Computer Technology, Electronic Communications Technologies |
|
|
|
|
3D face recognition based on keypoints and local feature |
GUO Meng-li, DA Fei-peng, DENG Xing, GAI Shao-yan |
School of Automation, Southeast University, Nanjing 210096, China;
Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing 210096, China |
|
|
Abstract A novel 3D face recognition algorithm based on keypoints and local feature was proposed to reduce the impact of expression variations in 3D face recognition. First, keypoints were detected according to the valuable profile and mean curvature. Then, the spatial structure of the local feature was set as DAISY descriptor. The local feature was obtained by concatenating the histograms of shape indices, slant angles and direction angles. Finally, the match of keypoints was performed; the number of keypoints which were matched properly was used to measure the similarity of two face surfaces. The identification experiments were carried out on the FRGC v2.0 database and the Bosphorus database. As a result, the rank-one recognition rates of the two experiments are 96.9% and 95.8%, respectively. The experimental results demonstrate that the proposed algorithm can achieve higher recognition performance and is robust to expression variations.
|
Published: 01 March 2017
|
|
|
Cite this article:
GUO Meng-li, DA Fei-peng, DENG Xing, GAI Shao-yan. 3D face recognition based on keypoints and local feature. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(3): 584-589.
|
基于关键点和局部特征的三维人脸识别
为了减少表情变化对三维人脸识别的影响,提出一种基于关键点和局部特征的三维人脸识别算法.根据有价值轮廓线和平均曲率检测关键点;根据DAISY描述符的形式构造局部特征的空间结构,采用形状指数直方图、倾斜角直方图和方向角直方图作为局部特征,进行关键点匹配;并利用匹配成功的关键点数目衡量2个人脸曲面的相似度.基于FRGC v2.0数据库和Bosphorus数据库开展身份识别实验,获得了96.9%和95.8%的Rank-1识别率.实验证明所提出的方法识别性能较好,并对表情变化识别具有一定的鲁棒性.
|
|
[1] 王跃明,潘纲,吴朝晖.三维人脸识别研究综述[J].计算机辅助设计与图形学学报,2008, 20(7): 819-829.
WANG Yue-ming, PAN Gang, WU Zhao-hui. Summary of 3D face recognition research [J]. Journal of Computer-Aided Design and Computer Graphics, 2008,20(7): 819-829.
[2] CHEN Y, MEDIONI G. Object modelling by registration of multiple range images [J]. Image and vision computing, 1992, 10(3): 145-155.
[3] MIAN A, BENNAMOUN M, OWENS R. An efficient multimodal 2D-3D hybrid approach to automatic face recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(11): 1927-1943.
[4] WANG Y, LIU J, TANG X. Robust 3D face recognition by local shape difference boosting [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(10): 1858-1870.
[5] SMEETS D, KEUSTERMANS J, VANDERMEULEN D, et al. meshSIFT: Local surface features for 3D face recognition under expression variations and partial data [J]. Computer Vision and Image Understanding, 2013, 117(2): 158-169.
[6] XU C, LI S, TAN T, et al. Automatic 3D face recognition from depth and intensity Gabor features [J]. Pattern Recognition, 2009, 42(9): 1895-1905.
[7] CAI L, DA F. Nonrigid-deformation recovery for 3D face recognition using multiscale registration [J]. Computer Graphics and Applications, IEEE, 2012, 32(3): 37-45.
[8] ALOSAIMI F, BENNAMOUN M, MIAN A. An expression deformation approach to non-rigid 3D face recognition [J]. International Journal of Computer Vision, 2009, 81(3): 302-316.
[9] CHANG K I, BOWYER K W, FLYNN P J. Multiple nose region matching for 3D face recognition under varying facial expression [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(10):1695-1700.
[10] PAN G, WANG Y M, WU Z H. Finding symmetry plane of 3d face shape [C]∥18th International Conference on Pattern Recognition (ICPR). Hong Kong: IEEE, 2006: 1143-1146.
[11] LI X, DA F. Efficient 3D face recognition handling facial expression and hair occlusion [J]. Image and Vision Computing, 2012, 30(9): 668-679.
[12] CHEN H, BHANU B. 3D free-form object recognition in range images using local surface patches [J]. Pattern Recognition Letters, 2007, 28(10): 1252-1262.
[13] TOLA E, LEPETIT V, FUA P. Daisy: An efficient dense descriptor applied to wide-baseline stereo [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 815-830.
[14] LI H, HUANG D, MORVAN J M, et al. Towards 3D face recognition in the real: a registration-free approach using fine-grained matching of 3D keypoint descriptors [J]. International Journal of Computer Vision, 2014, 113(2): 128-142.
[15] MAES C, FABRY T, KEUSTERMANS J, et al. Feature detection on 3D face surfaces for pose normalisation and recognition [C]∥ 2010 Fourth IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS), September 27-29, 2010. Washington DC: IEEE, 2010: 1-6.
[16] RATYAL N I, TAJ I A, BAJWA U I, et al. 3D face recognition based on pose and expression invariant alignment [J]. Computers and Electrical Engineering, 2015, 46: 241-255.
[17] LEI Y J, BENNAMOUN M, EL-SALLAM A A. An efficient 3D face recognition approach based on the fusion of novel local lowlevel features [J]. Pattern Recognition, 2013, 46(1): 24-37.
[18] ZHANG G, WANG Y, Robust 3D face recognition based on resolution invariant features [J]. Pattern Recognition Letters, 2011, 32(7): 1009-1019. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|