Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (9): 2736-2740.DOI: 10.11772/j.issn.1001-9081.2020111826

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

3D point cloud face recognition based on deep learning

GAO Gong1, YANG Hongyu1,2, LIU Hong1,2   

  1. 1. National Defense Key Laboratory of Visual Synthesizing Graphics and Image Technology(Sichuan University), Chengdu Sichuan 610064, China;
    2. College of Computer Science, Sichuan University, Chengdu Sichuan 610065, China
  • Received:2020-11-23 Revised:2021-03-03 Online:2021-09-10 Published:2021-05-12
  • Supported by:
    This work is partially supported by the Major Science and Technology Project of Sichuan Province (2019ZDZX0039).


高工1, 杨红雨1,2, 刘洪1,2   

  1. 1. 视觉合成图形图像技术国防重点实验室(四川大学), 成都 610064;
    2. 四川大学 计算机学院, 成都 610065
  • 通讯作者: 刘洪
  • 作者简介:高工(1995-),男,河南周口人,硕士研究生,主要研究方向:计算机视觉、点云识别;杨红雨(1967-),女,四川成都人,教授,博士,主要研究方向:图像处理;刘洪(1978-),男,四川彭州人,副研究员,博士,主要研究方向:智能优化算法、计算机网络、计算机视觉。
  • 基金资助:

Abstract: In order to enhance the robustness of the 3D point cloud face recognition system for multiple expressions and multiple poses, a deep learning-based point cloud feature extraction network was proposed, namely ResPoint. The modules such as grouping, sampling and local feature extraction (ResConv) were used in the ResPoint network, and skip connection was used in ResConv module, so that the proposed network had good recognition results for sparse point cloud. Firstly, the nose tip point was located by the geometric feature points of the face, and the face area was cut with this point as the center. The obtained area had noisy points and holes, so Gaussian filtering and 3D cubic interpolation were performed to it. Secondly, the ResPoint network was used to extract features of the preprocessed point cloud data. Finally, the features were combined in the fully connected layer to realize the classification of 3D faces. In the experiments on CASIA 3D face database, the recognition accuracy of the ResPoint network is increased by 5.06% compared with that of the Relation-Shape Convolutional Neural Network (RS-CNN). Experimental results show that the ResPoint network increases the depth of the network while using different convolution kernels to extract features, so that the ResPoint network has better feature extraction capability.

Key words: face recognition, robustness, Gaussian filtering, point cloud feature, 3D face

摘要: 为了增强三维点云人脸识别系统针对多表情、多姿态的鲁棒性,提出一种基于深度学习的点云特征提取网络ResPoint。ResPoint网络使用了分组、采样和局部特征提取(ResConv)等模块,而在ResConv模块中使用了跳跃式连接,因此所提网络对于稀疏点云有很好的识别结果。首先通过人脸几何特征点定位鼻尖点,并以该点为中心切割出面部区域,切割出的区域有噪点并且有孔洞,因此对其进行高斯滤波和三维立方插值;其次,使用ResPoint网络对预处理后的点云数据提取特征;最后,在全连接层组合特征以实现三维人脸的分类。在CASIA三维人脸数据库上的实验中,与关系型卷积神经网络(RS-CNN)相比,ResPoint网络的识别正确率提高了5.06%。实验结果表明,ResPoint网络增加了网络深度的同时使用不同的卷积核提取特征,因此ResPoint网络有更好的特征提取能力。

关键词: 人脸识别, 鲁棒性, 高斯滤波, 点云特征, 三维人脸

CLC Number: