Conference Paper

Robust sparse coding for face recognition

Hong Kong Polytech. Univ., Hong Kong, China
DOI: 10.1109/CVPR.2011.5995393 Conference: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Source: IEEE Xplore


Recently the sparse representation (or coding) based classification (SRC) has been successfully used in face recognition. In SRC, the testing image is represented as a sparse linear combination of the training samples, and the representation fidelity is measured by the l2-norm or l1-norm of coding residual. Such a sparse coding model actually assumes that the coding residual follows Gaussian or Laplacian distribution, which may not be accurate enough to describe the coding errors in practice. In this paper, we propose a new scheme, namely the robust sparse coding (RSC), by modeling the sparse coding as a sparsity-constrained robust regression problem. The RSC seeks for the MLE (maximum likelihood estimation) solution of the sparse coding problem, and it is much more robust to outliers (e.g., occlusions, corruptions, etc.) than SRC. An efficient iteratively reweighted sparse coding algorithm is proposed to solve the RSC model. Extensive experiments on representative face databases demonstrate that the RSC scheme is much more effective than state-of-the-art methods in dealing with face occlusion, corruption, lighting and expression changes, etc.

1 Follower
161 Reads
  • Source
    • ". Some other studies investigate the applications of sparse coding in image restoration [32], traffic sign recognition [26], face recognition [44] "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a new computational model of visual attention based on the relevant characteristics of the Human Visual System (HVS) and sparse features. The input image is first divided into small image patches. Then the sparse features of each patch are extracted based on the learned independent components. The human visual acuity is adopted in calculation of the center-surround differences between image patches for saliency extraction. We choose the neighboring patches for center-surround difference calculation based on the relevant characteristics of the HVS. Furthermore, the center-bias factor is adopted to enhance the saliency map. Experimental results show that the proposed saliency detection model achieves better performance than the relevant existing ones on a large public image database with ground truth.
    Information Sciences 07/2015; 309. DOI:10.1016/j.ins.2015.03.004 · 4.04 Impact Factor
  • Source
    • ", [14], we use the Logistic weight function to determine w for fair comparison with RSC in [15], whose loss function φ(·) and weight function ω(·) (as shown in Fig. 1) are respectively defined as "
    [Show abstract] [Hide abstract]
    ABSTRACT: Sparse representation-based classifier (SRC), which represents a test sample with a linear combination of training samples, has shown promise in pattern classification. However, there are two shortcomings in SRC: (1) the ℓ1-norm used to measure the reconstruction fidelity is noise-sensitive and (2) the ℓ2-norm induced sparsity did not consider the correlation among the training samples. Furthermore, in real applications, face images with similar variations, such as illumination or expression, often have higher correlation than those from the same subject. Therefore, we propose to improve the performance of SRC from two aspects: (1) replace the noise-sensitive ℓ2-norm with an M-estimator to enhance its robustness and (2) emphasize the sparsity of the number of classes instead of the number of training samples, which leads to the group sparsity. The proposed robust group sparse representation (RGSR) can be efficiently optimized via alternating minimization under the Half-Quadratic (HQ) framework. Extensive experiments on representative face data sets show that RGSR can achieve competitive performance in face recognition and outperforms several state-of-the-art methods in dealing with various types of noise such as corruption, occlusion and disguise.
    Canadian Conference on Electrical and Computer Engineering; 05/2015
  • Source
    • "With its inspirational roots in human vision system [16], [17], this technique has been successfully employed in image restoration [18], [19], [20], compressive sensing [21], [22] and morphological component analysis [23]. More recently, sparse representation based approaches have also shown promising results in face recognition and gender classification [9], [8], [10], [13], [24], [25], [26], texture and handwritten digit classification [14], [29], [30], [31], natural image and object classification [9], [11], [32] and human action recognition [33], [34], [35], [36]. The success of these approaches comes from the fact that a sample from a class can generally be well represented as a sparse linear combination of the other samples from the same class, in a lower dimensional manifold [8]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data. The proposed approach infers probability distributions over the atoms of a discriminative dictionary using a Beta Process. It also computes sets of Bernoulli distributions that associate class labels to the learned dictionary atoms. This association signifies the selection probabilities of the dictionary atoms in the expansion of class-specific data. Furthermore, the non-parametric character of the proposed approach allows it to infer the correct size of the dictionary. We exploit the aforementioned Bernoulli distributions in separately learning a linear classifier. The classifier uses the same hierarchical Bayesian model as the dictionary, which we present along the analytical inference solution for Gibbs sampling. For classification, a test instance is first sparsely encoded over the learned dictionary and the codes are fed to the classifier. We performed experiments for face and action recognition; and object and scene-category classification using five public datasets and compared the results with state-of-the-art discriminative sparse representation approaches. Experiments show that the proposed Bayesian approach consistently outperforms the existing approaches.
Show more

Similar Publications

Preview (2 Sources)

161 Reads
Available from