A Novel Modular PCA Method Based on Phase Congruency Images for Face Recognition

摘要

A novel modular PCA algorithm for face recognition based on phase congruency is presented in this paper. Phase congruency features in an image are defined as the points where the Fourier components of that image are maximally in- phase. These features are invariant to brightness and contrast of the image under consideration. This property allows to achieve the goal of lighting invariant face recognition. Firstly phase congruency maps of the training samples are generated. Then the phase congruency face images are divided into smaller sub-images and the PCA approach is applied to each of these sub-images. Since some of the local facial features of an individual do not vary even when the pose, lighting direction and facial expression vary, we expect the proposed method to be able to cope with these variations. The accuracy of the modular PCA method and the proposed method are evaluated under the conditions of varying expression, illumination and pose using standard face databases. The results indicate high improvement in the classification performance compared to the conventional modular PCA method.