IEEE 2015 Matlab Projects

IEEE 2015 Matlab Projects

Web : www.kasanpro.com Email : [email protected]

List Link : http://kasanpro.com/projects-list/ieee-2015-matlab-projects

Title :NMF-based Target Source Separation Using Deep Neural NetworkLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/nmf-based-target-source-separation-using-deep-neural-networkAbstract : Non-negativematrix factorization (NMF) is one of the most well-known techniques that are applied toseparate a desired source from mixture data. In the NMF framework, a collection of data is factorized into a basismatrix and an encoding matrix. The basismatrix for mixture data is usually constructed by augmenting the basismatrices for independent sources. However, target source separation with the concatenated basis matrix turns out tobe problematic if there exists some overlap between the subspaces that the bases for the individual sources span. Inthis letter, we propose a novel approach to improve encoding vector estimation for target signal extraction. Estimatingencoding vectors from themixture data is viewed as a regression problem and a deep neural network (DNN) is usedto learn the mapping between the mixture data and the corresponding encoding vectors. To demonstrate theperformance of the proposed algorithm, experiments were conducted in the speech enhancement task. Theexperimental results show that the proposed algorithm outperforms the conventional encoding vector estimationscheme.

Title :Classification of Hyperspectral Image Based on Sparse Representation in Tangent SpaceLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/hyperspectral-image-classification-based-sparse-representationAbstract : In many real-world problems, data always lie in a low-dimensional manifold. Exploiting the manifold cangreatly enhance the discrimination between different categories. In this letter, we propose a classification frameworkbased on sparse representation to directly exploit the underlying manifold. Specifically, using the tangent plane toapproximate the local manifold of each test sample, the proposed method classifies the sample by sparserepresentation in tangent space. Unlike several existing sparse-representation-based classification methods, whichsparsely represent the test sample itself, the proposed method sparsely represents the local manifold of the testsample by tangent plane approximation. Therefore, it goes beyond the sample itself and is more robust to kinds ofvariations confronted in hyperspectral image (HSI) such as illustration differences and spectrum mixing. Experimentalresults show that the proposed algorithm outperforms several state-of-the-art methods for the classification of HSIwith limited training samples.

Title :Non-Local Means Image Denoising With a Soft ThresholdLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/non-local-means-image-denoising-with-soft-thresholdAbstract : Non-local means (NLM) are typically biased by the accumulation of small weights associated withdissimilar patches, especially at image edges. Hence, we propose to null the small weights with a soft threshold toreduce this accumulation. We call this method the NLM filter with a soft threshold (NLM-ST). Its Stein's unbiased riskestimate (SURE) approaches the true mean square error; thus, we can linearly aggregate multiple NLM-STs ofMonte-Carlo-generated parameters by minimizing SURE to surpass the performance limit of single NLM-ST, which isreferred to as the Monte-Carlo-based linear aggregation (MCLA). Finally, we employ a simple moving average filter tosmooth the MCLA image sequence to further improve the denoising performance and stability. Experiments indicatethat the NLM-ST outperforms the classic patchwise NLM and three other well-known recent variants in terms of thepeak signal-to-noise ratio (PSNR), structural similarity (SSIM), and visual quality. Furthermore, its PSNR is higherthan that of BM3D for certain images.


Title :Gabor Feature-Based Collaborative Representation for Hyperspectral Imagery ClassificationLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/hyperspectral-imagery-classification-gabor-featureAbstract : Sparse-representation-based classification (SRC) assigns a test sample to the class with minimumrepresentation error via a sparse linear combination of all the training samples, which has successfully been appliedto several pattern recognition problems. According to compressive sensing theory, the l1-norm minimization couldyield the same sparse solution as the l0 norm under certain conditions. However, the computational complexity of thel1-norm optimization process is often too high for large-scale high-dimensional data, such as hyperspectral imagery(HSI). To make matter worse, a large number of training data are required to cover the whole sample space, which isdifficult to obtain for hyperspectral data in practice. Recent advances have revealed that it is the collaborativerepresentation but not the l1-norm sparsity that makes the SRC scheme powerful. Therefore, in this paper, a 3-DGabor feature-based collaborative representation (3GCR) approach is proposed for HSI classification. When 3-D

