Discriminant embedding by sparse representation and nonparametric discriminant analysis for face recognition

Abstract

A novel supervised dimensionality reduction algorithm, named discriminant embedding by sparse representation and nonparametric discriminant analysis (DESN), was proposed for face recognition. Within the framework of DESN, the sparse local scatter and multi-class nonparametric between-class scatter were exploited for within-class compactness and between-class separability description, respectively. These descriptions, inspired by sparse representation theory and nonparametric technique, are more discriminative in dealing with complex-distributed data. Furthermore, DESN seeks for the optimal projection matrix by simultaneously maximizing the nonparametric between-class scatter and minimizing the sparse local scatter. The use of Fisher discriminant analysis further boosts the discriminating power of DESN. The proposed DESN was applied to data visualization and face recognition tasks, and was tested extensively on the Wine, ORL, Yale and Extended Yale B databases. Experimental results show that DESN is helpful to visualize the structure of high-dimensional data sets, and the average face recognition rate of DESN is about 9.4%, higher than that of other algorithms.

Keywords

dimensionality reduction / sparse representation / nonparametric discriminant analysis

References

[1] JainA, DuinR, MaoJ. Statistical pattern recognition: A review [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(1): 4-37

[2] JolliffeI TPrincipal component analysis, second edition [M], 2002New YorkSpringer-Verlag6-10

[3] BelhumeurP, HepanhaJ, KriegmanD. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720

[4] LinT, ZhaH-bin. Riemannian manifold learning [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(5): 796-809

[5] TenenbaumJ B, SilvaV D, LangfordJ C. A global geometric framework for nonlinear dimensionality reduction [J]. Science, 2000, 290: 2319-2323

[6] RoweisS T, SaulL K. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2000, 290: 2323-2326

[7] HeX-f, CaiD, YanS-c, ZhangH-Jiang. Neighborhood preserving embedding [C]. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2005New YorkIEEE Computer Society1208-1213

[8] HeX-f, YanS-c, HuY-x, NiyogiP, ZhangH-Jiang. Face recognition using Laplacianfaces [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340

[9] YanS-c, XuD, ZhangB-y, ZhangH-J, YangQ, LinStephen. Graph embedding and extensions: A general framework for dimensionality reduction [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51

[10] XiangS-m, NieF-p, ZhangC-s, ZhangC-xia. Nonlinear dimensionality reduction with local spline embedding [J]. IEEE Transactions on Knowledge and Data Engineering, 2009, 21(9): 1285-1298

[11] QiaoH, ZhangP, WangD, ZhangBo. An explicit nonlinear mapping for manifold learning [J]. IEEE Transactions on System, Man and Cybernetics-Part B: Cybernetics, 2012, 99: 1-13

[12] WangH-xian. Structured sparse linear graph embedding [J]. Neural Networks, 2012, 27: 38-44

[13] QiaoL-s, ChenS-c, TanX-yang. Sparsity preserving projections with applications to face recognition [J]. Pattern Recognition, 2010, 43: 331-341

[14] RaduT, LucV G. Sparse representation based projections [C]. Proceedings of the 22nd British Machine Vision Conference (BMVC), 2011DundeeBMVA Press1-12

[15] FukunagaKIntroduction to statistical pattern recognition [M], 1990BostonAcademic Press466-479

[16] ZhangZ-y, WangJ, ZhaH-yuan. Adaptive manifold learning [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(2): 253-265

[17] GaoX-f, LiangJ-ye. The dynamical neighborhood selection based on the sampling density and manifold curvature for isometric data embedding [J]. Pattern Recognition Letters, 2011, 32: 202-209

[18] WrightJ, YangA Y, GaneshA, SastryS S, MaYi. Robust face recognition via sparse representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227

[19] YanS-c, WangHuan. Semi-supervised learning by sparse representation [C]. Proceedings of the SIAM International Conference on Data Mining, 2009PhiladelphiaSIAM Press792-801

[20] BressanM, VitriaJ. Nonparametric discriminant analysis and nearest neighbor classification [J]. Pattern Recognition Letters, 2003, 24(15): 2743-2749

[21] LiZ-f, LinD-h, TangX-ou. Nonparametric discriminant analysis for face recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(4): 755-761

[22] JiaY-q, NieF-p, ZhangC-shui. Trace ratio problem revisited [J]. IEEE Transactions on Neural Network, 2009, 20(4): 729-735

[23] ZhaoM-b, ZhangZ, ChowT W. Trace ratio criterion based generalized discriminative learning for semi-supervised dimensionality reduction [J]. Pattern Recognition, 2012, 45: 1482-1499