55
1 Evaluation 2001-2005 14 November 2005 INRIA Rocquencourt http://www-rocq.inria.fr/ imedia/ IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

  • Upload
    oneida

  • View
    45

  • Download
    5

Embed Size (px)

DESCRIPTION

IMEDIA Image and Multimedia Indexing, Browsing and Retrieval. Evaluation 2001-2005 14 November 2005 INRIA Rocquencourt http://www-rocq.inria.fr/imedia/. The Team (November 2005) Senior members. INRIA personnel Nozha Boujemaa (DR2) Anne Verroust-Blondet(CR1) - PowerPoint PPT Presentation

Citation preview

Page 1: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1

Evaluation 2001-2005

14 November 2005

INRIA Rocquencourt

http://www-rocq.inria.fr/imedia/

IMEDIAImage and Multimedia Indexing,

Browsing and Retrieval

Page 2: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

214 November 2005 IMEDIA

The Team (November 2005)

Senior members INRIA personnel

Nozha Boujemaa (DR2) Anne Verroust-Blondet (CR1)

Jean-Paul Chièze Research Engineer [part-time] Laurence Bourcier Team Assistant

Scientific Adviser Donald Geman (1/2 time, Pr. Johns Hopkins)

External collaborators Michel Crucianu (Pr. CNAM) [3 years mob. IMEDIA] Valérie Gouet-Brunet (MdC CNAM) [2 years mob. IMEDIA] Jean-Philippe Tarel (CR1 LCPC) [2 years mob. IMEDIA] Olivier Buisson INA Researcher (Institut National de l’Audiovisuel)

Marie-Luce Viaud INA Researcher

Page 3: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

314 November 2005 IMEDIA

Post-docs /Expert engineers

Sabri Boughorbel Marin Ferecatu Alexis Joly Itheri YahiaouiPhD students Olfa Besbes Mohamed Chaouch Nizar Grira Nicolas Hervé Hichem Houissa Julien Law-To

The TeamNon permanent members

Former team members

Peter Belhumeur (Sab. visit) Prof. Columbia Univ. NY

François Fleuret (CR) EPFL researcher

Yuchun Fang (Post-doc) Assistant Prof. Shanghai Univ.

Andreas Rauber (Post-doc) Assoc. Prof. Vienna Univ. of Technology

Sylvain Bernard (PhD) Research Engineer (GE Health Care)

Julien Fauqueur (PhD) Research Assoc. Cambridge

Hichem Sahbi (PhD) Research Assoc. Cambridge

Bertrand Le Saux (PhD) Research Assoc. CMLA - ENS

Present team members

Page 4: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

414 November 2005 IMEDIA

Overview

Objectives

Results and Contributions

Applications and Grants

Positioning

Future objectives

Page 5: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

514 November 2005 IMEDIA

Objectives

Design and Develop new Methods for Visual Information Retrieval by Content

Visual content indexing Visual appearance modeling

Constructing efficient indexes for minimizing query cost

Interactive browsing, querying and retrieval Similarity learning

Clustering techniques

Relevance feedback: learning from user interaction

Combine keyword annotation (when available) search with visual-content search

Page 6: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

614 November 2005 IMEDIA

Key Issues Fidelity of physical-content descriptors to visual

appearance Numerical gap vs. Semantic gap

Rich user expression : Partial visual query formulation focused on user interest

(region-based or point-based)

Subjective preference by relevance feedback mechanism

Mental image search and “page zero” problem

Smart navigation

Cross-media indexing and retrieval

Page 7: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

714 November 2005 IMEDIA

General Methodological Issues Image content description:

analysis, segmentation;

considering specific and generic content

Learning from few examples:

Active learning for efficient personalization mechanism

Semi-supervised clustering

Adaptive Clustering (interactive SVM-based refinement)

Information theory: Mental Image search

Page 8: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

814 November 2005 IMEDIA

Overview Objectives

Results and Contributions Visual Content Description

Clustering Methods

Relevance Feedback Mechanism

Mental Image Search

Applications and Grants

Positioning

Future Objectives

Page 9: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

914 November 2005 IMEDIA

Visual Content Description Generic content:

Global image signature: combined color-structure signature (MMCBIR 01, LNCS 05), shape signature (ICIP 05), 3D signature,

Local image description: region-based (JVLC 04), color point-based (CBAIVL/CVPR 01)

Specific content: Face detection (IJCV 01, JMLR 05) Face recognition (Biometric WS/ECCV 02) Fingerprints recognition (ACCV 02)

IKONA search engine demo availablehttp://www-rocq.inria.fr/imedia/ikona.html

Page 10: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1014 November 2005 IMEDIA

Basic color histogram

Local Color activity descriptor (before combination with shape and texture descrip.)