Gabor transformation could significantly increase the discrimination power of material features, a nonparametric andeffective l2-norm collaborative representation method is developed to calculate the coefficients. Due to the simplicityof the method, the computational cost has been substantially reduced; thus, all the extracted Gabor features can bedirectly utilized to code the test sample, which conversely makes the l2-norm collaborative representation robust tonoise and greatly improves the classification accuracy. The extensive experiments on two real hyperspectral data setshave shown higher performance of the proposed 3GCR over the state-of-the-art methods in the literature, in terms ofboth the classifier complexity and generalization ability from very small training sets.

Title :Extracting Man-Made Objects From High Spatial Resolution Remote Sensing Images via Fast Level SetEvolutionsLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/extracting-man-made-objects-from-high-spatial-resolution-remote-sensing-imagesAbstract : Object extraction from remote sensing images has long been an intensive research topic in the field ofsurveying and mapping. Most past methods are devoted to handling just one type of object, and little attention hasbeen paid to improving the computational efficiency. In recent years, level set evolution (LSE) has been shown to bevery promising for object extraction in the field of image processing because it can handle topological changesautomatically while achieving high accuracy. However, the application of state-of-the-art LSEs is compromised bylaborious parameter tuning and expensive computation. In this paper, we proposed two fast LSEs for manmadeobject extraction from high spatial resolution remote sensing images. We replaced the traditional meancurvature-based regularization term by a Gaussian kernel, and it is mathematically sound to do that. Thus, we canuse a larger time step in the numerical scheme to expedite the proposed LSEs. Compared with existing methods, theproposed LSEs are significantly faster. Most importantly, they involve much fewer parameters while achieving betterperformance. Their advantages over other state-of-the-art approaches have been verified by a range of experiments.

Title :Enhanced Ridge Structure for Improving Fingerprint Image Quality Based on a Wavelet DomainLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/improving-fingerprint-image-quality-based-wavelet-domain-enhanced-ridge-structureAbstract : Fingerprint image enhancement is one of the most crucial steps in an automated fingerprint identificationsystem. In this paper, an effective algorithm for fingerprint image quality improvement is proposed. The algorithmconsists of two stages. The first stage is decomposing the input fingerprint image into four subbands by applyingtwo-dimensional discrete wavelet transform. At the second stage, the compensated image is produced by adaptivelyobtaining the compensation coefficient for each subband based on the referred Gaussian template. The experimentalresults indicated that the compensated image quality was higher than that of the original image. The proposedalgorithm can improve the clarity and continuity of ridge structures in a fingerprint image. Therefore, it can achievehigher fingerprint classification rates than related methods can.


Title :Discriminative Clustering and Feature Selection for Brain MRI SegmentationLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/brain-mri-segmentation-discriminative-clustering-feature-selectionAbstract : Automatic segmentation of brain tissues from MRI is of great importance for clinical application andscientific research. Recent advancements in supervoxel-level analysis enable robust segmentation of brain tissues byexploring the inherent information among multiple features extracted on the supervoxels.Within this prevalentframework, the difficulties still remain in clustering uncertainties imposed by the heterogeneity of tissues and theredundancy of theMRI features. To cope with the aforementioned two challenges, we propose a robust discriminativesegmentation method from the view of information theoretic learning. The prominent goal of the method is tosimultaneously select the informative feature and to reduce the uncertainties of supervoxel assignment fordiscriminative brain tissue segmentation. Experiments on two brain MRI datasets verified the effectiveness andefficiency of the proposed approach.

