摘要
多姿态人脸识别已成为人脸识别研究的重要方向之一.简要回顾人脸识别研究进展,针对近年来国内外出现的多姿态人脸识别技术和方法进行简单介绍和系统分类,分析各种方法的优缺点,并做出简要评价.阐明多姿态人脸识别技术所面临的挑战,展望未来多姿态人脸识别研究的发展方向.
Multi-pose face recognition has became one of important research directions of face recognition. In this paper,the research progress of face recognition is briefly reviewed. Multi-pose face recognition techniques and methods at home and abroad in recent years are introduced briefly and categorized systematically. The advantages and disadvantages of each method are analyzed,and a brief evaluation is made. The challenges of multi-pose face recognition technology are elucidated,and the development direction of the future research on multi-pose face recognition is discussed.
引文
[1]Galton F.Personal Identification and Description.Nature,1888,38(973):173-177
[2]Galton F.Numeralised Profiles for Classification and Recognition.Nature,1910,83(2109):127-130
[3]Bledsoe W W,Chan H.A Man-Machine Facial Recognition System:Some Preliminary Results.Technical Report,PRI 19A.Palo Alto,USA:Panoramic Research Incorporated,1965
[4]Li C C,Wang Y J,Tu X Y,et al.Artificial Intelligence.Acta Automatica Sinica,1979,5(1):74-87(in Chinese)(李家治,汪云九,涂序彦,等.人工智能国外研究情况综述.自动化学报,1979,5(1):74-87)
[5]Hong Z Q,Yang J Y.Algebraic Feature Extraction of Images for Recognition.Acta Automatica Sinica,1992,18(2):233-238(in Chinese)(洪子泉,杨静宇.用于图象识别的图象代数特征抽取.自动化学报,1992,18(2):233-238)
[6]Zheng J P,You W Y.Recognizing a Typical Human Face from the Front Side.Computer Engineering,1992,18(1):1-6(in Chinese)(郑坚平,尤婉英.标准正面人脸图像的识别.计算机工程,1992,18(1):1-6)
[7]Li W J,Wang C J,Zhang W,et al.A Survey of Face Recognition.Pattern Recognition and Artificial Intelligence,2006,19(1):58-66(in Chinese)(李武军,王崇骏,张炜,等.人脸识别研究综述.模式识别与人工智能,2006,19(1):58-66)
[8]Zhang X Z,Gao Y S.Face Recognition across Pose:A Review.Pattern Recognition,2009,42(11):2876-2896
[9]Tan X Y,Chen S C,Zhou Z H,et al.Face Recognition from a Single Image Per Person:A Survey.Pattern Recognition,2006,39(9):1725-1745
[10]Wang K J,Duan S L,Feng W X.A Survey of Face Recognition Using Single Training Sample.Pattern Recognition and Artificial Intelligence,2008,21(5):635-642(in Chinese)(王科俊,段胜利,冯伟兴.单训练样本人脸识别技术综述.模式识别与人工智能,2008,21(5):635-642)
[11]Zhu C R,Wang R S.Multi-pose Face Recognition Based on a Single View.Chinese Journal of Computers,2003,26(1):104-109(in Chinese)(朱长仁,王润生.基于单视图的多姿态人脸识别算法.计算机学报,2003,26(1):104-109)
[12]Zhang S L.Various Pose Face Recognition with One Front Training Sample.Computer Applications,2006,26(12):2851-2853(in Chinese)(张生亮.单样本多姿态人脸识别研究.计算机应用,2006,26(12):2851-2853)
[13]Zhang Y S,Yang S.Multi-pose Face Recognition Based on Virtual Samples of Local Weighted Mean.Journal of Jiangsu University of Science and Technology:Natural Science Edition,2013,21(1):74-79(in Chinese)(张尤赛,杨姝.局部加权平均虚拟样本的多姿态人脸识别算法.江苏科技大学学报:自然科学版,2013,21(1):74-79)
[14]Wu M,Wang Y,Liu Z J,et al.Multi-pose Face Recognition Based on Orthogonal Views.Journal of Xidian University,2004,31(4):597-601,621(in Chinese)(武芒,王燕,刘志镜,等.基于正投影视图的多姿态人脸识别算法.西安电子科技大学学报:自然科学版,2004,31(4):597-601,621)
