Face recognition with DWT and Two-dimensional Principal Component Analysis

In this paper, we propose a method for recognizing face images by combining wavelet decomposition and two-dimensional principal component analysis (2DPCA). The first stage uses the wavelet decomposition that extracts intrinsic features of face images. In wavelet multi-resolution decomposition of images, an image is split into approximation and details in horizontal, vertical, and diagonal directions. The second stage of the method concerns the application of the 2DPCA method to the approximation image. The discriminative features in the corner are use to classify the face image. The experiment results show that the proposed method is more effective than several representative wavelet.