3D Face Recognition Using Face Feature Points Based on Parallel Stereo Vision

In this paper, we will present a novel face recognition algorithm using 3D geometric information of the face, which is acquired using parallel stereo vision. Firstly, we present an effective method of detecting facial feature, which mainly depends on the facial skin color information in the YCbCr color space. We define the feature points for the facial feature and compute the depth data of each feature point using the stereo vision principle. At the same time, a mesh generation method based on Ohtake’s mesh clearing method is employed to generate the mesh structure of the face. Finally, we use the nD-PCA algorithm to recognize the mesh data. A simulation was carried out to evaluate the efficiency of the proposed approach. A recognition rate of 95% was achieved. The results demonstrated that our proposed algorithm has satisfactory performance.