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

ABSTRACT 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.

139 Reads
  • 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 "
    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.
  • Source
    • "We first introduce the low rank in the multi-view feature selection for (1) measuring sample significance with respect to different views, and (2) capturing the related patterns across views. For high-dimensional single-view data, sparse feature selection methods such as Lasso [19] and its variants [20], [21], [22], [23], [24] have been successfully applied to many applications , e.g., medical image analysis [25], face recognition [26] and social network analysis [27]. In this paper, Lasso is extended to a multi-view learning scenario by considering the correlation across views, where the most significant features of multi-views can be simultaneously selected. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Learning about multiview data involves many applications, such as video understanding, image classification, and social media. However, when the data dimension increases dramatically, it is important but very challenging to remove redundant features in multiview feature selection. In this paper, we propose a novel feature selection algorithm, multiview rank minimization-based Lasso (MRM-Lasso), which jointly utilizes Lasso for sparse feature selection and rank minimization for learning relevant patterns across views. Instead of simply integrating multiple Lasso from view level, we focus on the performance of sample-level (sample significance) and introduce pattern-specific weights into MRM-Lasso. The weights are utilized to measure the contribution of each sample to the labels in the current view. In addition, the latent correlation across different views is successfully captured by learning a low-rank matrix consisting of pattern-specific weights. The alternating direction method of multipliers is applied to optimize the proposed MRM-Lasso. Experiments on four real-life data sets show that features selected by MRM-Lasso have better multiview classification performance than the baselines. Moreover, pattern-specific weights are demonstrated to be significant for learning about multiview data, compared with view-specific weights.
    IEEE transactions on neural networks and learning systems 02/2015; DOI:10.1109/TNNLS.2015.2396937 · 4.29 Impact Factor
Show more

Preview (2 Sources)

139 Reads
Available from