A novel nonlinear dimensionality reduction method named kernel neighborhood preserving discriminant embedding (KNPDE) was proposed in order to extract nonlinear feature in high dimensional face image. The within-class affinity matrix and the between-class similarity matrix were constructed respectively in order to represent the within-class neighborhood geometry and the similarity between the samples from different classes in feature space. KNPDE integrated neighborhood preserving embedding (NPE) with Fisher discriminant criterion by using kernel trick. KNPDE possessed much more power in classification, which preserve the within-class neighborhood geometry in feature space and sufficiently use the between-class discriminant information. Experimental results on the Yale and the UMIST face databases demonstrated the effectiveness of the algorithm.
［1］ LI S Z, JAIN A K. Handbook of face recognition ［M］. NewYork: Springer, 2005: 153-156. ［2］ ROWEIS S T, SAUL L K. An introduction to locally linear embedding ［R］. ［S.l.］: AT&T, 2000. ［3］ SHASHUA A, LEVIN A, AVIDAN S. Manifold pursuit: a new approach to appearance based recognition ［C］∥ 16th International Conference on Pattern Recognition. Quebec City: ［s. n.］, 2002: 590-594. ［4］ TAYLOR J S, CRISTIANINI N. Kernel methods for pattern analysis ［M］. London: Cambridge University Press, 2004: 25-45. ［5］ SCHOLKOPF B, SMOLA A, MULLER K R. Nonlinear component analysis as a kernel eigenvalue problem ［J］. Neural Computation, 1998, 10(5): 1299-1319. ［6］ YANG M H. Kernel eigenfaces vs. kernel Fisherfaces: face recognition using kernel methods ［C］∥ Proceedings of the 5th IEEE International Conference on Automatic Face and Gesture Recognition. Washington D.C: IEEE, 2002: 215-220. ［7］ PLESS R, SOUVENIR R. A survey of manifold learning for images ［J］. IPSJ Transactions on Computer Vision and Applications, 2009, 1(1): 83-94. ［8］ ROWEIS S T, SAUL K L. Nonlinear dimensionality reduction by locally linear embedding ［J］. Science, 2000, 290(5500): 2323-2326. ［9］ TENENBAUM J B, DE SILVA V, LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction ［J］. Science, 2000, 290(5500): 2319-2323. ［10］ BELKIN M, NIYOGI P. Laplacian Eigenmaps and spectral techniques for embedding and clustering ［C］∥ Neural Information Processing Systems. Vancouver: MIT, 2001: 585-591. ［11］ CHUNG F R K. Spectral graph theory ［M］. Providence: American Mathematical Society, 1997: 12-24. ［12］ 罗四维,赵连伟.基于谱图理论的流形学习算法［J］.计算机研究与发展,2006,43(7): 1173-1179. LUO Siwei, ZHAO Lianwei. Manifold learning algorithms based on spectral graph theory ［J］. Journal of Computer Research and Development, 2006, 43(7): 1173-1179. ［13］ HE X F, NIYOGI P. Locality preserving projections ［C］∥Advance in Neural Information Processing Systems. Vancouver: MIT, 2003. ［14］ HE X F, YAN S C, HU Y X, et al. Learning a locality preserving subspace for visual recognition ［C］∥ Proceedings of the 9th IEEE International Conference on Computer Vision. Nice : IEEE, 2003: 385-392. ［5］ HE X F, YAN S C, HU Y X, et al. Face recognition using Laplacianfaces ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340. ［16］ HE X F, CAI D, YAN S, et al. Neighborhood preserving embedding ［C］ ∥ Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing: IEEE, 2005: 1208-1213. ［17］ 王国强,欧宗瑛,刘典婷,等. 基于保持近邻判别嵌入的人脸识别［J］.大连理工大学学报,2008,48(3): 378-382. WANG Guoqiang, OU Zongying, LIU Dianting, et al. Face recognition using preserving discriminaembedding ［J］. Journal of Dalian University of Technology, 2008, 48(3): 378-382. ［18］ KOKIOPOULOU E, SAAD Y. Orthogonal neighborhood preserving projections: a projectionbased dimensionality reduction technique ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12): 2143-2156. ［19］ 边肇棋,张学工.模式识别［M］.北京:清华大学出版社,2000: 88-89.
