Background removal using k-means clustering as a preprocessing technique for DWT based Face Recognition

Face Recognition (FR) under varying background conditions is challenging, and exacting background invariant features is an effective approach to solve this problem. In this paper, we propose a novel method for background removal based on the k-means clustering algorithm, which lays the ground for DWT-based feature extraction to enhance the performance of a FR system. Individual stages of the FR system are examined and an attempt is made to improve each stage. A Binary Particle Swarm Optimization (BPSO)-based feature selection algorithm is used to search the feature vector space for the optimal feature subset. Experimental results, obtained by applying the proposed algorithm on ORL, UMIST, Extended Yale B and ColorFERET databases, show that the proposed system outperforms other FR systems. A significant increase in the overall recognition rate and a substantial reduction in the number of features are observed.