[15]Jiang D L,Hu Y X,Yan S C,et al.Efficient 3D Reconstruction for Face Recognition.Pattern Recognition,2005,38(6):787-798
[16]Hu F S,Zhang M J,Zou B J,et al.Pose and Illumination Invariant Face Recognition Based on HMM with One Sample Per Person.Chinese Journal of Computers,2009,32(7):1424-1433(in Chinese)(胡峰松,张茂军,邹北骥,等.基于HMM的单样本可变光照、姿态人脸识别.计算机学报,2009,32(7):1424-1433)
[17]Du C,Su G D,Lin X G,et al.Synthesis of Face Image with Pose Variations.Journal of Optoelectronics·Laser,2004,15(12):1498-1501(in Chinese)(杜成,苏光大,林行刚,等.多姿态人脸图像合成.光电子·激光,2004,15(12):1498-1501)
[18]Sun Z Y,Wu X J,Wang S T,et al.Face Recognition Based on Synthesis of Face Images with Pose Variations.Computer Engineering and Applications,2008,44(23):197-200(in Chinese)(孙志远,吴小俊,王士同,等.基于多姿态人脸图像合成的识别方法研究.计算机工程与应用,2008,44(23):197-200)
[19]Lin Z X,Yang W J,Ho C C,et al.Fast Vertical-Pose-Invariant Face Recognition Module for Intelligent Robot Guard//Proc of the4th International Conference on Autonomous Robots and Agents.Wellington,New Zealand,2009:613-617
[20]Wang K J,Zou G F,Fu G X,et al.An Approach of Fast Eye Location and Face Plane Rotation Correction.Journal of ComputerAided Design&Computer Graphics,2013,25(6):865-872,879(in Chinese)(王科俊,邹国锋,傅桂霞,等.一种快速眼睛定位与人脸平面旋转校正方法.计算机辅助设计与图形学学报,2013,25(6):865-872,879)
[21]Gonzalez-Jimenez D,Alba-Castro J L.Toward Pose-Invariant 2-D Face Recognition through Point Distribution Models and Facial Symmetry.IEEE Trans on Information Forensics and Security,2007,2(3):413-429
[22]Chai X J,Shan S G,Chen X L,et al.Local Linear Regression(LLR)for Pose Invariant Face Recognition//Proc of the 7th International Conference on Automatic Face and Gesture Recognition.Southampton,UK,2006:631-636
[23]Tan X H,Zhang J H.Multi-pose Face Recognition Based on LLR Algorithm.Application Research of Computers,2011,28(1):392-394(in Chinese)(谭晓衡,张建慧.基于LLR算法的多姿态人脸识别.计算机应用研究,2011,28(1):392-394)
[24]Chen H J,Wei W.Multi-pose Face Recognition Based on Correlative Sub-region Mapping.Journal of Image and Graphics,2007,12(7):1254-1260(in Chinese)(陈华杰,韦巍.基于关联子区域映射的多姿态人脸识别.中国图象图形学报,2007,12(7):1254-1260)
[25]Ho H T,Chellappa R.Pose-Invariant Face Recognition Using Markov Random Fields.IEEE Trans on Image Processing,2013,22(4):1573-1584
[26]Sarfraz M S,Hellwich O.Statistical Appearance Models for Automatic Pose Invariant Face Recognition//Proc of the 8th IEEE International Conference on Automatic Face&Gesture Recognition.Amsterdam,The Netherlands,2008.DOI:10.1109/AFGR.2008.04813387
[27]Guillemaut J Y,Kittler J,Sadeghi M T,et al.General Pose Face Recognition Using Frontal Face Model//Proc of the 11th Iberoamerican Congress in Pattern Recognition.Cancun,Mexico,2006:79-88
[28]Zhao H,Yu P.AAM-Based Alignment and Local Weighted Matching Method for Face Recognition.Journal of Image and Graphics,2013,18(12):1582-1586(in Chinese)(赵恒,俞鹏.基于主动表观模型姿态矫正和局部加权匹配人脸识别.中国图象图形学报,2013,18(12):1582-1586)
[29]Ding L,Ding X Q,Fang C.Continuous Pose Normalization for Pose-Robust Face Recognition.IEEE Signal Processing Letters,2012,19(11):721-724
