Recursive Binary Particle Swarm Optimization based Face Localization

Face Localization on frontal pose grayscale images under varying conditions of illumination, background and gender is challenging. Developing a robust technique to handle all the aforementioned variations requires a lot of training time and hardware to obtain a good localization rate. In this paper, a novel Recursive Binary Particle Swarm Optimization is proposed, to create a generic template of the face. This template is then used for template matching in the Block DCT Signal Space to obtain the position of the face in the test image. Experimental results, obtained by applying the proposed algorithm on CalTech, FERET and Extended Yale B face databases, show that the proposed system provides good localization rates with a low training time.