Real Time Face Recognition Based on Face Descriptor and Its Application

Abstract

This paper presents a real time face recognition based on face descriptor and its application for door locking. The face descriptor is represented by both local and global information. The local information, which is the dominant frequency content of sub-face, is extracted by zoned discrete cosine transforms (DCT). While the global information, which also is the dominant frequency content and shape information of the whole face, is extracted by DCT and by Hu-moment. Therefore, face descriptor has rich information about a face image which tends to provide good performance for real time face recognition. To decrease the dimensional size of face descriptor, the predictive linear discriminant analysis (PDLDA) is employed and the face classification is done by kNN. The experimental results show that the proposed real time face recognition provides good performances which indicated by 98.30%, 21.99%, and 1.8% of accuracy, FPR, and FNR respectively. In addition, it also needs short computational time (1 second).