Numerical Gap / Fidelity vs Weakness of signatures

Page 11: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1114 November 2005 IMEDIA

FaceRecognition

Dynamic

programming on local

entropy map features

WBA/ ECCV 2002 (LNCS)

Specific Content Image Database

Page 12: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1214 November 2005 IMEDIA

Coarse-to-Fine Strategy forFace Detection

(Nested partitions of the set of possible poses– IJCV01)( Hierarchy of SVM-classifiers - JMLR 05)

Page 13: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1314 November 2005 IMEDIA

Local Description of the Image

R

p

Region-based query Points-based query

Region SegmentationPoint of interest

extraction

Page 14: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1414 November 2005 IMEDIA

Region-based Indexing and Retrieval

User interest selection (Visual query):

Lavender regions regardless the

background information

X

Yj

Xi

Y

Yj

Yi

Y

Xj

Xi

X n

jicc

n

jijicc

n

jijicc

n

jijiquad ayxayyaxxYXd

1, 1,1,1,

2),(

New Coarse Segmentation +Fine Region Description

Introduction of ADCS Signature+Generalized Quadratic Distance

JVLC 2004

Page 15: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1514 November 2005 IMEDIA

Precise Search by Local Color Invariants Descriptors

CVPR/CBAIVL 01

Optimal order of color differential invariantRobustness to JPEG coding

Color constancy

Page 16: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1614 November 2005 IMEDIA

Overview Objectives Results and Contributions

Visual Content Description Clustering Methods Relevance Feedback Mechanism Mental Image Search

Applications and Grants Positioning Future Objectives

Page 17: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1714 November 2005 IMEDIA

Clustering Methods

Context: unknown number of clusters, competitive agglomeration approaches

Application: image database categorization, image segmentation

Contributions: Adaptive robust clustering (ICPR02) : Noise cluster and

cluster density/shape adapting Entropy regularization and extension to non linearly

separable data (IEEE Fuz.Sys05) Active semi-supervised learning (MIR05, IEE VISP 05)

Page 18: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1814 November 2005 IMEDIA

Active Semi-Supervised Categorization

Learning from few examples:Fully automatic categories could do not reflect user expectations

User constraints indicate how similarity space is different from feature spaceNew clustering

objective function that takes into account

violation cost of “must-link” and “can-not-link” constraints

IEE Vision, Image & Signal Processing, to appear

Page 19: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

1914 November 2005 IMEDIA

Active Semi-Supervised Categorization

Active selection of constraints:Identifying the ambiguous data items with weak membership

Supervision effort Identifying non compact and less separated clusters from their neighbors

Identify the frontier of the least well separated cluster using the fuzzy hypervolume:

Ck is the covariance matrix

Page 20: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2014 November 2005 IMEDIA

Illustration

Scientific databases: Gene Expression Studies

Plants with long stems and round leaves

Textured plants, …

must-link

Can not-link

Generalist databases applicable to video-keyframes for smart video abstract

Class1

Class2

Class3

Class4

Page 21: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2114 November 2005 IMEDIA

Overview Objectives Results and Contributions

Visual Content Description Clustering Methods Relevance Feedback Mechanism Mental Image Search

Applications and Grants Positioning Future Objectives

Page 22: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2214 November 2005 IMEDIA

Relevance Feedback Mechanism

Example: search for Cézanne Paintings

Positive ExamplesNegative Examples

Selection strategy?

Most informative images Most similar images

Online Personalization of Retrieval Results

Page 23: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2314 November 2005 IMEDIA

Contribution to Components of RF Mechanism :

Learner: kernels inducing insensitivity to the scale of the data in the feature vector space

Selector: active learning selection criterion that minimizes the redundancy between the samples

SVM-based decision function select least redundant (orthogonal) items among most ambiguous

items

User: consistent annotation?

Extensive study of user strategies

[MIR04, MIR05, AVIVDiLib'05 ][ACM Multimedia journal (under revision)]

Active Relevance Feedback Framework

Page 24: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2414 November 2005 IMEDIA

Overview Objectives Results and Contributions

Visual Content Description Clustering Methods Relevance Feedback Mechanism Mental Image Search

Applications and Grants Positioning Future Objectives

Page 25: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2514 November 2005 IMEDIA

Mental Picture Retrieval

Context: No starting image example or keyword

A person has a picture “in mind”, e.g., a face painting Scene

Problem: How to reach the target? Bayesian framework

Composition from Visual Thesaurus

Page 26: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2614 November 2005 IMEDIA

Bayesian Framework Components:

Answer Model: Discover answer models which match human behavior

Display Model: (Optimization Problem)

Discover approximations to the optimal display

Each display should catch as much as possible information about target from user.

