Face Recognition Algorithm Using Two Dimensional Locality Preserving Projection in Discrete Wavelet Domain

Abstract

This paper proposes a new method for face recognition using Two Dimensional Locality Preserving Projection (2DLPP) in Discrete Wavelet Domain (DWT). Firstly, the dimensionality of the original face image is reduced by using the discrete wavelets transform and low frequency channel (LL) is selected to be as the features of face image. And then 2DLPP is applied to decrease the dimension of LL. Finally, the nearest neighbour classifier is used for face classification. The experiment results on ORL face database demonstrate the effectiveness of the proposed method.