FACE RECOGNITION SYSTEM USING PRINCIPAL COMPONENT ANALYSIS & LINEAR DISCRIMINANT ANALYSIS METHOD SIMULTANEOUSLY WITH 3D MORPHABLE MODEL AND NEURAL NETWORK BPNN METHOD.

Abstract

This paper proposes a face recognition technique that effectively combines principle components analysis (PCA) and Fisherface algorithm (LDA). PCA use as dimension reduction and Fisherface algorithm as a class specific method is robust about variations such as lighting and different angle Condition. We use 3D morphable model to convert 2D image into 3D image & we can derive multiple image by different lighting and can be rotated to generate multiple images in different poses, the PCA method reduces dimensionality& LDA for the classification. Also recognition is done by using back propagation neural network. In comparison with a conventional method the proposed approach could obtain satisfactory results in the perspectives of recognition rates and speeds.