Loading...

Fuzzy regularized linear discriminant analysis for face recognition

Aghaei Taghlidabad, M ; Sharif University of Technology

907 Viewed
  1. Type of Document: Article
  2. DOI: 10.1117/12.920913
  3. Abstract:
  4. A new face recognition method is proposed in this paper. The proposed method is based on fuzzy regularized linear discriminant analysis (FR-LDA) and combines the regularized linear discriminant analysis (R-LDA) and the fuzzy set theory. R-LDA is based on a new regularized Fisher's discriminant criterion, which is particularly robust against the small sample size problem compared to the traditional one used in LDA. In the proposed method, we calculate the membership degree matrix by Fuzzy K-nearest neighbor (FKNN) and then incorporate the membership degree into the definition of the between-class and within-class scatter matrices and get the fuzzy between-class and within-class scatter matrices. Experimental results obtained on the FERET database demonstrate that the proposed method improves the classification rate performance
  5. Keywords:
  6. Face recognition ; Fuzzy regularized linear Discriminant analysis (FR-LDA) ; Regularized linear Discriminant analysis (R-LDA) ; Classification rates ; Face recognition methods ; FERET database ; Fisher's discriminant ; K-nearest neighbors ; Linear discriminant analysis ; Matrix ; Membership degrees ; Scatter matrix ; Small sample size problems ; Computer vision ; Fuzzy set theory ; Membership functions
  7. Source: Proceedings of SPIE - The International Society for Optical Engineering, 9 December 2011 through 10 December 2011 ; Volume 8349 , December , 2012 ; 0277786X (ISSN) ; 9780819490254 (ISBN)
  8. URL: http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1233098