Abstract:This paper presents face recognition using maximum a posteriori (MAP) discriminant on YCbCr color space. The YCbCr color space is considered in order to cover the skin information of face image on the recognition process. The proposed method is employed to improve the recognition rate and equal error rate (EER) of the gray scale based face recognition. In this case, the face features vector consisting of small part of dominant frequency elements which is extracted by non-blocking DCT is implemented as dimensional reduction of the raw face images. The matching process between the query face features and the trained face features is performed using maximum a posteriori (MAP) discriminant. From the experimental results on data from four face databases containing 2268 images with 196 classes show that the face recognition YCbCr color space provide better recognition rate and lesser EER than those of gray scale based face recognition which improve the first rank of grayscale based method result by about 4%. However, it requires three times more computation time than that of grayscale based method.
Abstract:This paper presents a multi-pose face recognition approach using hybrid face features descriptors (HFFD). The HFFD is a face descriptor containing of rich discriminant information that is created by fusing some frequency-based features extracted using both wavelet and DCT analysis of several different poses of 2D face images. The main aim of this method is to represent the multi-pose face images using a dominant frequency component with still having reasonable achievement compared to the recent multi-pose face recognition methods. The HFFD based face recognition tends to achieve better performance than that of the recent 2D-based face recognition method. In addition, the HFFD-based face recognition also is sufficiently to handle large face variability due to face pose variations .