Classwise Sparse and Collaborative Patch Representation for Face Recognition

Abstract

Sparse representation has shown its merits in solving some classification problems and delivered some impressive results in face recognition. However, the unsupervised optimization of the sparse representation may result in undesired classification outcome if the variations of the data population are not well represented by the training samples. In this paper, a method of class-wise sparse representation (CSR) is proposed to tackle the problems of the conventional sample-wise sparse representation and applied to face recognition. It seeks an optimum representation of the query image by minimizing the class-wise sparsity of the training data. To tackle the problem of the uncontrolled training data, this paper further proposes a collaborative patch (CP) framework, together with the proposed CSR, named CSR-CP. Different from the conventional patch-based methods that optimize each patch representation separately, the CSR-CP approach optimizes all patches together to seek a CP groupwise sparse representation by putting all patches of an image into a group. It alleviates the problem of losing discriminative information in the training data caused by the partition of the image into patches. Extensive experiments on several benchmark face databases demonstrate that the proposed CSR-CP significantly outperforms the sparse representation-related holistic and patch-based approaches.

Robust Face Recognition With Kernelized Locality-Sensitive Group Sparsity Representation

“…The figure in [21] illustrates the failure case of SRC and GSRC, in which four training samples (i.e., a1,1, a1,2, a2,1, a2,2) from two individuals (triangle and diamond) and a query sample y (circle) are shown. If the subspaces spanned by two individuals are highly correlated, the query sample can be well represented by the samples of either triangle or diamond subject, i.e.…”

“…Elhamifar et al [20] proposed a more robust group sparse representation (GSRC) method, which aims to represent the test image using the minimum number of groups/blocks. In [21], Lai et al further extended group lasso to class-wise sparse representation (CSR) by laying more stress on the sparsity between the classes during optimization. More recently, Jiang et al [22] proposed a low-rank dictionary decomposition bases sparse-and densehybrid representation method to overcome the problem of corrupted training data and insufficient representative samples in each class.…”

Generic and attribute-specific deep representations for maritime vessels

“…Especially, face recognition has been studied extensively, and state-of-the-art methods [31,32], which perform effectively on the benchmark datasets [33][34][35], have been proposed. Since encouraging performance results are obtained with recent methods, another application performed, utilizing MARVEL, is vessel recognition task, where the ultimate goal is to perceive a vessel's identity by its visual appearance.…”

Patch Based Collaborative Representation with Gabor Feature and Measurement Matrix for Face Recognition

“…The PCRC and some related works [17,18] have demonstrated their effects on small sample size problem of FR; however, some key issues remain to be further optimized. On one hand, all the PCRC related works used the original face feature, but the original feature cannot effectively handle the variations of illumination, pose, facial expression, and noise [19].…”