Kernel ICA: An alternative formulation and its application to face recognition

被引：79

作者：

Yang, J ^{[1
]}

Gao, XM

Zhang, D

Yang, JY

机构：

[1] Hong Kong Polytech Univ, Dept Comp, Kowloon, Hong Kong, Peoples R China

[2] Nanjing Univ Sci & Technol, Dept Comp Sci, Nanjing 210094, Peoples R China

来源：

PATTERN RECOGNITION | 2005年 / 38卷 / 10期

基金：

中国国家自然科学基金;

关键词：

kernel-based methods; independent component analysis (ICA); principal component analysis (PCA); feature extraction; face recognition;

D O I：

10.1016/j.patcog.2005.01.023

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper formulates independent component analysis (ICA) in the kernel-inducing feature space and develops a two-phase kernel ICA algorithm: whitened kernel principal component analysis (KPCA) plus ICA. KPCA spheres data and makes the data structure become as linearly separable as possible by virtue of an implicit nonlinear mapping determined by kernel. ICA seeks the projection directions in the KPCA whitened space, making the distribution of the projected data as non-gaussian as possible. The experiment using a subset of FERET database indicates that the proposed kernel ICA method significantly outperform ICA, PICA and KPCA in terms of the total recognition rate. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：1784 / 1787

页数：4

共 5 条

[1] Bach F.R., 2002, J MACHINE LEARNING R, V3, P1
[2] Face recognition by independent component analysis
Bartlett, MS
Movellan, JR
Sejnowski, TJ
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (06): : 1450 - 1464
[3] Hyvärinen A, 2001, INDEPENDENT COMPONENT ANALYSIS: PRINCIPLES AND PRACTICE, P71
[4] Independent component analysis of Gabor feature's for face recognition
Liu, CJ
Wechsler, H
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (04): : 919 - 928
[5] Nonlinear component analysis as a kernel eigenvalue problem
Scholkopf, B
Smola, A
Muller, KR
[J]. NEURAL COMPUTATION, 1998, 10 (05) : 1299 - 1319

← 1 →