基于深度学习的三维点云人脸识别

doi:10.11772/j.issn.1001-9081.2020111826

计算机应用 ›› 2021, Vol. 41 ›› Issue (9): 2736-2740.DOI: 10.11772/j.issn.1001-9081.2020111826

所属专题：多媒体计算与计算机仿真

• 多媒体计算与计算机仿真 • 上一篇下一篇

基于深度学习的三维点云人脸识别

高工¹, 杨红雨^1,2, 刘洪^1,2

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

收稿日期:2020-11-23 修回日期:2021-03-03 出版日期:2021-09-10 发布日期:2021-05-12
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:
四川省重大科技专项（2019ZDZX0039）。

3D point cloud face recognition based on deep learning

GAO Gong¹, YANG Hongyu^1,2, LIU Hong^1,2

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).

摘要/Abstract

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

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

中图分类号:

TP391.4

高工, 杨红雨, 刘洪. 基于深度学习的三维点云人脸识别[J]. 计算机应用, 2021, 41(9): 2736-2740.

GAO Gong, YANG Hongyu, LIU Hong. 3D point cloud face recognition based on deep learning[J]. Journal of Computer Applications, 2021, 41(9): 2736-2740.

参考文献

[1] 刘蓉. 姿态和表情不变的三维人脸识别研究[D]. 杭州:浙江大学,2015:16-23. (LIU R. Research on pose and expression invariant 3D face recognition[D]. Hangzhou:Zhejiang University, 2015:16-23.)
[2] DRIRA H,BEN AMOR B,SRIVASTAVA A,et al. 3D face recognition under expressions,occlusions,and pose variations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(9):2270-2283.
[3] LEI Y J,BENNAMOUN M,HAYAT M,et al. An efficient 3D face recognition approach using local geometrical signatures[J]. Pattern Recognition,2014,47(2):509-524.
[4] RUSS T D,KOCH M W,LITTLE C Q. A 2D range Hausdorff approach for 3D face recognition[C]//Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway:IEEE,2005:169-169.
[5] XU C H,WANG Y H,TAN T N,et al. Automatic 3D face recognition combining global geometric features with local shape variation information[C]//Proceedings of the 6th IEEE International Conference on Automatic Face and Gesture Recognition. Piscataway:IEEE,2004:308-313.
[6] GILANI S Z,MIAN A. Learning from millions of 3D scans for largescale 3D face recognition[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:1896-1905.
[7] JIANG L, ZHANG J Y, DENG B L. Robust RGB-D face recognition using attribute-aware loss[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(10):2552-2566.
[8] 李章燕. 基于局部特征的三维人脸识别算法的研究[D]. 哈尔滨:哈尔滨工业大学,2018:26-31.(LI Z Y. Research on local feature of three dimensional face recognition[D]. Harbin:Harbin Institute of Technology,2018:26-31.)
[9] 贾媛媛. 三维点云与RGB的融合与语义分割方法研究[D]. 北京:北京交通大学,2019:37-41. (JIA Y Y. Research on fusion and semantic segmentation of 3D point cloud and RGB image[D]. Beijing:Beijing Jiaotong University,2019:37-41.)
[10] QI C R,SU H,MO K C,et al. PointNet:deep learning on point sets for 3D classification and segmentation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:652-660.
[11] QI C R,YI L,SU H,et al. PointNet++:deep hierarchical feature learning on point sets in a metric space[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook,NY:Curran Associates Inc.,2017:5105-5114.
[12] LIU Y C, FAN B, XIANG S M, et al. Relation-shape convolutional neural network for point cloud analysis[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:8887-8896.
[13] 谷晓英. 三维重建中点云数据处理关键技术研究[D]. 秦皇岛:燕山大学,2015:14-19. (GU X Y. Research on the key Technologies of point clouds processing in 3D reconstruction[D]. Qinhuangdao:Yanshan University,2015:14-19.)
[14] 袁华, 庞建铿, 莫建文. 基于噪声分类的双边滤波点云去噪算法[J]. 计算机应用,2015,35(8):2305-2310.(YUAN H, PANG J K,MO J W. Denoising algorithm for bilateral filtered point cloud based on noise classification[J]. Journal of Computer Applications,2015,35(8):2305-2310.)
[15] SUN L J,LI W J,NING X,et al. Gradient-enhanced softmax for face recognition[J]. IEICE Transactions on Information and Systems,2020,E103. D (5):1185-1189.
[16] 卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理,2016,31(1):1-17.(LU H T, ZHANG Q C. Applications of deep convolutional neural network in computer vision[J]. Journal of Data Acquisition and Processing, 2016,31(1):1-17.)
[17] XU C H,LI S,TAN T N,et al. Automatic 3D face recognition from depth and intensity Gabor features[J]. Pattern Recognition, 2009,42(9):1895-1905.
[18] SERAFIN J,GRISETTI G. NICP:dense normal based point cloud registration[C]//Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway:IEEE,2015:742-749.
[19] LIU F,ZHAO Q J,LIU X M,et al. Joint face alignment and 3D face reconstruction with application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020, 42(3):664-678.

基于深度学习的三维点云人脸识别

3D point cloud face recognition based on deep learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[2]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.
[3]	赵青, 余元辉. 基于分层特征化网络的三维人脸识别[J]. 计算机应用, 2020, 40(9): 2514-2518.
[4]	方书雅, 刘守印. 基于学生人体检测的无感知课堂考勤方法[J]. 计算机应用, 2020, 40(9): 2519-2524.
[5]	王本杰, 农丽萍, 张文辉, 林基明, 王俊义. 基于Spider卷积的三维点云分类与分割网络[J]. 计算机应用, 2020, 40(6): 1607-1612.
[6]	邢志伟, 乔迪, 刘洪恩, 高志伟, 罗晓, 罗谦. 基于松弛算法的停机位分配优化方法[J]. 计算机应用, 2020, 40(6): 1850-1855.
[7]	李东博, 黄铝文. 重加权稀疏主成分分析算法及其在人脸识别中的应用[J]. 计算机应用, 2020, 40(3): 717-722.
[8]	龚锐, 丁胜, 章超华, 苏浩. 基于深度学习的轻量级和多姿态人脸识别方法[J]. 计算机应用, 2020, 40(3): 704-709.
[9]	陈放, 刘晓瑞, 杨明业. 基于活体检测和身份认证的人脸识别安防系统[J]. 计算机应用, 2020, 40(12): 3666-3672.
[10]	周健, 黄章进. 基于改进三维形变模型的三维人脸重建和密集人脸对齐方法[J]. 计算机应用, 2020, 40(11): 3306-3313.
[11]	任珍文, 吴明娜. 基于熵自加权联合正则化最近点的图像集分类算法[J]. 计算机应用, 2019, 39(9): 2547-2551.
[12]	丁莲静, 刘光帅, 李旭瑞, 陈晓文. 加权信息熵与增强局部二值模式结合的人脸识别[J]. 计算机应用, 2019, 39(8): 2210-2216.
[13]	方国康, 李俊, 王垚儒. 基于深度学习的ARM平台实时人脸识别[J]. 计算机应用, 2019, 39(8): 2217-2222.
[14]	来杰, 王晓丹, 李睿, 赵振冲. 基于去噪自编码器的极限学习机[J]. 计算机应用, 2019, 39(6): 1619-1625.
[15]	桑高丽, 闫超, 朱蓉. 基于多区域融合的表情鲁棒三维人脸识别算法[J]. 计算机应用, 2019, 39(6): 1685-1689.