=> The idea is to maximize mutual information between

target and answer. )|()();( XYHYHYXI Reduction in uncertainty of r.v. Y due to r.v. X

Page 27: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2714 November 2005 IMEDIA

Mental face retrieval: Complications Mental matching involves human memory,

perception and opinions. Images are not indexed by semantic content,

but rather by low-level features (“semantic gap”).

Face recognition is easier, yet unsolved. Sparse literature.

Best Paper Award A-V-based Biometric Person Authentication (AVBA'2005)

Joint work with Sagem Corp.

Page 28: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2814 November 2005 IMEDIA

Query by “Visual Words” Composition

Rejected images

Landscapes

Visual Thesaurus:set of similar regions categories“Cityscape”

? Retrieved images

Page 29: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

2914 November 2005 IMEDIA

Query composition interface => The Visual Thesaurus = summary of region categories (cluster prototypes set)

Category 23

Category 48

[MTAP 05]

Query by “Visual Words” Composition

Page 30: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3014 November 2005 IMEDIA

Symbolic Indexing

“Inverted visual files”in MTAP 05

Page 31: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3114 November 2005 IMEDIA

Additional Results Cross-modal Indexing and Retrieval

Copy detection and more generally semantic behavior of local descriptors for selective video content retrieval

Kernels for similarity learning

Extensive study of user strategies in relevance feedback.

3D model indexing and retrieval, 2D shape descriptors

Page 32: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3214 November 2005 IMEDIA

3D model retrieval

Page 33: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3314 November 2005 IMEDIA

Overview

Objectives Results and Contributions Applications and Grants Positioning Future objectives

Page 34: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3414 November 2005 IMEDIA

Applications and Grants Scientific content collections:

Remote sensing images (ACI QuerySat – CNES, IGN)

Biodiversity images (ACI Biotim – INRA/NASC, IRD)

Audio-visual content: TV news (RIAM Mediaworks – TF1 Tv; INA)

Personal and prof. content (IP-FP6 AceMedia)

Art and Design: Alinari collection

Security application: Pedophilia images (Central Judiciary Police Dep. Europ. STOP)

Biometry (Face - Sagem, fingerprints – Thales)

Page 35: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3514 November 2005 IMEDIA

Other Grants NoE-FP6 Muscle

Important involvement (WP leader, NoE deputy scientific

coordinator, steering committee)

NoE-FP6 Delos

PAI Galilée (recognition for video-surveillance with Modena Univ.)

Associated-Team ViMining with NII

RNRT - RECIS (FT R&D, INSA, NF)

Page 36: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3614 November 2005 IMEDIA

IKONA Search Engine

Images courtesy of Alinari (Oldest private European art photo

archive)

Page 37: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3714 November 2005 IMEDIA

Relevance of hybrid signatures: visual + semantic

information

keyword: “building”

[MIR05]

Page 38: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3814 November 2005 IMEDIAStarting point for RF

Costal area with visible boats

Page 39: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

3914 November 2005 IMEDIA

Gene expression studies on “Arabidopsis”

Images courtesy of NASC (Nottingham Arabidopsis Stock Centre)

Jointly with INRA

Page 40: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4014 November 2005 IMEDIA

Leaf IdentificationSmithsonian databaseShape descriptor [ICIP05]

Images courtesy of Peter Belhumeur (Columbia Univ. NY)

Page 41: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4114 November 2005 IMEDIA

Copy detection

False Alarm

Detected copy

Page 42: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4214 November 2005 IMEDIA

Security ApplicationCriminal Investigation within Pedophilia Images

Central Judiciary Police Department within EC « STOP »

Ikona prototype for “Ministère de l’Intérieur”

Page 43: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4314 November 2005 IMEDIA

USER INTERFACE

Annotate display given a target face

Page 44: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4414 November 2005 IMEDIA

Overview

Objectives Results and Contributions Applications and Grants Positioning Future objectives

Page 45: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4514 November 2005 IMEDIA

INRIA PositioningWrt. INRIA’s strategic goals (2nd): Developing multimedia data and information processing

INRIA projects: ARIANA: probabilistic and variational image analysis for earth

observation, joint ACI QuerySat on remote sensing image indexing, Muscle NoE

LEAR: focus on object recognition involving offline learning methods (learning datasets) while we work on information retrieval and develop different learning methods from few examples (on-line) for image clustering and search personalization - complementary, joint AceMedia FP6

VISTA: Video indexing – complementary, NoE Muscle, MediaWorks,

TEXMEX (SymC): Pluri-disciplinary project (NLP, ImageP.,DB), we have joint interest to feature space structuring and hybrid indexing. (Texmex: audio, video, NLP, visual…); AceMedia and NoE Muscle

Page 46: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4714 November 2005 IMEDIA

National Positioning Telecom Paris – SIP: Remote sensing indexing,

partner within ACI QuerySat, 3D indexing

INT ARTEMIS: 2D and 3D indexing

Ecole Centrale Lyon (L. Chen): face detection recognition, TechnoVision IV2.

