Linear Discriminant Analysis LDA and logic fusion of Color decisions to face authentication

Abstract

In this paper , we investigate the use of color information to face authentication in order to improve the performance of this system, Many color components have been used. The results in different colorimetric components are combined by using a logic fusion for classification with different operators like: and, or, 2 and. We have applied the method of linear discriminant analysis: LDA for the extraction of feature vectors. The proposed feature set is tested on benchmark database, namely XM2VTS according to its associated Protocol (Protocol of Lausanne).