Rahman Khorsandi

Online multi-modal task-driven dictionary learning and robust joint sparse representation for visual tracking

Robust visual tracking is a challenging problem due to pose variance, occlusion and cluttered backgrounds. No single feature can be robust to all possible scenarios in a video sequence. However, exploiting multiple features has demonstrated its effectiveness in overcoming challenging situations in visual tracking. We propose a new framework for multi-modal fusion at both the feature level and decision level by training a reconstructive and discriminative dictionary and classifier for each modality simultaneously with the additional constraint of label consistency across different modalities. In addition, a joint decision measure is designed based on both reconstruction and classification error to adaptively adjust the weights of different features such that unreliable features can be removed from tracking. The proposed tracking scheme is referred to as the label-consistent and fusion-based joint sparse coding (LC-FJSC). Extensive experiments on publicly available videos demonstrate that LC-FJSC outperforms state-of-the-art trackers.

Gender classification using 2-D ear images and sparse representation

Gender classification attracted the attention of researchers in computer vision for its use in many applications. Researches have addressed this issue based on facial images. In this paper, we present the first approach for gender classification using 2-D ear images based upon sparse representation. In sparse representation, the training data is used to develop a dictionary based on extracted features. In this work, Gabor filters are used for feature extraction. Classification is achieved by representing the test data using the dictionary based upon the extracted features. Experimental results conducted on the University of Notre Dame (UND) collection J dataset, containing large appearance, pose, and lighting variability, yielded gender classification rate of 89.49%.

Ear recognition via sparse representation and Gabor filters

In this paper, we present a fully automated approach for ear recognition based upon sparse representation. In sparse representation, features extracted from the training data of each subject are used to develop a dictionary. In this work, Gabor filters are used for feature extraction. Classification is performed by extracting features from the test data and using the dictionary for representing the test data. The class of the test data is then determined based upon the involvement of the dictionary entries in its representation. Experimental results conducted on the University of Notre Dame (UND) collection G dataset, containing large appearance, pose, and lighting variability, yielded a rank-one recognition rate of 98.46%. The proposed system outperforms the method described in [1], which achieves a recognition rate of 96.88% when evaluated on the same dataset. Moreover, the proposed system was evaluated on a greater number of test images per subject, demonstrating its robustness.

Gender Classification Using Facial Images and Basis Pursuit

In many social interactions, it is important to correctly recognize the gender. Researches have addressed this issue based on facial images, ear images and gait. In this paper, we present an approach for gender classification using facial images based upon sparse representation and Basis Pursuit. In sparse representation, the training data is used to develop a dictionary based on extracted features. Classification is achieved by representing the extracted features of the test data using the dictionary. For this purpose, basis pursuit is used to find the best representation by minimizing the l 1 norm. In this work, Gabor filters are used for feature extraction. Experimental results are conducted on the FERET data set and obtained results are compared with other works in this area. The results show improvement in gender classification over existing methods.

Joint weighted dictionary learning and classifier training for robust biometric recognition

In this paper, we present an automated system for robust biometric recognition based upon sparse representation and dictionary learning. In sparse representation, extracted features from the training data are used to develop a dictionary. Training data of real world applications are likely to be exposed to geometric transformations, which is a big challenge for designing of discriminative dictionaries. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. We propose joint weighted dictionary learning and classifier training (JWDL-CT) approach which simultaneously learns from a set of training samples along with weight vectors that correspond to the atoms in the learnt dictionary. The components of the weight vector associated with an atom represent the relationship between the atom and each of the classes. The weight vectors and atoms are jointly obtained during the dictionary learning. In the proposed method, a constraint is imposed on the correlation between the atoms to decrease the similarity between these atoms. The proposed dictionary learning objective function enhances the class-discrimination capabilities of individual atoms that renders the designed dictionaries especially suitable for classification of query images with very sparse representation. Experiments conducted on the West Virginia University (WVU) and the University of Notre Dame (UND) datasets for ear recognition show that the proposed method outperforms other state-of-the-art classifiers.

