Face recognition based on discriminant waveletfaces

Principal component analysis (PCA) and linear discriminant analysis (LDA) have been widely applied in the face detection and recognition, yet still they have some limitations such as poor discriminative power and large computational load. This paper presents a method for face recognition using discriminant waveletfaces. Firstly wavelet transform is used to decompose the face image into different frequency subbands for extracting feature - waveletfaces, and then the discriminant analysis of PCA plus LDA is performed on the chosen subband. Finally the nearest neighbor classifier is adopted to make decision. In comparison with the traditional discriminant analysis, the experiments show that the proposed approach has better recognition rate and can reduce the computational load.