Title :Dimension Reduction Using Spatial and Spectral Regularized Local Discriminant Embedding for HyperspectralImage ClassificationLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/hyperspectral-dimension-reduction-using-spatial-spectral-regularized-local-discriminantAbstract : Dimension reduction (DR) is a necessary and helpful preprocessing for hyperspectral image (HSI)classification. In this paper, we propose a spatial and spectral regularized local discriminant embedding (SSRLDE)method for DR of hyperspectral data. In SSRLDE, hyperspectral pixels are first smoothed by the multiscale spatialweighted mean filtering. Then, the local similarity information is described by integrating a spectral-domain regularizedlocal preserving scatter matrix and a spatial-domain local pixel neighborhood preserving scatter matrix. Finally, theoptimal discriminative projection is learned by minimizing a local spatial-spectral scatter and maximizing a modifiedtotal data scatter. Experimental results on benchmark hyperspectral data sets show that the proposed SSRLDEsignificantly outperforms the state-of-the-art DR methods for HSI classification.

Title :Aerial Image Registration for TrackingLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/aerial-image-registration-trackingAbstract : To facilitate the tracking of moving targets in a video, the relation between the camera and the scene iskept fixed by registering the video frames at the ground level. When the camera capturing the video is fixed withrespect to the scene, detected motion will represent the target motion. However, when a camera in motion is used tocapture the video, image registration at ground level is required to separate camera motion from target motion. Animage registration method is introduced that is capable of registering images from different views of a 3-D scene inthe presence of occlusion. The proposed method is capable of withstanding considerable occlusion andhomogeneous areas in images. The only requirement of the method is for the ground to be locally flat and sufficientground cover be visible in the frames being registered. Experimental results of 17 videos fromthe Brown Universitydata set demonstrate robustness of the method in registering consecutive frames in videos covering various urbanand suburban scenes. Additional experimental results are presented demonstrating the suitability of the method inregistering images captured from different views of hilly and coastal scenes.


Title :Cardiovascular Biometrics: Combining Mechanical and Electrical SignalsLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/cardiovascular-biometrics-combining-mechanical-electrical-signalsAbstract : The electrical signal originating from the heart, the electrocardiogram (ECG), has been examined for itspotential use as a biometric. Recent ECG studies have shown that an inter-session authentication performance below6% equal error rate (EER) can be achieved using training data from two days while testing with data from a third day.More recently, a mechanical measurement of cardiovascular activity, the laser Doppler vibrometry (LDV) signal, wasproposed by our group as a biometric trait. The inter-session authentication performance of the LDV biometric systemis comparable to that of the ECG biometric system. Combining both the electrical and mechanical aspects of thecardiovascular system, an overall improvement in authentication performance can be attained. In particular, themultibiometric system achieves about 2% EER. Moreover, in the identification mode, with a testing databasecontaining 200 individuals, the rank-1 accuracy improves from about 80% for each individual biometric system, toabout 92% for the multibiometric system. Although there are implementation issues that would need to be resolvedbefore this combined method could be applied in the field, this report establishes the basis and utility of the method inprinciple, and it identifies effective signal analysis approaches.

Title :An Adaptive Pixon Extraction Technique for Multispectral/Hyperspectral Image ClassificationLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/pixon-extraction-technique-multispectral-hyperspectral-image-classificationAbstract : Hyperspectral imaging has gained significant interest in the past few decades, particularly in remotesensing applications. The considerably high spatial and spectral resolution of modern remotely sensed data oftenprovides more accurate information about the scene. However, the complexity and dimensionality of such data, aswell as potentially unwanted details embedded in the images, may act as a degrading factor in some applicationssuch as classification. One solution to this issue is to utilize the spatial-spectral features to extract segments beforethe classification step. This preprocessing often leads to better classification results and a considerable decrease incomputational time. In this letter, we propose a Pixon-based image segmentation method, which benefits from apreprocessing step based on partial differential equation to extractmore homogenous segments.Moreover, a fastalgorithm has been presented to adaptively tune the required parameters used in our Pixon-based schema. Theacquired segments are then fed into the support vector machine classifier, and the final thematic class maps areproduced. Experimental results on multi/hyperspectral data are encouraging to apply the proposed Pixons forclassification.

