论文:2014,Vol:32,Issue(3):382-387
引用本文:
郭哲, 樊养余, 雷涛, 刘姝. 基于联合稀疏描述的多姿态三维人脸识别[J]. 西北工业大学
Guo Zhe, Fan Yangyu, Lei Tao, Liu Shu. Multi-Pose 3D Face Recognition Based on Joint Sparse Representation[J]. Northwestern polytechnical university

基于联合稀疏描述的多姿态三维人脸识别
郭哲, 樊养余, 雷涛, 刘姝
西北工业大学 电子信息学院, 陕西 西安 710072
摘要:
提出一种基于联合稀疏描述的多姿态三维人脸识别算法。该算法基于多幅不同姿态的三维人脸测试样本联合完成身份识别,通过假设多幅测试样本共享同一稀疏类型,联合多视图信息,构建三维空间字典和稀疏描述模型,用于对稀疏描述向量进行联合重建。该方法最显著的特点就是利用所有观测视图的相互关系,避免单独对待每一个观测值时所潜在的错误判别风险,从而提高识别准确率。在国际三维人脸数据库FRGC2.0上的实验证明该算法对多姿态三维人脸的识别性能优于相互子空间算法和稀疏表示识别算法。
关键词:    人脸识别    图像分类    联合稀疏描述    多姿态    三维人脸识别   
Multi-Pose 3D Face Recognition Based on Joint Sparse Representation
Guo Zhe, Fan Yangyu, Lei Tao, Liu Shu
Department of Electronics Engineering, Northwestern Polytechnical University, Xi'an 710072, China
Abstract:
A multi-pose 3D face recognition method based on joint sparse representation, called Joint Sparse Repre-sentation-based Classification (JSRC), is proposed in this paper. Multi-view 3D face test data are jointed for identi-ty recognition by the hypothesis of multi test data joining the same sparse pattern. Consequently, we, using the JS-RC method, construct 3D overcomplete dictionary and sparse representation model, thus completing the joint recon-struction of the sparse representation vector. The most notable advantage of the JSRC method is:utilizing the corre-lation of multi-view face, reducing the error identification risk of the traditional methods which consider only one test face each time, and improving the recognition accuracy. Experimental results on FRGC2?0 database and their analysis show preliminarily that JSRC method has higher performance in multi-pose 3D face recognition as compared with those obtainable respectively with mutual subspace method and sparse representation-based classification meth-od.
Key words:    face recognition    image classification    joint sparse representation    multi-pose    three dimensional face recognition   
收稿日期: 2013-10-10     修回日期:
DOI:
基金项目: 国家自然科学基金(61202314);陕西省自然科学基础研究计划(2013JQ8039);中央高校基本科研业务费专项资金(3102014JCQ01060);中国博士后科学基金(2012M521801)资助
通讯作者:     Email:
作者简介: 郭哲(1984-),西北工业大学讲师,主要从事模式识别及虚拟现实研究。
相关功能
PDF(379KB) Free
打印本文
把本文推荐给朋友
作者相关文章
郭哲  在本刊中的所有文章
樊养余  在本刊中的所有文章
雷涛  在本刊中的所有文章
刘姝  在本刊中的所有文章

参考文献:
[1] Bowyer K W, Chang K, Flynn P. A Survey of Approaches and Challenges in 3D and Multi-Modal 3D + 2D Face Recognition [J]. Computer Vision and Image Understanding, 2006, 101 (1): 1-15
[2] Farhat M, Alfalou A, Hamam H, Brosseau C. Double Fusion Filtering Based Multi-View Face Recognition[J]. Optics Communications, 2009, 282 (11): 2136-2142
[3] Kokiopoulou E, Frossard P. Graph-Based Classification of Multiple Observation Sets[J]. Pattern Recognition, 2010, 43 (12):3988-3997
[4] Cevikalp H, Triggs B. Face Recognition Based on Image Sets[C]//Proceedings of Computer Vision Pattern Recognition, 2010,2567-2573
[5] Fukui K, Yamaguchi O. Face Recognition Using Multi-Viewpoint Patterns for Robot Vision[J]. Springer Tracts in Advanced Robotics, 2005, 15: 192-201
[6] Hamm J, Lee D D. Grassmann Discriminant Analysis: A Unifying View on Subspace-Based Learning[C]//Proceedings of ICML, 2008, 376-383
[7] Wright J, Yang A Y, Ganesh A, et al. Robust Face Recognition via Sparse Representation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2009, 31 (2): 210-227
[8] Li X, Jia T, Zhang H. Expression Insensitive 3D Face Recognition Using Sparse Representation[C]//Proceedings of Computer Vision Pattern Recognition, 2009: 2575-2582
[9] Guo Z, Zhang Y, Xia Y, et al. Multi-Pose 3D Face Recognition Based on 2D Sparse Representation[J]. Journal of Visual Communication and Image Representation, 2013, 24(2): 117-126
[10] Tang H, Sun Y, Yin B, et al. 3D Face Recognition Based on Sparse Representation[J]. The Journal of Supercomputing, 2011,58(1): 84-95
[11] Rakotomamonjy A. Surveying and Comparing Simultaneous Sparse Approximation (or Group Lasso) Algorithms[R]. Technical Report, 2010
[12] Tropp J A, Gilbert A C, Strauss M J. Algorithms for Simultaneous Sparse Approximation[J]. Eurasip Journal on Applied Signal Processing, 2006, 86: 572-588
[13] Phillips P, Flynn P, Scruggs T, et al. Overview of the Face Recognition Grand Challenge[C]//Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 2005, 947-954