[30]de Marsico M,Nappi N,Riccio D,et al.Robust Face Recognition for Uncontrolled Pose and Illumination Changes.IEEE Trans on Systems,Man,and Cybernetics:Systems,2013,43(1):149-163
[31]An K H,Chung M J.Pose-Robust Face Recognition Based on Texture Mapping//Proc of the 17th IEEE International Symposium on Robot and Human Interactive Communication.Munich,Germany,2008:65-70
[32]Gong W G,Huang X Y,Li W H.Face Pose Correction for Facial Recognition Based on Sine Transform.Computer Engineering and Applications,2010,46(22):213-216(in Chinese)(龚卫国,黄潇莹,李伟红.基于正弦变换的人脸姿态校正及识别研究.计算机工程与应用,2010,46(22):213-216)
[33]Zhang J Q,Liao H B,Li Y.Multi-view Face Recognition Based on Factor Analysis and Sparse Representation.Computer Engineering and Applications,2013,49(5):154-159(in Chinese)(张疆勤,廖海斌,李原.基于因子分析与稀疏表示的多姿态人脸识别.计算机工程与应用,2013,49(5):154-159)
[34]Li Q B,Liu J G,Huang Z.Multi-view Face Recognition Based on Horizontal Mirror Image and Decision Fusion.Computer Applications and Software,2012,29(12):33-35,80(in Chinese)(李全彬,刘锦高,黄智.基于水平镜像和决策融合的多姿态人脸识别方法.计算机应用与软件,2012,29(12):33-35,80)
[35]Lee M W,Ranganath S.Pose-Invariant Face Recognition Using a3D Deformable Model.Pattern Recognition,2003,36(8):1835-1846
[36]Yang J,Liu Z F,Zhang X Q,et al.Pose Invariant Face Recognition Based on 3D Model.Opto-Electronic Engineering,2009,36(1):140-145(in Chinese)(杨军,刘直芳,张秀琼,等.基于三维模型的多姿态人脸识别.光电工程,2009,36(1):140-145)
[37]Tang H L,Yin B C,Sun Y F,et al.Pose-Invariant Face Recognition Based on a Single View.Journal of Information&Computational Science,2010,7(12):2369-2376
[38]Yuan L,Chen Q H,Yan Y C,et al.Application of Two-Factors Model in Multi-pose Face Recognition.Geomatics and Information Science of Wuhan University,2012,37(5):546-549,585(in Chinese)(袁理,陈庆虎,鄢煜尘,等.两因子模型在多姿态人脸识别中的应用.武汉大学学报·信息科学版,2012,37(5):546-549,585)
[39]Chen X L,Shan S G,Gao W.Pose-Varied Face Recognition.Journal of Image and Graphics,1999,4A(10):818-824(in Chinese)(陈熙霖,山世光,高文.多姿态人脸识别.中国图象图形学报,1999,4A(10):818-824)
[40]Lu J W,Plataniotis K N,Venetsanopoulos A N.A Kernel Machine Based Approach for Multi-view Face Recognition//Proc of the IEEE International Conference on Image Processing.Rochester,USA,2002,I:265-268
[41]Liu X J,Dang J W,Yang F,et al.Development of Face Recognition System Using Multi-views Database//Proc of the 3rd IEEE International Conference on Signal-Image Technologies and Internet-Based System.Shanghai,China,2007:1013-1019
[42]Kisku D R,Mehrotra H,Rattani A,et al.Multiview Gabor Face Recognition by Fusion of PCA and Canonical Covariate through Feature Weighting.Proceedings of SPIE,2009.DOI:10.1117/12.824087
[43]Khaleghian S,Rabiee H R,Rohban M H.Face Recognition across Large Pose Variations via Boosted Tied Factor Analysis//Proc of the IEEE Workshop on Applications of Computer Vision.Kona,USA,2011:190-195
[44]Sharma A,Haj M A,Choi J,et al.Robust Pose Invariant Face Recognition Using Coupled Latent Space Discriminant Analysis.Computer Vision and Image Understanding,2012,116(11):1095-1110
[45]Gao X B,Tian C N.Multi-view Face Recognition Based on Tensor Subspace Analysis and View Manifold Modeling.Neurocomputing,2009,72(16/17/18):3742-3750
