A regularized low-rank representation model for facial expression recognition

Subspace learning plays a key role in pattern recognition and machine learning. However, its performance would be degraded when data are corrupted by various occlusions. Low-rank representation (LRR) can recover the corrupted data and explore low-dimensional subspace structures embedded in data. Inspired by low-rank representation and subspace learning, in this paper, we propose a regularized low-rank representation model, which not only learns a low-rank matrix that can capture the global structure of data, but also derives a robust subspace from the corrupted data. The problem can be formulated a rank minimization objective function, which is effectively solved by numerical algorithm. The extensive experimental results on two facial expression databases demonstrate the effectiveness of the proposed method.

[1]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  ChenSongcan,et al.  Sparsity preserving projections with applications to face recognition , 2010 .

[4]  Wei Jia,et al.  Discriminant sparse neighborhood preserving embedding for face recognition , 2012, Pattern Recognit..

[5]  Yi Ma,et al.  The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices , 2010, Journal of structural biology.

[6]  G. Sapiro,et al.  A collaborative framework for 3D alignment and classification of heterogeneous subvolumes in cryo-electron tomography. , 2013, Journal of structural biology.

[7]  Yong Yu,et al.  Robust Recovery of Subspace Structures by Low-Rank Representation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Takeo Kanade,et al.  Comprehensive database for facial expression analysis , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[9]  JiShuiwang,et al.  Discriminant sparse neighborhood preserving embedding for face recognition , 2012 .

[10]  Shuicheng Yan,et al.  Learning With $\ell ^{1}$-Graph for Image Analysis , 2010, IEEE Transactions on Image Processing.

[11]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[12]  YanShuicheng,et al.  Learning with l1-graph for image analysis , 2010 .

[13]  Michael J. Lyons,et al.  Coding facial expressions with Gabor wavelets , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[14]  Shuyuan Yang,et al.  Low-rank representation with local constraint for graph construction , 2013, Neurocomputing.

[15]  Takeo Kanade,et al.  The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[16]  Daoqiang Zhang,et al.  Efficient and robust feature extraction by maximum margin criterion , 2003, IEEE Transactions on Neural Networks.

[17]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[18]  Nenghai Yu,et al.  Non-negative low rank and sparse graph for semi-supervised learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Xiaoyang Tan,et al.  Pattern Recognition , 2016, Communications in Computer and Information Science.

[20]  Hailin Zhang,et al.  Discriminative sparsity preserving projections for image recognition , 2015, Pattern Recognit..