Kernel direct discriminant analysis and its theoretical foundation

被引：8

作者：

Liang, ZZ ^{[1
]}

Shi, PF ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai 200030, Peoples R China

来源：

PATTERN RECOGNITION | 2005年 / 38卷 / 03期

基金：

中国国家自然科学基金;

关键词：

kernel discriminant analysis; QR decomposition; face recognition; feature extraction;

D O I：

10.1016/j.patcog.2004.07.007

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, the method of kernel direct discriminant analysis is analyzed from a new viewpoint and its theoretical foundation is revealed. Based on this result, an efficient and robust method is proposed. That is, the QR decomposition on the small-size matrix is adopted and then a small eigenvalue problem is solved. Finally, experimental results on ORL face database show that the proposed method is effective and feasible. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：445 / 447

页数：3

共 5 条

[1] Generalized discriminant analysis using a kernel approach
Baudat, G
Anouar, FE
[J]. NEURAL COMPUTATION, 2000, 12 (10) : 2385 - 2404
[2] Fukunaga K., 1990, INTRO STAT PATTERN R
[3] Face recognition using kernel direct discriminant analysis algorithms
Lu, JW
Plataniotis, KN
Venetsanopoulos, AN
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (01): : 117 - 126
[4] Nonlinear component analysis as a kernel eigenvalue problem
Scholkopf, B
Smola, A
Muller, KR
[J]. NEURAL COMPUTATION, 1998, 10 (05) : 1299 - 1319
[5] Essence of kernel Fisher discriminant: KPCA plus LDA
Yang, J
Jin, Z
Yang, JY
Zhang, D
Frangi, AF
[J]. PATTERN RECOGNITION, 2004, 37 (10) : 2097 - 2100

← 1 →