Boosting Color Feature Selection for Color Face Recognition

Abstract

This paper introduces the new color face recognition (FR) method that makes effective use of boosting \nlearning as color-component feature selection framework. The proposed boosting color-component \nfeature selection framework is designed for finding the best set of color-component features from various \ncolor spaces (or models), aiming to achieve the best FR performance for a given FR task. In addition, to \nfacilitate the complementary effect of the selected color-component features for the purpose of color FR, \nthey are combined using the proposed weighted feature fusion scheme. The effectiveness of our color FR \nmethod has been successfully evaluated on the following five public face databases (DBs): CMU-PIE, \nColor FERET, XM2VTSDB, SCface, and FRGC 2.0. Experimental results show that the results of the \nproposed method are impressively better than the results of other state-of-the-art color FR methods over \ndifferent FR challenges including highly uncontrolled illumination, moderate pose variation, and small \nresolution face images.