In order to solve the problem of low recognition accuracy in recognition of 3D face images collected by traditional sensors, a face recognition algorithm for 3D point cloud collected by mixed image sensors is proposed. The algorithm first uses the 3D wheelbase to expand the face image edge. According to the 3D wheelbase, the noise of extended image is detected, and median filtering is used to eliminate the detected noise. Secondly, the priority of the boundary pixels to recognize the face image in the denoising image recognition process is determined, and the key parts such as the illuminance line are analyzed, so that the recognition of the 3D point cloud face image is completed. Experiments show that the proposed algorithm improves the recognition accuracy of 3D face images, which recognition time is lower than that of the traditional algorithm by about 4 times, and the recognition efficiency is high.

1. [1] H. Huang, “3D face point cloud registration and fusion in multi-view of texture consistency,” Software Guide, Vol.14, No.9, pp. 49-51, 2015.
2. [2] H. Tan, Y. Geng, and W. Du, “An efficient face 3D point cloud super-resolution fusion method,” Optical Technology, Vol.42, No.6, pp. 501-505, 2016.
3. [3] S. Yang, X. Lan, and Z. Zhao, “Efficient and robust face recognition based on KINECT sensor for 3D point clouds,” Computer Application and Software, No.3, pp. 177-181, 2015.
4. [4] L. Nie, “An affine package recognition model for face recognition,” Computer Simulation, Vol.33, No.10, pp. 395-398, 2016.
5. [5] H. Wang, T. Wang, and Y. Li, “Using Kinect depth information for studying 3D point cloud registration,” Computer Engineering and Application, Vol.52, No.12, pp. 153-157, 2016.
6. [6] Y. Zhang, Q. Chen, and Y. Luo, “The construction and optimization of 3D point cloud map based on Kinect sensor,” Semiconductor Photoelectricity, Vol.37, No.5, pp. 754-757, 2016.
7. [7] H. Wang, T. Wang, and Y. Li, “Using Kinect depth information for studying 3D point cloud registration,” Computer Engineering and Application, Vol.52, No.12, pp. 153-157, 2016.
8. [8] L. Yue and T. Shen, “3D facial expression recognition based on automatic feature points extraction,” J. of Beijing Institute of Technology, Vol.36, No.5, pp. 508-513, 2016.
9. [9] J. Nie, X. Liu, C. Liu, et al., “The design and implementation of the 3D feature information collection system of the portrait,” New Industrialization, Vol.6, No.10, pp. 61-65, 2016.
10. [10] G. Yang, X. Deng, and C. Liu, “Facial expression recognition model based on deep spatiotemporal convolutional neural networks,” Zhongnan Daxue Xuebao (Ziran Kexue Ban) / J. of Central South University (Science and Technology), Vol.47, No.7, pp. 2311-2319, 2016.
11. [11] G. Yang, W. Tan, H. Jin, et al., “Review wearable sensing system for gait recognition,” Cluster Computing, pp. 1-9, 2018.
12. [12] X. Wang, “3D Face Recognition Based on Regional Shape Maps,” J. Adv. Comput. Intell. Intell. Inform., Vol.22, No.1, pp. 141-146, 2018.