Title :Saliency-Guided Unsupervised Feature Learning for Scene ClassificationLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/scene-classification-saliency-guided-unsupervised-feature-learningAbstract : Due to the rapid technological development of various different satellite sensors, a huge volume ofhigh-resolution image data sets can now be acquired. How to efficiently represent and recognize the scenes fromsuch high-resolution image data has become a critical task. In this paper, we propose an unsupervised featurelearning framework for scene classification. By using the saliency detection algorithm, we extract a representative setof patches from the salient regions in the image data set. These unlabeled data patches are exploited by anunsupervised feature learning method to learn a set of feature extractors which are robust and efficient and do notneed elaborately designed descriptors such as the scale-invariant-feature-transform-based algorithm. We show thatthe statistics generated from the learned feature extractors can characterize a complex scene very well and canproduce excellent classification accuracy. In order to reduce overfitting in the feature learning step, we further employa recently developed regularization method called "dropout," which has proved to be very effective in imageclassification. In the experiments, the proposed method was applied to two challenging high-resolution data sets: theUC Merced data set containing 21 different aerial scene categories with a submeter resolution and the Sydney dataset containing seven land-use categories with a 60-cm spatial resolution. The proposed method obtained results thatwere equal to or even better than the previous best results with the UC Merced data set, and it also obtained thehighest accuracy with the Sydney data set, demonstrating that the proposed unsupervised-feature-learning-based

scene classification method provides more accurate classification results than the otherlatent-Dirichlet-allocation-based methods and the sparse coding method.


Title :A New Framework for SAR Multitemporal Data RGB Representation: Rationale and ProductsLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/sar-multitemporal-data-rgb-representationAbstract : This paper presents the multitemporal adaptive processing (MAP3) framework for the treatment ofmultitemporal synthetic aperture radar (SAR) images. The framework is organized in three major activities dealingwith calibration, adaptability, and representation. The processing chain has been designed looking at the simplicity,i.e., the minimization of the operations needed to obtain the products, and at the algorithms' availability in theliterature. Innovation has been provided in the crosscalibration step, which is solved introducing the variableamplitude levels equalization (VALE) method, through which it is possible to establish a common metrics for themeasurement of the amplitude levels exhibited by the images of the series. Representation issues are discussed withan application-based approach, supported by examples with regard to semiarid and temperate regions in whichamplitude maps and interferometric coherence are combined in an original way.

Title :Supervised Spectral-Spatial Hyperspectral Image Classification With Weighted Markov Random FieldsLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/supervised-spectral-spatial-hyperspectral-image-classification-with-weighted-markov-random-fieldsAbstract : This paper presents a new approach for hyperspectral image classification exploiting spectral-spatialinformation. Under the maximum a posteriori framework, we propose a supervised classification model which includesa spectral data fidelity term and a spatially adaptive Markov random field (MRF) prior in the hidden field. The datafidelity term adopted in this paper is learned from the sparse multinomial logistic regression (SMLR) classifier, whilethe spatially adaptive MRF prior is modeled by a spatially adaptive total variation (SpATV) regularization to enforce aspatially smooth classifier. To further improve the classification accuracy, the true labels of training samples are fixedas an additional constraint in the proposed model. Thus, our model takes full advantage of exploiting the spatial andcontextual information present in the hyperspectral image. An efficient hyperspectral image classification algorithm,named SMLR-SpATV, is then developed to solve the final proposed model using the alternating direction method ofmultipliers. Experimental results on real hyperspectral data sets demonstrate that the proposed approach outperformsmany state-of-the-art methods in terms of the overall accuracy, average accuracy, and kappa (k) statistic.

