institute for Infocomm Research, Singapore
WP-PG.7: COLLUSION-RESISTANT VIDEO FINGERPRINTING BASED ON ................................3128TEMPORAL OSCILLATIONYu-Tzu Lin, National Taiwan Normal University, Taiwan; Chun-Hsiang Huang, Ja-Ling Wu, National Taiwan University, Taiwan
WP-PG.8: FAIRNESS DYNAMICS IN MULTIMEDIA COLLUDERS’ SOCIAL ................................3132NETWORKSW. Sabrina Lin, University of Maryland, United States; H. Vicky Zhao, University of Alberta, Canada; K. J. Ray Liu, University of Maryland, United States
WP-PG.9: A NOVEL VIDEO ENCRYPTION TECHNIQUE BASED ON .............................................3136SECRET SHARINGNarsimha Raju Chigullapally, Umadevi Ganugula, Srinathan Kannan, Jawahar C. V., International Institute of Information Technology, India
WP-PG.10: RECAPTURED PHOTO DETECTION USING SPECULARITY ......................................3140DISTRIBUTION
MA-PF.12: COLOR ENHANCEMENT IN THE COMPRESSED DOMAIN..........................................3144
Hang Yu, Tian-Tsong Ng, Qibin Sun, Institute for Infocomm Research, Singapore
WP-PH: ENHANCEMENT AND DENOISING III
WP-PH.1: IMAGE DEBLOCKING USING CONVEX OPTIMIZATION ..............................................3148Liwei Guo, Oscar C. Au, Mengyao Ma, Xiaopeng Fan, Peter H.W. Wong, Daniel P. Palomar, Hong Kong University of Science and Technology, Hong Kong SAR of China
California, United States
WP-PH.2: A PERCEPTUAL METRIC FOR BLIND MEASUREMENT OF .........................................3152BLOCKING ARTIFACTS WITH APPLICATIONS IN TRANSFORM-BLOCK-BASED IMAGE AND VIDEO CODINGKoohyar Minoo, Truong Nguyen, University of California, San Diego, United States
WP-PH.3: DIRECTIONAL MOTION-COMPENSATED SPATIO-TEMPORAL ................................3156FUZZY FILTERING FOR QUALITY ENHANCEMENT OF COMPRESSED VIDEO SEQUENCESDung Vo, Truong Nguyen, University of California, San Diego, United States
Jayanta Mukhopadhyay, Indian Institute of Technology, Kharagpur, India; Sanjit Mitra, University of Southern
WP-PH.4: A KALMAN FILTER-BASED APPROACH FOR ADAPTIVE ............................................3160RESTORATION OF IN-VEHICLE CAMERA FOGGY IMAGESTomoki Hiramatsu, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan
WP-PH.5: IMAGE ENHANCEMENT BASED ON QUADRATIC ..........................................................3164PROGRAMMINGTzu-Cheng Jen, Sheng-Jyh Wang, National Chiao Tung University, Taiwan
WP-PH.6: SUB-BAND DECOMPOSED MULTISCALE RETINEX WITH ..........................................3168SPACE VARYING GAINJae Ho Jang, Boorym Choi, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea; Sung Deuk Kim, Andong National University, Republic of Korea; Jong Beom Ra, Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea
WP-PH.7: REGULARIZED DEQUANTIZATION FOR IMAGE COPIES ...........................................3172COMPRESSED WITH DIFFERENT QUANTIZATION PARAMETERSGao Yang, Ci Wang, Yap-Peng Tan, Nanyang Technological University, Singapore
WP-PH.8: MOTION-COMPENSATED DEBLOCKING AND UPSCALING ........................................3176FOR VIEWING LOW-RES VIDEOS ON HIGH-RES DISPLAYSVikas Ramachandra, University of California, San Diego, United States; Andrew Patti, Hewlett-Packard Company, United States
WP-PH.9: IMAGE CONTRAST ENHANCEMENT BASED ON 2D ......................................................3180TEAGER-KAISER OPERATORAbdel-Ouahab Boudraa, El-Hadji Samba Diop, Ecole Navale, France
WP-PH.10: NONLINEAR MULTI-SCALE CONTRAST ENHANCEMENT FOR ...............................3184CHEST RADIOGRAPH
AUTHOR INDEX
Xuanqin Mou, Min Zhang, Xi’an Jiaotong University, China
WP-PI: IMAGE SEGMENTATION VI
WP-PI.1: A GRAPH CUT BASED ACTIVE CONTOUR FOR MULTIPHASE ....................................3188IMAGE SEGMENTATIONNoha El-Zehiry, Adel Elmaghraby, University of Louisville, United States
WP-PI.2: BOOSTING IMAGE SEGMENTATION ....................................................................................3192Hyung Il Koo, Nam Ik Cho, Seoul National University, Republic of Korea
WP-PI.3: AUTOMATIC TEXT AREA SEGMENTATION IN NATURAL IMAGES ...........................3196Syed Ali Jafri, Mireille Boutin, Edward J. Delp, Purdue University, United States
WP-PI.4: ONLINE, SIMULTANEOUS SHOT BOUNDARY DETECTION AND ................................3200KEY FRAME EXTRACTION FOR SPORTS VIDEOS USING RANK TRACINGWael Abd-Almageed, Institute for Advanced Computer Studies, United States
WP-PI.5: LEARNING DISTANCE METRIC FOR SEMI-SUPERVISED IMAGE ..............................3204SEGMENTATIONYangqing Jia, Changshui Zhang, Tsinghua University, China
WP-PI.6: ACTIVITY-BASED TEMPORAL SEGMENTATION FOR VIDEOS ...................................3208OF INTERACTING OBJECTS USING INVARIANT TRAJECTORY FEATURESAlexandre Hervieu, Patrick Bouthemy, INRIA Rennes, France; Jean-Pierre Le Cadre, IRISA / CNRS, France
WP-PI.7: A SPLIT AND MERGE BASED ELLIPSE DETECTOR..........................................................3212Alex Chia, Deepu Rajan, Maylor Leung, Susanto Rahardja, Nanyang Technological University, Singapore
WP-PI.8: A FEATURE ANALYSIS APPROACH TO ESTIMATE 3D SHAPE FROM .......................3216IMAGE FOCUSMuhammad Tariq Mahmood, Tae-Sun Choi, Gwangju Institute of Science and Technology, Republic of Korea
WP-PI.9: GAGM-AAM: A GENETIC OPTIMIZATION WITH GAUSSIAN .......................................3220MIXTURES FOR ACTIVE APPEARANCE MODELSAbdul Sattar, Yasser Aidarous, Renaud Seguier, SUPELEC/IETR, France
WP-PI.10: TIME-SEQUENTIAL EXTRACTION OF MOTION LAYERS ............................................3224Matthieu Fradet, Thomson Corporate Research, France; Patrick Perez, INRIA Rennes Bretagne-Atlantique, France; Philippe Robert, Thomson Corporate Research, France
WP-PI.11: TOWARDS RECOGNITION OF FACIAL EXPRESSIONS IN SIGN .................................3228LANGUAGE: TRACKING FACIAL FEATURES UNDER OCCLUSIONTan Dat Nguyen, Surendra Ranganath, National University of Singapore, Singapore
![IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Blind Image ... · IEEE TRANSACTIONS ON IMAGE PROCESSING 3 image classification [34], image retrieval [35] [36] and image aesthetic evaluation](https://img.dokumen.tips/doc/110x75/5fb4af8856a0b6167b3ddb7f/ieee-transactions-on-image-processing-1-blind-image-ieee-transactions-on-image.jpg)
