Date Added: Jan 2012
Face Recognition has always been a challenging issue. Selecting less and proper number of features to represent an image with reduced redundancy and noise affects the performance of pattern recognition system. This paper presents a novel algorithm for feature extraction using the Discrete Cosine Transforms (DCT) and feature selection using Binary Particle Swarm Optimization (BPSO) for the Face Recognition System. Major contribution lies in application of suitable image preprocessing techniques depending upon image acquisition conditions.