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

Jian Yang, Xiumei Gao, Dapeng Zhang, Jing Yu Yang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

102 Citations (Scopus)

Abstract

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, PCA and KPCA in terms of the total recognition rate.
Original languageEnglish
Pages (from-to)1784-1787
Number of pages4
JournalPattern Recognition
Volume38
Issue number10
DOIs
Publication statusPublished - 1 Oct 2005

Keywords

  • Face recognition
  • Feature extraction
  • Independent component analysis (ICA)
  • Kernel-based methods
  • Principal component analysis (PCA)

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this