Title :Stable Mean-Shift Algorithm and Its Application to the Segmentation of Arbitrarily Large Remote SensingImagesLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/segmentation-arbitrarily-large-remote-sensing-images-stable-mean-shift-algorithmAbstract : Segmentation of real-world remote sensing images is challenging because of the large size of those data,particularly for very high resolution imagery. However, a lot of high-level remote sensing methods rely onsegmentation at some point and are therefore difficult to assess at full image scale, for real remote sensingapplications. In this paper, we define a new property called stability of segmentation algorithms and demonstrate thatpieceor tile-wise computation of a stable segmentation algorithm can be achieved with identical results with respect toprocessing the whole image at once. We also derive a technique to empirically estimate the stability of a givensegmentation algorithm and apply it to four different algorithms. Among those algorithms, the mean-shift algorithm isfound to be quite unstable. We propose a modified version of this algorithm enforcing its stability and thus allowing fortile-wise computation with identical results. Finally, we present results of this method and discuss the various trendsand applications.


Title :Reversible Image Data Hiding with Contrast EnhancementLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/reversible-image-data-hiding-contrast-enhancementAbstract : In this letter, a novel reversible data hiding (RDH) algorithm is proposed for digital images. Instead of tryingto keep the PSNR value high, the proposed algorithm enhances the contrast of a host image to improve its visualquality. The highest two bins in the histogram are selected for data embedding so that histogram equalization can beperformed by repeating the process. The side information is embedded along with the message bits into the hostimage so that the original image is completely recoverable. The proposed algorithm was implemented on two sets ofimages to demonstrate its efficiency. To our best knowledge, it is the first algorithm that achieves image contrastenhancement byRDH. Furthermore, the evaluation results show that the visual quality can be preserved after aconsiderable amount of message bits have been embedded into the contrast-enhanced images, even better thanthree specificMATLAB functions used for image contrast enhancement.

Title :Hidden Markov Model Based Dynamic Texture ClassificationLanguage : Matlab

Project Link : http://kasanpro.com/p/matlab/dynamic-texture-classification-hidden-markov-modelAbstract : The stochastic signal model, hidden Markov model (HMM), is a probabilistic function of the Markov chain.In this letter, we propose a general nth-order HMM based dynamic texture description and classification method.Specifically, the pixel intensity sequence along time of a dynamic texture ismodeled with a HMM that encodes theappearance information of the dynamic texture with the observed variables, and the dynamic properties over time withthe hidden states. A new dynamic texture sequence is classified to the category by determining whether it is the mostsimilar to this category with the probability that the observed sequence is produced by the HMMs of the trainingsamples. The experimental results demonstrate the arbitrary emission probability distribution and the higher-orderdependence of hidden states of a higher-order HMM result in better classification performance, as compared with thelinear dynamical system (LDS) based method.

Title :Rotation-Invariant Object Detection in Remote Sensing Images Based on Radial-Gradient AngleLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/rotation-invariant-object-detection-remote-sensing-images-based-radial-gradient-angleAbstract : To improve the detection precision in complicated backgrounds, a novel rotation-invariant object detectionmethod to detect objects in remote sensing images is proposed in this letter. First, a rotation-invariant feature calledradial-gradient angle (RGA) is defined and used to find potential object pixels from the detected image blocks bycombining with radial distance. Then, a principal direction voting process is proposed to gather the evidence ofobjects from potential object pixels. Since the RGA combined with the radial distance is discriminative and the votingprocess gathers the evidence of objects independently, the interference of the backgrounds is effectively reduced.Experimental results demonstrate that the proposed method outperforms other existing well-known methods (such asthe shape context-based method and rotation-invariant part-based model) and achieves higher detection precision forobjects with different directions and shapes in complicated background. Moreover, the antinoise performance andparameter influence are also discussed.


