A Novel Method for Color Face Recognition

Abstract

A two-phase test sample sparse representation method (TPTSR) attracted wide attentions for its good performance after it had been proposed. This good method just exploited gray images for face recognition rather than color face recognition. In this paper, we extend TPTSR for color face recognition. We first exploit the first, second and third channels of each color image to produce recognition scores and then use a fusion scheme to obtain the ultimate fusion score for face recognition. Finally we use the fusion score to classify test samples. Our experiments compare our method with the original TPTSR, PCA, LDA, LPCA, KLDA on AR color face database. Our experiment results demonstrate that our method take a good performance on color face recognition.