[1]邓星,达飞鹏,杨乔生.基于自适应人脸切割的三维人脸识别算法[J].东南大学学报(自然科学版),2016,46(2):260-264.[doi:10.3969/j.issn.1001-0505.2016.02.006]
 Deng Xing,Da Feipeng,Yang Qiaosheng.3D face recognition algorithm based on adaptive face cutting[J].Journal of Southeast University (Natural Science Edition),2016,46(2):260-264.[doi:10.3969/j.issn.1001-0505.2016.02.006]
点击复制

基于自适应人脸切割的三维人脸识别算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
46
期数:
2016年第2期
页码:
260-264
栏目:
计算机科学与工程
出版日期:
2016-03-20

文章信息/Info

Title:
3D face recognition algorithm based on adaptive face cutting
作者:
邓星达飞鹏杨乔生
东南大学自动化学院, 南京210096; 东南大学复杂工程系统测量与控制教育部重点实验室, 南京210096
Author(s):
Deng Xing Da Feipeng Yang Qiaosheng
School of Automation, Southeast University, Nanjing 210096, China
Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education, Southeast University, Nanjing 210096, China
关键词:
三维人脸识别 自动预处理技术 改进的meshSIFT特征 自适应人脸切割 多任务稀疏表示分类
Keywords:
three-dimensional face recognition automatic preprocessing technology improved mesh scale invariant feature transform(meshSIFT) adaptive face cutting multi-task sparse representation classification
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2016.02.006
摘要:
为克服表情变化对人脸识别的影响,提出了一种基于自适应人脸切割的三维人脸识别算法.首先,采用一种自动预处理技术来去除离群点、填补孔洞和归一化姿态,以提高三维人脸数据的质量;其次,通过简化meshSIFT特征的规范化方向并加入形状直径函数描述符,讨论了方向分配和特征描述符的设计问题,改进了meshSIFT特征;最后,通过运用字典构造、压缩与自适应区域切割稀疏分类,提出了一种基于多任务稀疏表示分类最小残差和的自适应人脸切割算法.FRGC v2.0人脸数据库上的实验分析结果表明,所提算法对三维人脸识别具有较高的识别率.
Abstract:
In order to overcome the effects of expression variation on face recognition, a three-dimensional(3D)face recognition algorithm based on adaptive face cutting is proposed. First, an automatic preprocessing technique is used to remove the outliers, fill the holes and normalize the pose to improve the quality of 3D facial data. Secondly, by simplifying the canonical orientation of the mesh scale invariant feature transform(meshSIFT)as well as jointing the shape diameter function(SDF)descriptor, the direction assignment and the feature descriptor are discussed and the meshSIFT is improved. Finally, by using the dictionary calculation, compression and adaptive region cutting sparse classification, an adaptive face cutting algorithm based on the minimum residual sum associated to the multitask sparse representation classification is proposed. The experimental results on the FRGC v2.0 face database indicate that the proposed algorithm has a high recognition rate for 3D face recognition.

参考文献/References:

[1] Patil H, Kothari A, Bhurchandi K. 3-D face recognition: Features, databases, algorithms and challenges[J]. Artificial Intelligence Review, 2015, 44(3): 393-441.
[2] Lü S W, Da F P, Deng X. A 3D face recognition method using region-based extended local binary pattern[C]//IEEE International Conference on Image Processing. Quebec,Canada, 2015: 3635-3639.
[3] Al-Osaimi 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. DOI:10.1007/s11263-008-0174-0.
[4] Bronstein A M, Bronstein M M, Kimmel R. Three-dimensional face recognition[J]. International Journal of Computer Vision, 2005, 64(1): 5-30. DOI:10.1007/s11263-005-1085-y.
[5] Phillips P J, Flynn P J, Scruggs T, et al. Overview of the face recognition grand challenge[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA,USA, 2005: 947-954.
[6] 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. DOI:10.1016/j.cviu.2012.10.002.
[7] Shapira L, Shamir A, Cohen-Or D. Consistent mesh partitioning and skeletonisation using the shape diameter function[J]. The Visual Computer, 2008, 24(4): 249-259. DOI:10.1007/s00371-007-0197-5.
[8] Zhang L, Ding Z, Li H, et al. 3D face recognition based on multiple keypoint descriptors and sparse representation[J]. PLoS One, 2014, 9(6): e100120. DOI:10.1371/journal.pone.0100120.
[9] Liao S, Jain A K, Li S Z. Partial face recognition: Alignment-free approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(5): 1193-1205.DOI:10.1109/TPAMI.2012.191.
[10] Berretti S, Bimbo A D, Pala P. 3D face recognition using isogeodesic stripes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12): 2162-2177. DOI:10.1109/TPAMI.2010.43.
[11] Lei Y, Bennamoun M, El-Sallam A A. A structured template based 3D face recognition approach[C]//Proceedings of the 27th Conference on Image and Vision Computing. Dunedin,New Zealand: ACM, 2012:61-66.

相似文献/References:

[1]邹红艳,达飞鹏,李晓莉.基于面部曲线特征融合的三维人脸识别[J].东南大学学报(自然科学版),2012,42(4):618.[doi:10.3969/j.issn.1001-0505.2012.04.008]
 Zou Hongyan,Da Feipeng,Li Xiaoli.3D face recognition using compositional features from facial curves[J].Journal of Southeast University (Natural Science Edition),2012,42(2):618.[doi:10.3969/j.issn.1001-0505.2012.04.008]
[2]吕士文,达飞鹏,邓星.基于区域改进LBP的三维人脸识别[J].东南大学学报(自然科学版),2015,45(4):678.[doi:10.3969/j.issn.1001-0505.2015.04.012]
 Lü Shiwen,Da Feipeng,Deng Xing.3D face recognition method based on regional enhanced local binary pattern[J].Journal of Southeast University (Natural Science Edition),2015,45(2):678.[doi:10.3969/j.issn.1001-0505.2015.04.012]

备注/Memo

备注/Memo:
收稿日期: 2015-08-05.
作者简介: 邓星(1987—), 女, 博士生; 达飞鹏(联系人), 男, 博士, 教授, 博士生导师, dafp@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(51175081, 51475092, 61405034)、教育部博士点基金资助项目(20130092110027).
引用本文: 邓星,达飞鹏,杨乔生.基于自适应人脸切割的三维人脸识别算法[J].东南大学学报(自然科学版),2016,46(2):260-264. DOI:10.3969/j.issn.1001-0505.2016.02.006.
更新日期/Last Update: 2016-03-20