Classification based on weighted sparse representation using smoothed L 0 norm with non-negative coefficients

We present a novel classification technique based on sparse representation. The main idea of sparse representation for classification is the assumption that the training samples, or atoms, for a particular class form a linear basis for any new test sample that belongs to that class. Currently, most of the methods for sparse representation classification do not apply constraints to the coefficients that form the linear combination of the atoms, which leads to coefficients that can be positive or negative. In addition, all the training samples in the dictionary are treated equally. In this paper, we impose non-negative constraint on the components of the coefficient vector to ensure that the coefficient vector represents the contributions of the training samples towards the query, which is more natural for classification purposes. We also use the mutual information between the query sample and each of the training samples to obtain a weight for each of the atoms in the dictionary. These weights have the effect of reducing the search space and speeding the convergence of the algorithm in finding the coefficient vector. Experiments conducted on the Extended Yale B database for face recognition and on the University of Notre Dame (UND) database for ear recognition show that the proposed non-negative weighted sparse representation obtained by smoothed l0 norm outperforms other state-of-the-art classifiers.

Ear biometrics and sparse representation based on smoothed l 0 norm

Ear biometrics attracted the attention of researchers in computer vision and machine learning for its use in many applications. In this paper, we present a fully automated system for recognition from ear images based upon sparse representation. In sparse representation, extracted features from the training data is used to develop a dictionary. Classification is achieved by representing the extracted features of the test data as a linear combination of entries in the dictionary. In fact, there are many solutions for this problem and the goal is to find the sparsest solution. We use a relatively new algorithm named smoothed l0 norm to find the sparsest solution and Gabor wavelet features are used for building the dictionary. Furthermore, we expand the proposed approach for gender classification from ear images. Several researches have addressed this issue based on facial images. We introduce a novel approach based on majority voting for gender classification. Experimental results conducted on the University of Notre Dame (UND) collection J data set, containing large appearance, pose, and lighting variations, resulted in a gender classification rate of 89.49%. Furthermore, the proposed method is evaluated on the WVU data set and classification rates for different view angles are presented. Results show improvement and great robustness in gender classification over existing methods.

Multimodal weighted dictionary learning

Classical dictionary learning algorithms that rely on a single source of information have been successfully used for the discriminative tasks. However, exploiting multiple sources has demonstrated its effectiveness in solving challenging real-world situations. We propose a new framework for feature fusion to achieve better classification performance as compared to the case where individual sources are utilized. In the context of multimodal data analysis, the modality configuration induces a strong group/coupling structure. The proposed method models the coupling between different modalities in space of sparse codes while at the same time within each modality a discriminative dictionary is learned in an all-vs-all scheme whose class-specific sub-parts are non-correlated. The proposed dictionary learning scheme is referred to as the multimodal weighted dictionary learning (MWDL). We demonstrate that MWDL outperforms state-of-the-art dictionary learning approaches in various experiments.

Robust object tracking via adaptive sparse representation

In this paper, we present a robust object tracking system capable of handling pose and scale variations. The system is based on adaptive sparse representation and dictionary learning. We focus on the problem of automatic tracking with no prior knowledge other than the location of the region to be tracked in the first frame, which could be located by a detector. The detected region, i.e., a bounding box, and some samples near the bounding box are extracted as positive samples. In addition, we select regions outside the bounding box as negative samples. Both, positive and negative samples are used to build the dictionary and we use K-SVD method for dictionary learning in order to decrease the number of atoms and improve the processing speed. One of the main drawbacks in tracking systems is false tracking when the object is not in the frame any more. We overcome this problem by comparing the newly tracked region with previously tracked regions to find out if the object is still in the frame or not. If the object is not in the frame, the algorithm stops tracking and starts searching for the object using the sparse detector in the following frames. Experiments on video sequences demonstrate the effectiveness and robustness of the proposed system for tracking.