Face Recognition with Multi-feature Joint Representation

Different methods have been proposed over the last few years to improve the recognition rate for face images. In this paper, the merits of multi-feature joint representation based for face recognition is studied. The whole approach of face recognition can be separated into two phases: training phase and recognition phase. At first, given a query image, we train the recognition system by using the gabor and gradient features together to represent the face images. In the second phase, modular LRC classification will be used to classify the face images rather than an NN classification. Unlike the traditional LRC algorithm which operates directly on the whole face image patterns, the modular method operates on sub-blocks partitioned from an original whole face image. Experiments are carried on two face databases, the results show that the combination of the gabor information and the gradient information by modular LRC are better than the method using the single information.