Hidden Markov Models For Face Recognition

The work presented in this paper focuses on the use of Hidden Markov Models for face recognition. A new method based on the extraction of 2D-DCT feature vectors is described, and the recognition results are compared with other face recognition approaches. The method introduced in this paper reduces significantly the computational complexity of previous HMM-based face recognition system, while preserving the same recognition rate. 1. INTRODUCTION Face recognition from still images and video sequences is emerging as an active research area with numerous commercial and law enforcement applications. These applications require robust algorithms for human face recognition under different lighting conditions, facial expressions, and orientations. An excellent survey on face recognition is given in [1]. Previous attempts to develop a face recognition system that has a high recognition rate include the correlation method [2], the eigenface method [3] and the linear discriminant method [4]. Howe..