全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于协作表示残差融合的3维人脸识别

DOI: 10.11834/jig.20150512

Keywords: 协作表示,Gabor特征,Geodesic特征,残差融合,人脸识别,3维人脸深度图,特征选择

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的针对2维人脸难以克服光照、表情、姿态等复杂问题,提出了一种基于协作表示残差融合的新算法.方法协作表示分类算法是将所有类的训练图像一起协作构成字典,通过正则化最小二乘法代替1范数求解稀疏系数,减小了计算的复杂度,由此系数重构测试人脸,根据重构误差最小原则,对测试人脸正确分类.该方法首先在3维人脸深度图上提取Gabor特征和Geodesic特征,然后在协作表示算法的基础上融合两者的残差信息,作为最终差异性度量,最后根据融合残差最小原则,进行人脸识别.结果在不同的训练样本、特征维数条件下,在CIS和Texas2个人脸数据库上,本文算法的识别率可分别达到94.545%和99.286%.与Gabor-CRC算法相比,本文算法的识别率平均高出了10%左右.结论在实时成像系统采集的人脸库和Texas3维人脸库上的实验结果表明,该方法对有无姿态、表情、遮挡等变化问题具有较好的鲁棒性和有效性.

References

[1]  Shi Q F, Eriksson A, Van D H A, et al. Is face recognition really a compressive sensing problem?[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI:IEEE, 2011: 553-560.[DOI: 10.1109/CVPR.2011.5995556]
[2]  Rigamonti R, Brown M A, Lepetit V. Are sparse representations really relevant for image classification?[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providence,RI:IEEE,2011:1545-1552.[DOI:10.1109/CVPR.2011.5995313]
[3]  Zhang L, Yang M, Feng XC. Sparse representation or collaborative representation: which helps face recognition? [C]// Proceedings of IEEE Conference on Computer Vision. Barcelona: IEEE Computer Society Press, 2011: 471-478. [DOI:10.1109/ICCV.2011.6126277]
[4]  Zhu P F, Zuo W M, ZhangL, et al. Image set based collaborative representation for face recognition [C]// IEEE Transactions on Information Forensics and Security.Biometrics Compendium:IEEE, 2014:1120-1132.[DOI: 10.1109/TIFS.2014.2324277]
[5]  Hu Z Q,Xu B,Bai Y. Sparse representation for image recognition based on Gabor feature set and discriminative dictionary learning [J]. Journal of Image and Graphics, 2013, 18(2): 189-194.[胡正平, 徐波, 白洋. Gabor特征集结合判别式字典学习的稀疏表示图像识别[J]. 中国图象图形学报, 2013,18(2): 189-194.] [DOI:10.11834/jig.2013]
[6]  Yang M, Zhang L.Gabor feature based sparse representation for face recognition with Gabor occlusion dictionary[M].Computer Vision-ECCV 2010. Berlin Heidelberg: Springer, 2010: 448-461.
[7]  Zhan S, Zhang Q X, Jiang J G, et al.3D face recognition by kernel collaborative representation based on Gabor feature[J].Acta Photonica Sinica, 2013,42(12): 1448-1453.[詹曙, 张启祥, 蒋建国, 等. 基于 Gabor 特征核协作表达的三维人脸识别[J]. 光子学报, 2013,42(12): 1448-1453.] [DOI:10.3788/gzxb20134212.1448]
[8]  Liu Z H,Yin J, Jin Z. An adaptive feature and weight selection method based on Gabor image for face recognition [J]. ActaPhotonica Sinica, 2011, 40(4): 636-641.[刘中华,殷俊,金忠.一种自适应的Gabor图像特征抽取和权重选择的人脸识别方法[J].光子学报,2011,40(4):636-641.] [DOI:10.3788/gzxb20114004.0636]
[9]  Bronstein A M, Bronstein M M,Kimmel R. Three-dimensional face recognition[J]. International Journal of Computer Vision, 2005, 64(1): 5-30.
[10]  Bronstein A M, Bronstein M M,Kimmel R. Expression-invariant representations of faces[J]. IEEE Transactions on Image Processing, 2007, 16(1): 188-197. [DOI: 10.1109/TIP.2006.884940]
[11]  Drira H, Ben A 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. [DOI: 10.1109/TPAMI.2013.48]
[12]  更多...
[13]  Chi Y J, Porikli F. Classification and boosting with multiple collaborative representations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(8):1519-1531. [DOI: 10.1109/TPAMI.2013.236]
[14]  Yang M, Zhang L,Jian Y, et al. Regularized robust coding for face recognition[J]. IEEE Transactions on Image Processing, 2013, 22(5): 1753-1766. [DOI:10.1109/TIP.2012.2235849]
[15]  Johnson D B. A note on Dijkstra\'s shortest path algorithm[J]. Journal of the ACM, 1973, 20(3): 385-388.
[16]  Sethian J A. A fast marching level set method for monotonically advancing fronts[J]. Proceedings of the National Academy of Sciences, 1996, 93(4): 1591-1595.
[17]  KuriharaT, Ono N, Ando S. Surface orientation imager using three-phase amplitude-modulated illumination and correlation image sensor[C]// Electronic Imaging 2003. Minnesota, USA: International Society for Optics and Photonics. 2003: 95-102.
[18]  Gupta S, Castleman K R, Markey M K, et al. Texas 3D face recognition database [C]// IEEE Southwest Symposium on Image Analysis & Interpretation. Austin, TX, USA: IEEE,2010:97-100. [DOI:10.1109/SSIAI.2010.5483908]
[19]  Turk M, Pentland A. Eigenfaces for recognition[J]. Journal of Cognitive Neuroscience,1991,3(1):71-86.[DOI:10.1162/jocn.1991.3.1.7]
[20]  Belhumeu P N, Hespanha J P, Kriegman D. Eigenfaces vs. fisherfaces: recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7): 711-720.[DOI:10.1109/34.598228]
[21]  Sam T, RoweisSaul L K. Nonlinear dimensionality reduction by locally linear embedding[J].Science, 2000, 290(5500): 2323-2326.[DOI: 10.1126/science.290.5500.2323]
[22]  Scholkopf B, Smola A, Muller K. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998, 10 (5): 1299-1319. [DOI:10.1162/089976698300017467]
[23]  Hintong E,Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507. [DOI: 10.1126/science.1127647]
[24]  Zheng Y, Chen Q Q, Zhang Y J.Deep learning and its new progress in object and behavior recognition[J]. Journal of Image and Graphics, 2014,19(2): 175-184.[郑胤,陈权崎,章毓晋. 深度学习及其在目标和行为识别中的新进展[J]. 中国图象图形学报,2014,19(2): 175-184.] [DOI:10. 11834 / jig. 20140202]
[25]  Sun Y,Wang X G, Tang X O. Deep Learning Face Representation from Predicting 10,000 Classes[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Columbus, OH: IEEE, 2014:1891 - 1898. [DOI: 10.1109/CVPR.2014.244]
[26]  Sun Y, Wang X G, Tang X O. Deep convolutional network cascade for facial point detection[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR:IEEE, 2013:3476 - 3483. [DOI:10.1109/CVPR.2013.446]
[27]  Wright J, YangA Y, Ganesh A, et al. Robust face recognition via sparse representation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.[DOI: 10.1109/TPAMI.2008.79]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133