传统人脸识别算法通常把光照处理和姿态校正作为两个相对独立的处理过程,难以取得全局最优识别性能.针对该问题,本文根据人脸的非刚体特性,将仿射变换和分块思想融入线性重构模型中,提出了一种基于仿射最小线性重构误差(Affine Minimum Linear Reconstruction Error,AMLRE)的人脸识别算法,在处理光照问题的同时能够补偿姿态变化造成的局部区域对齐误差,以获得更好的全局识别性能.在公共数据集上的实验结果表明,本文提出的算法对光照和姿态有很好的鲁棒性,同时与现有的人脸识别算法相比,本文的算法具有更高的识别率.
Abstract
Traditional face recognition algorithms usually handle variations in illumination and pose independently.Therefore,it is difficult to obtain the global optimal recognition performance.To this end,we propose an affine minimum linear reconstruction error (AMLRE) algorithm based on the non-rigid characteristics of human faces in this paper,which combines an affine transformation model and the idea of patch with a linear reconstruction model. Our algorithm simultaneously handles illumination variations as well as compensates the local area alignment errors caused by pose variations,which achieves much better recognition performance.Comprehensive experiments on several public face datasets clearly demonstrate that our proposed algorithm is robust to both illumination and pose,and thus outperforms most state-of-the-art methods.
关键词
人脸识别 /
线性重构 /
仿射变换 /
Lucas-Kanade算法
{{custom_keyword}} /
Key words
face recognition /
linear reconstruction /
affine transformation /
lucas-kanade algorithm
{{custom_keyword}} /
中图分类号:
TP391
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Z Zhou,A Ganesh,J Wright,et al.Nearest subspace patch matching for face recognition under varying pose and illumination [A].Proceedings of the 8th IEEE International Conference on Automatic Face Gesture Recognition [C].Amsterdam,the Netherlands,2008.1-8.
[2] S Baker,I Matthews.Lucas-kanade 20 years on:A unifying framework [J].International Journal of Computer Vision,2004,56(3):221-255.
[3] W Zhao,R Chellappa,et al.Face recognition:A literature survey [J].ACM Computing Surveys,2003,35:399-458.
[4] X Zou,J Kittler,K Messer.Illumination invariant face recognition:A survey [A].Proceedings of IEEE Conference on Biometrics:Theory,Applications and Systems [C].USA:IEEE Press,2007.1-8.
[5] R Basri,D Jacobs.Lambertian reflectance and linear subspaces [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(2):218-233.
[6] A Georghiades,P Belhumeur,D Kriegman.From few to many:Illumination cone models for face recognition under variable lighting and pose [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):643-660.
[7] V Blanz,T Vetter.Face recognition based on fitting a 3D morphable model [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(9):1063-1073.
[8] R Gross,I Mattews,S Baker.Appearance based face recognition and light-fields [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(4):449-465.
[9] R Gross,I Matthews,S Baker.Eigen light-fields and face recognition across pose [A].Proceedings of IEEE International Conference on Automatic Face Gesture Recognition [C].Washington DC,2002.3-9.
[10] John Wright,Allen Yang,et al.Robust face recognition via sparse representation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[11] D J Beymer.Face recognition under varying pose [A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C].USA:IEEE,1994.756-761.
[12] J Luo,Y Ma,E Takikawa,et al.Person-specific SIFT features for face recognition [A].Proceedings of International Conference on Acoustics,Speech,and Signal Processing (ICASSP) [CX].USA:IEEE,2007.593-596.
[13] P J Phillips,et al.The FERET evaluation methodology for face recognition algorithms [J].IEEE Transactions on PAMI,2000,22(10):1090-1104.
[14] F Perronin,J Dugelay,K Rose.A probabilistic model of face mapping with local transformations and its application to person recognition [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(7):1157-1171.
[15] X Zhang,Y Gao.Face recognition across pose:a review [J].Pattern Recognition,2009,42(11):2876-2896.
[16] 王海涛,等.自商图像[J].计算机工程,2005,31(18):178-179,215. Wang Hai-tao,et al.Self-quotient image [J].Computer Engineering,2005,31(18):178-179,215.(in Chinese)
[17] 庄连生,龙飞,等.基于全变分模型的光照处理算法[J].电路与系统学报,2008,13(5):103-107. Zhuang Lian-sheng,Long Fei,et al.An illumination processing algorithm based on total variation model [J].Journal of Circuits and Systems,2008,13(5):103-107.(in Chinese)
[18] A Bronstein,M Bronstein,R Kimmel,et al.3D face recognition without facial surface reconstruction [A].Proceedings of European Conference on Computer Vision (ECCV) [C].Prague,Czech Republic,2004.11-14.
[19] 陈北京,等.一种融合二值边缘特征和灰度特征的人脸识别方法[J].电子学报,2009,37(6):1180-1184. Chen Bei-jing,et al.A novel face recognition method based on the fusion of binary edge and grayscale features [J].Acta Electronica Sinica,2009,37(6):1180-1184.(in Chinese)
[20] 谢晓华,等.基于二次多项式模型的人脸光照归一化[J].电子学报,2010,38(8):1791-1797. Xie Xiao-hua,et al.Illumination normalization of human face based on the second-order polynomial model [J].Acta Electronica Sinica,2010,38(8):1791-1797.(in Chinese)
[21] T Sim,S Baker,M Bsat.The CMU pose,illumination and expression database [J].PAMI,2003,25(12):1615-1618.
[22] 周杰,卢春雨,张长水,等.人脸自动识别方法综述[J].电子学报,2000,28(4):102-106. Zhou Jie,Lu Chun-yu,Zhang Chang-shui,et al.A survey of automatic human face recognition [J].Acta Electronica Sinica,2000,28(4):102-106.(in Chinese)
[23] X Chai,S Shan,X Chen,W Gao.Locally linear regression for pose-invariant face recognition [J].IEEE Transactions on Image Processing,2007,16(7):1716-1725.
[24] S J D Prince,J Warrell,J H Elder,et al.Tied factor analysis for face recognition across large pose differences [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(6):970-984.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金 (No.61103134,No.60933013); "新一代宽带无线移动通信网"国家科技重大专项 (No.2010ZX03004-003); 中央高校基本科研业务经费专项资金 (No.WK210023002,No.WK2101020003); 安徽省优秀青年人才基金 (No.BJ2101020001)
{{custom_fund}}