Face Recognition Using Heteroscedastic Weighted Kernel Discriminant Analysis

• Published in: Lecture notes in computer science pp. 199 - 205
• Main Authors: Liang, Yixiong, Gong, Weiguo, Li, Weihong, Pan, Yingjun
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Data processing. List processing. Character string processing; Exact sciences and technology; Face Pattern; Face Recognition; Fisher Criterion; Kernel Trick; Linear Discriminant Analysis; Memory organisation. Data processing; Pattern recognition. Digital image processing. Computational geometry; Software; Discriminant analysis; Face recognition; Classification; Facies; Database; Pattern recognition; Data mining; Principal component analysis; Heteroscedasticity; Kernel method
• ISBN: 9783540288336; 3540288333; 3540287574; 9783540287575
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11552499_23

In this paper, we propose a novel heteroscedastic weighted kernel discriminant analysis (HW-KDA) method that extends the linear discriminant analysis (LDA) to deal explicitly with heteroscedasticity and nonlinearity of the face pattern’s distribution by integrating the weighted pairwise Chernoff criterion and Kernel trick. The proposed algorithm has been tested, in terms of classification rate performance, on the multiview UMIST face database. Results indicate that the HW-KDA methodology is able to achieve excellent performance with only a very small set of features and outperforms other two popular kernel face recognition methods, the kernel PCA (KPCA) and generalized discriminant analysis (GDA).