A novel 3D face recognition approach based on singular point neighborhood structure is proposed in this paper. Firstly, by detecting feature sub-region in face texture image, two dimensional singular points and singular point neighborhood structure are extracted. Then three dimensional singular points and its neighborhood structure as facial features are marked in face vertex image. Finally, recognition results are obtained by using the method of nearest point of singular point neighborhood structure. Experiment results show that the proposed approach achieves good recognition results with higher recognition accuracy and good robustness.