A Novel One-Parameter Regularized Kernel Fisher Discriminant Method for Face Recognition

Wensheng Chen, Pong Chi Yuen, Jian Huang, Daoqing Dai

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review


Kernel-based regularization discriminant analysis (KRDA) is one of the promising approaches for solving small sample size problem in face recognition. This paper addresses the problem in regularization parameter reduction in KRDA. From computational complexity point of view, our goal is to develop a KRDA algorithm with minimum number of parameters, in which regularization process can be fully controlled. Along this line, we have developed a Kernel 1-parameter RDA (K1PRDA) algorithm (W. S. Chen, P C Yuen, J Huang and D. Q. Dai, "Kernel machine-based one-parameter regularized Fisher discriminant method for face recognition," IEEE Transactions on SMC-B, to appear, 2005.). K1PRDA was developed based on a three-parameter regularization formula. In this paper, we propose another approach to formulate the one-parameter KRDA (1PRKFD) based on a two-parameter formula. Yale B database, with pose and illumination variations, is used to compare the performance of 1PRKFD algorithm, K1PRDA algorithm and other LDA-based algorithms. Experimental results show that both 1PRKFD and K1PRDA algorithms outperform the other LDA-based face recognition algorithms. The performance between 1PRKFD and K1PRDA algorithms are comparable. This concludes that our methodology in deriving the one-parameter KRDA is stable.

Original languageEnglish
Title of host publicationPattern Recognition and Image Analysis
Subtitle of host publicationSecond Iberian Conference, IbPRIA 2005, Estoril, Portugal, June 7-9, 2005, Proceeding, Part II
EditorsJorge S. Marques, Nicolás Pérez de la Blanca, Pedro Pina
Place of PublicationBerlin, Heidelberg
Number of pages8
ISBN (Electronic)9783540322382
ISBN (Print)9783540261544
Publication statusPublished - 13 May 2005
EventSecond Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005 - Estoril, Portugal
Duration: 7 Jun 20059 Jun 2005

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameImage Processing, Computer Vision, Pattern Recognition, and Graphics
NameIbPRIA: Iberian Conference on Pattern Recognition and Image Analysis


ConferenceSecond Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005
Internet address

Scopus Subject Areas

  • Theoretical Computer Science
  • Computer Science(all)

User-Defined Keywords

  • Face Recognition
  • Conjugate Gradient Method
  • Illumination Variation
  • Rank1 Accuracy
  • Small Sample Size Problem


Dive into the research topics of 'A Novel One-Parameter Regularized Kernel Fisher Discriminant Method for Face Recognition'. Together they form a unique fingerprint.

Cite this