Title :A New Self-Training-Based Unsupervised Satellite Image Classification Technique Using Cluster EnsembleStrategyLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/self-training-based-unsupervised-satellite-image-classification-techniAbstract : This letter addresses the problem of unsupervised land-cover classification of remotely sensedmultispectral satellite images fromthe perspective of cluster ensembles and self-learning. The cluster ensemblescombine multiple data partitions generated by different clustering algorithms into a single robust solution. Acluster-ensemble-based method is proposed here for the initialization of the unsupervised iterativeexpectation-maximization (EM) algorithm which eventually produces a better approximation of the cluster parametersconsidering a certain statistical model is followed to fit the data. The method assumes that the number of land-coverclasses is known. A novel method for generating a consistent labeling scheme for each clustering of the consensus isintroduced for cluster ensembles. A maximum likelihood classifier is henceforth trained on the updated parameter setobtained from the EM step and is further used to classify the rest of the image pixels. The self-learning classifier,although trained without any external supervision, reduces the effect of data overlapping from different clusters whichotherwise a single clustering algorithm fails to identify. The clustering performance of the proposed method on amedium resolution and a very high spatial resolution image have effectively outperformed the results of the individualclustering of the ensemble.

Title :An Efficient SIFT-Based Mode-Seeking Algorithm for Sub-Pixel Registration of Remotely Sensed ImagesLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/sift-based-mode-seeking-algorithm-sub-pixel-registration-remotely-sensed-imagesAbstract : Several image registration methods, based on the scaled-invariant feature transform (SIFT) technique,have appeared recently in the remote sensing literature. All of these methods attempt to overcome problemsencountered by SIFT in multimodal remotely sensed imagery, in terms of the quality of its feature correspondences.The deterministic method presented in this letter exploits the fact that each SIFT feature is associated with a scale,orientation, and position to perform mode seeking (in transformation space) to eliminate outlying corresponding keypoints (i.e., features) and improve the overall match obtained. We also present an exhaustive empirical study on avariety of test cases, which demonstrates that our method is highly accurate and rather fast. The algorithm is capableof automatically detecting whether it succeeded or failed.

Title :Remote Sensing Image Segmentation Based on an Improved 2-D Gradient Histogram and MMAD ModelLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/remote-sensing-image-segmentation-based-improved-2-d-gradient-histogram-mmad-modelAbstract : A novel remote sensing image segmentation algorithm based on an improved 2-D gradient histogram andminimum mean absolute deviation (MMAD) model is proposed in this letter. We extract the global features as a 1-Dhistogram from an improved 2-D gradient histogram by diagonal projection and subsequently use the MMAD modelon the 1-D histogram to implement the optimal threshold. Experiments on remote sensing images indicate that thenew algorithm provides accurate segmentation results, particularly for images characterized by Laplace distribution

histograms. Furthermore, the new algorithm has low time consumption.


Title :An Efficient MRF Embedded Level Set Method for Image SegmentationLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/mrf-embedded-level-set-method-image-segmentationAbstract : This paper presents a fast and robust level set method for image segmentation. To enhance therobustness against noise, we embed a Markov random field (MRF) energy function to the conventional level setenergy function. This MRF energy function builds the correlation of a pixel with its neighbors and encourages them tofall into the same region. To obtain a fast implementation of the MRF embedded level set model, we explore algebraicmultigrid (AMG) and sparse field method (SFM) to increase the time step and decrease the computation domain,respectively. Both AMG and SFM can be conducted in a parallel fashion, which facilitates the processing of ourmethod for big image databases. By comparing the proposed fast and robust level set method with the standard levelset method and its popular variants on noisy synthetic images, synthetic aperture radar (SAR) images, medicalimages and natural images, we comprehensively demonstrate the new method is robust against various kinds ofnoises. Especially, the new level set method can segment an image of size 500 by 500 within three seconds onMATLAB R2010b installed in a computer with 3.30GHz CPU and 4GB memory.

