Abstract：High dimensional data is sensitive to noise and the curse of dimensionality problem appears easily. A local discriminant projection algorithm based on random subspace(RSLDP) is proposed. The attributes of original high dimensional data are selected by random subspace method to generate a low dimensional subspace, and the nearest neighbor graphs are constructed in the low dimensional subspace. Thus, the influence of noise is reduced effectively. By RSLDP, the local inter-class weighted scatter is maximized, the local intra-class weighted scatter is minimized, and simultaneously the local scatter on data is minimized as well. Consequently, the performance of local maximal margin discriminant embedding (LMMDE) algorithm is improved.The relationship between the focusing point and its inter-class/intra-class nearest neighbor center point is well characterized by RSLDP. The effectiveness of the proposed algorithm is verified by the experiments on CMU PIE and AR face datasets.
[1] SHEN X B, SUN Q S, YUAN Y H. A Unified Multiset Canonical Correlation Analysis Framework Based on Graph Embedding for Multiple Feature Extraction. Neurocomputing, 2015, 148: 397-408. [2] JING X Y, WU F, ZHU X K, et al. Multi-spectral Low-Rank Structured Dictionary Learning for Face Recognition. Pattern Recognition, 2016, 59: 14-25. [3] YE Q L, YE N, YIN T M. Fast Orthogonal Linear Discriminant Analysis with Applications to Image Classification. Neurocomputing, 158: 216-224. [4] ZHANG C L, ZHANG S W. A Supervised Orthogonal Discriminant Projection for Tumor Classification Using Gene Expression Data. Computers in Biology and Medicine, 2013, 43(5): 568-575. [5] YAMBOR W S, DRAPER B A, BEVERIDGE J R. Analyzing PCA-Based Face Recognition Algorithm: Eigenvector Selection and Distance Measures[C/OL]. [2016-08-20]. http://www.cs.colostate.edu/~vision/publications/eemcvcsu2000.pdf. [6] MARITINEZ A M, KAK A C. PCA Versus LDA. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2): 228-233. [7] LUNGA D, PRASAD S, CRAWFORD M M, et al. Manifold-Lear-ning-Based Feature Extraction for Classification of Hyperspectral Data: A Review of Advances in Manifold Learning. IEEE Signal Processing Magazine, 2014, 31(1): 55-66. [8] HE X F, YAN S C, HU Y X, et al. Face Recognition Using Laplacian Faces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340. [9] LI B, WANG C, HUANG D S. Supervised Feature Extraction Based on Orthogonal Discriminant Projection. Neurocomputing, 2009, 73(1/2/3): 191-196. [10] ZHANG H G, DENG W H, GUO J, et al. Locality Preserving and Global Discriminant Projection with Prior Information. Machine Vision and Applications, 2010, 21(4): 577-585.
[11] LIN K Z, RONG Y H, WU D, et al. Discriminant Locality Preserving Projections Based on Neighborhood Maximum Margin. International Journal of Hybrid Information Technology, 2014, 7(6): 165-174. [12] WONG W K, ZHAO H T. Supervised Optimal Locality Preserving Projection. Pattern Recognition, 2012, 45(1): 186-197. [13] HUANG P, TANG Z M, CHEN C K, et al. Local Maximal Margin Discriminant Embedding for Face Recognition. Journal of Visual Communication and Image Representation, 2014, 25(2): 296-305. [14] CAI X F, WEI J, WEN G H, et al. Local and Global Preserving Semisupervised Dimensionality Reduction Based on Random Subspace for Cancer Classification. IEEE Journal of Biomedical and Health Informatics, 2014, 18(2): 500-507. [15] ZHANG S W, LEI Y K, WU Y H, et al.Modified Orthogonal Discriminant Projection for Classification. Neurocomputing, 2011, 74(17): 3690-3694. [16] SIM T, BAKER S, BSAT M. The CMU Pose, Illumination, and Expression Database. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12): 1615-1618. [17] MARTINEZ A, BENAVENTE R. The AR Database. Technical Report, 24. Barcelona, Spain: Computer Vision Center(CVC), 1998.
2017, Vol. 30 
