DocumentCode
2074256
Title
Comparison of Feature Space Methods for Face Recognition
Author
Xie, Chunyan ; Savvides, Marios ; Kumar, B. V K Vijaya
Author_Institution
Carnegie Mellon University, USA
fYear
2006
fDate
17-22 June 2006
Firstpage
46
Lastpage
46
Abstract
Many feature space methods have been investigated for appearance-based face recognition. In this paper we compare a new feature space face recognition method - the class-dependence feature analysis (CFA) with three other popular methods, namely, the principal component analysis (PCA), the linear discriminant analysis (LDA) and the independent component analysis (ICA), for appearance-based 2-D face recognition. The numerical results on the face recognition grand challenge (FRGC) show that the CFA outperforms the other three method
Keywords
Euclidean distance; Face recognition; Feature extraction; Filters; Frequency domain analysis; Independent component analysis; Linear discriminant analysis; Principal component analysis; Probes; Spatial databases;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Conference on
Print_ISBN
0-7695-2646-2
Type
conf
DOI
10.1109/CVPRW.2006.58
Filename
1640486
Link To Document