INSA Lyon IRIS (J-M Jolion): local descriptors

ENSEA ETIS : Relevance feedback, Muscle NoE

Ecole des Mines (JP. Vert): kernel design

Page 47: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4814 November 2005 IMEDIA

International PositioningVery active domain, below non-exhaustive list T.Huang (Urbana-Champaign), Ed. Chang (U.Cal.Santa-Barbara),

Relevance feedback, A. Smeulders (ISIS group U. Amsterdam), D. Lowe (Univ. BC), A.

Zisserman (Oxford), H. Bishof (Tech. Univ Graz); point-based features

J. Wang (Penn State Univ.), region-based retrieval P. Belhumeur (Columbia Univ.), Leaf species identification and shape

descriptors S. Satoh (NII – Japan) Associated-team “ViMining”, saliency

detection, face detection, image and text–based retrieval R. Cucchiara (Univ. Modena) PAI Gallileo, biometry and video

surveillance, 3D indexing A. Delbimbo (Univ. Florence) NoEDelos, 3D indexing H. Frigui (Univ. NSF-INRIA), semi-supervised clustering T. Tan (CASIA) Liama project

Page 48: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

4914 November 2005 IMEDIA

Overview

Objectives Results and Contributions Applications and Grants Positioning Future Objectives

Page 49: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

5014 November 2005 IMEDIA

Future Scientific Objectives

Visual content description Saliency investigation for selective content

retrieval Geometric consistency of local descriptors Specific content: 2D/3D shape (biodiversity),

extension of face detection methods to be invariant to view point

Efficient search in large collections of imagesMultidimensional data structure indexing (example: multiple queries processing)

Page 50: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

5114 November 2005 IMEDIA

Future Scientific Objectives (cont.)

Mental image search: improved models for perceptual similarity for a higher

degree of coherence between system models and actual human behavior

More efficient visual thesaurus construction methods (hierarchical description with relational clustering)

Toward scalable methods: semi-supervised clustering, Relevance Feedback

Hybrid image and text indexing and retrieval: extension to semi-annotated databases,

dynamic weighting of text and visual rankings

Page 51: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

5214 November 2005 IMEDIA

Future Applications

Biodiversity: Pollen database indexing and retrieval (INRA)

Remote sensing image collection - QuerySat

Design Trends (FP6 Strep – TREND, start January 2006)

Audi-visual: INFOMAGIC (“Pôle de compétitivité” IdF IMVN)

SIGMUND (RIAM with INA)

Security IRFACE: : jointly with Liama and INT on Iris-face biometry,

Information filtering with “Ministère de l’Intérieur”

Page 52: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

5314 November 2005 IMEDIA

Future Plan

A common project between IMEDIA and the Database Research Group VERTIGO of the Cedric/CNAM Lab is planned

Page 53: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

5414 November 2005 IMEDIA

Planned Joint IMEDIA Project INRIA/CNAM composition

INRIA personnel Nozha Boujemaa (DR2) Anne Verroust-Blondet (CR1)

Scientific Adviser Donald Geman (1/2 time, Pr. Johns Hopkins)

CNAM personnel Michel Crucianu (Pr. CNAM) Valérie Gouet-Brunet (MdC CNAM) Michel Scholl (Pr. CNAM) [part-time]

External collaborators Jean-Philippe Tarel (CR1 LCPC) Olivier Buisson INA Researcher (National Institute of Audiovisual)

Marie-Luce Viaud INA Researcher

Research engineer Jean-Paul Chièze (part-time)

Post-Doc and Engineer (4)

PhD (9)Team Assistant: Laurence Bourcier

Page 54: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

5514 November 2005 IMEDIA

Summary

Promising scientific results

Smooth evolution of current research directions

Important application impact

Highly competitive context

Support for INRIA research scientist hiring highly

appreciated (major risk)

Page 55: IMEDIA Image and Multimedia Indexing, Browsing and Retrieval

5614 November 2005 IMEDIA

Thanks for your attention

http://www-rocq.inria.fr/imedia/