A new method for human face recognition using texture and depth information

The efficiency of a human face recognition system depends on the capability of face recognition in presence of different changes in the appearance of face. One of the main difficulties regarding the face recognition systems is to recognize face in different views and poses. In this paper we propose a new algorithm which utilizes the combination of texture and depth information to overcome the problem of pose variation and illumination change for face recognition. In the proposed algorithm, we first use intensity image to extract efficient key features and find probable face matches in the face database using feature matching algorithm. We have defined some criteria to find the final match based on texture information or leave the decision to second stage. In the second stage the depth information are normalized and used for pose invariant face recognition. We tested the proposed algorithm using a face database with different poses and illumination and compared the results with those of other methods. We obtained the recognition rate of 88.96 percent which shows the considerable enhancement compared to previous methods.