In this article, a high performance face recognition system based on local binary pattern (LBP) using the probability\r\ndistribution functions (PDFs) of pixels in different mutually independent color channels which are robust to frontal\r\nhomogenous illumination and planer rotation is proposed. The illumination of faces is enhanced by using the stateof-\r\nthe-art technique which is using discrete wavelet transform and singular value decomposition. After equalization,\r\nface images are segmented by using local successive mean quantization transform followed by skin color-based\r\nface detection system. Kullbackââ?¬â??Leibler distance between the concatenated PDFs of a given face obtained by LBP\r\nand the concatenated PDFs of each face in the database is used as a metric in the recognition process. Various\r\ndecision fusion techniques have been used in order to improve the recognition rate. The proposed system has\r\nbeen tested on the FERET, HP, and Bosphorus face databases. The proposed system is compared with conventional\r\nand the state-of-the-art techniques. The recognition rates obtained using FVF approach for FERET database is\r\n99.78% compared with 79.60 and 68.80% for conventional gray-scale LBP and principle component analysis-based\r\nface recognition techniques, respectively.
Loading....