Color Local Texture Features Based Face Recognition

For the purpose of face recognition (FR), the new color local texture features, i.e., color local Gabor wavelets (CLGWs) and color local binary pattern (CLBP), are being proposed. The proposed color local texture features are able to exploit the discriminative information derived from spatiochromatic texture patterns of different spectral channels within a certain local face region. This method encodes the discriminative features by combining both color and texture information as well as its fusion approach. To make full use of both color and texture information, the opponent color texture features are used. The opponent features capture the spatial correlation between spectral bands and taken into the generation of CLGW and CLBP. In addition, to perform the final classification, multiple color local texture features (each corresponding to the associated color band) are combined within a feature-level fusion framework. Particularly, compared with gray scale texture features, the proposed color local texture features are able to provide excellent recognition rates for face images taken under severe variation in illumination, as well as some variations in face images.