Face recognition using Gabor-Feature-based DFT shifting

The appearance of the face varies drastically when background and pose change. Variations in these conditions make Face Recognition (FR) an even more challenging and difficult task. In this paper we propose two novel techniques, viz., Gabor-Feature-based DFT Shifting (GFDS) and Skin-detection-based Background Removal, to improve the performance of the FR system. GFDS is used to detect and neutralize the image variations like location, scale, pose etc., thereby enhancing Face Recognition. Skin-detection-based Background Removal is used to ascertain the shape of the face and distance from the camera to eliminate complex backgrounds. Experimental results show the promising performance of the proposed techniques for Face Recognition on three benchmark face databases, namely, Color FERET, Pointing Head Pose and CMUPIE databases.