Title :An EEG-Based Biometric System Using Eigenvector Centrality in Resting State Brain NetworksLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/eeg-based-biometric-system-using-eigenvector-centrality-resting-state-brain-networksAbstract : Recently, there has been a growing interest in the use of brain activity for biometric systems. However, sofar these studies have focused mainly on basic features of the Electroencephalography. In this study we propose anapproach based on phase synchronization, to investigate personal distinctive brain network organization. To this end,the importance, in terms of centrality, of different regions was determined on the basis of EEG recordings. Wehypothesized that nodal centrality enables the accurate identification of individuals. EEG signals from a cohort of 10964-channels EEGs were band-pass filtered in the classical frequency bands and functional connectivity between thesensors was estimated using the Phase Lag Index. The resulting connectivity matrix was used to construct aweighted network, from which the nodal Eigenvector Centrality was computed. Nodal centrality was successivelyused as feature vector. Highest recognition rates were observed in the gamma band (equal error rate (EER = 0.044)and high beta band (EER = 0.102). Slightly lower recognition rate was observed in the low beta band (EER = 0.144),while poor recognition rates were observed for the others frequency bands. The reported results show thatresting-state functional brain network topology provides better classification performance than using only a measureof functional connectivity, and may represent an optimal solution for the design of next generation EEG basedbiometric systems. This study also suggests that results from biometric systems based on high-frequency scalp EEGfeatures should be interpreted with caution.

Title :Image Sensor-Based Heart Rate Evaluation From Face Reflectance Using Hilbert-Huang TransformLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/heart-rate-evaluation-from-face-reflectance-using-hilbert-huang-transformAbstract : Monitoring heart rates using conventional electrocardiogram equipment requires patients to wear adhesivegel patches or chest straps that can cause skin irritation and discomfort. Commercially available pulse oximetrysensors that attach to the fingertips or earlobes also cause inconvenience for patients and the spring-loaded clips canbe painful to use. Therefore, a novel robust face-based heart rate monitoring technique is proposed to allow for theevaluation of heart rate variation without physical contact with the patient. Face reflectance is first decomposed from asingle image and then heart rate evaluation is conducted from consecutive frames according to the periodic variationof reflectance strength resulting from changes to hemoglobin absorptivity across the visible light spectrum asheartbeats cause changes to blood volume in the blood vessels in the face. To achieve a robust evaluation, ensembleempirical mode decomposition of the Hilbert-Huang transform is used to acquire the primary heart rate signal whilereducing the effect of ambient light changes. Our proposed approach is found to outperform the current state of theart, providing greater measurement accuracy with smaller variance and is shown to be feasible in real-worldenvironments.


Title :Live Video Forensics: Source Identification in Lossy Wireless NetworksLanguage : MatlabProject Link : http://kasanpro.com/p/matlab/source-identification-lossy-wireless-networksAbstract : Video source identification is very important in validating video evidence, tracking down video piracycrimes, and regulating individual video sources. With the prevalence of wireless communication, wireless videocameras continue to replace their wired counterparts in security/surveillance systems and tactical networks. However,wirelessly streamed videos usually suffer from blocking and blurring due to inevitable packet loss in wirelesstransmissions. The existing source identification methods experience significant performance degradation or even fail

to work when identifying videos with blocking and blurring. In this paper, we propose a method that is effective andefficient in identifying such wirelessly streamed videos. In addition, we also propose to incorporate wireless channelsignatures and selective frame processing into source identification, which significantly improve the identificationspeed. We conduct extensive realworld experiments to validate our method. The results show that the sourceidentification accuracy of the proposed scheme largely outperforms the existing methods in the presence of videoblocking and blurring. Moreover, our method is able to identify the video source in a near-real-time fashion, which canbe used to detect the wireless camera spoofing attack.

Education

IEEE 2015 Matlab Projects