Applications of symmetry average method of local singular value features in face recognition

Face recognition is an active subject in the field of pattern recognition, which has a wide range of potential applications. In this paper, a method of face recognition based on symmetry average of local singular value feature is presented. First, original face image data are linearly mapped in order to eliminate the effects of illumination and noise of image. Second, the local singular values of the face image matrix are extracted and employed as the feature matrix, then the feature matrix is averaged symmetrically. Finally, the nearest neighbor decision (NND) rule is used as recognition rule. Experimental results on ORL (Olivetti Research Laboratory) database show that this method can lessen the number of original features of face images effectively and then get a higher correct recognition rate.