[46]Jiang S,Wang Y,Tian C N.Multi-view Face Recognition Based on Tensorfaces Algorithm.Science Technology and Engineering,2009,9(15):4381-4385(in Chinese)(姜珊,王羽,田春娜.基于张量脸的多姿态人脸识别算法.科学技术与工程,2009,9(15):4381-4385)
[47]Li W Q,Chen D S.Multi-pose Face Recognition Combining Tensor Face and Manifold Learning//Proc of the IEEE International Conference on Computer Science and Automation Engineering.Shanghai,China,2011,IV:543-547
[48]Wang Z H,Yuan H,Jiang W T.A Face Recognition Algorithm Based on Composite Gradient Vector.Acta Automatica Sinica,2011,37(12):1445-1454(in Chinese)(王志宏,袁姮,姜文涛.基于复合梯度向量的人脸识别算法.自动化学报,2011,37(12):1445-1454)
[49]Ping Q,Zhuang L S,Yu N H.Affine Minimum Linear Reconstruction Error Face Recognition under Varying Pose and Illumination.Acta Electronica Sinica,2012,40(10):1965-1970(in Chinese)(平强,庄连生,俞能海.姿态和光照可变条件下的仿射最小线性重构误差人脸识别算法.电子学报,2012,40(10):1965-1970)
[50]Xian X B,Wu H J,Zhang M X,et al.A Novel Multi-pose Face Recognition via Robust SIFT Feature//Proc of the International Conference on Wavelet Analysis and Pattern Recognition.Tianjin,China,2013:32-37
[51]Zhang J,He H,Zhan X S,et al.Pose-Invariant Face Recognition via SIFT Vocabulary Tree.Journal of Computer-Aided Design&Computer Graphics,2013,25(11):1694-1700(in Chinese)(张剑,何骅,詹小四,等.用SIFT词汇树实现的姿态无关的人脸识别.计算机辅助设计与图形学学报,2013,25(11):1694-1700)
[52]Lin M Z,Fan X.Low Resolution Face Recognition with Pose Variations Using Deep Belief Networks//Proc of the 4th International Congress on Image and Signal Processing.Shanghai,China,2011,III:1522-1526
[53]Zhu Z Y,Luo P,Wang X G,et al.Deep Learning Identity Preserving Face Space//Proc of the IEEE International Conference on Computer Vision.Sydney,Australia,2013:113-120
[54]Lian S F,Liu Y H,Li L C.Face Recognition under Unconstrained Based on LBP and Deep Learning.Journal on Communications,2014,35(6):154-160(in Chinese)(梁淑芬,刘银华,李立琛.基于LBP和深度学习的非限制条件下人脸识别算法.通信学报,2014,35(6):154-160)
[55]Chai R M,Cao Z J.Face Recognition Algorithm Based on Gabor Wavelet and Deep Belief Networks.Journal of Computer Applications,2014,34(9):2590-2594(in Chinese)(柴瑞敏,曹振基.基于Gabor小波与深度信念网络的人脸识别方法.计算机应用,2014,34(9):2590-2594)
[56]Chen L,Huang X W,Sun B.Pose-Varied Face Recognition Based on WT and LVQ Network.Computer Engineering,2006,32(21):47-49(in Chinese)(陈蕾,黄贤武,孙兵.基于WT和LVQ网络的多姿态人脸识别.计算机工程,2006,32(21):47-49)
[57]Gernoth T,Goossen A,Grigat R R.Face Recognition under Pose Variations Using Shape-Adapted Texture Features//Proc of the17th IEEE International Conference on Image Processing.Hong Kong,China,2010:4525-4528
[58]Castillo C D,Jacobs D W.Wide-Baseline Stereo for Face Recognition with Large Pose Variation//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Providence,USA,2011:537-544
[59]Zhang H C,Nasrabadi N M,Zhang Y N,et al.Joint Dynamic Sparse Representation for Multi-view Face Recognition.Pattern Recognition,2012,45(4):1290-1298
[60]Fransens R,Strecha C,Van Gool L.Parametric Stereo for Multipose Face Recognition and 3D-Face Modelling//Proc of the 2nd International Workshop on Analysis and Modelling of Faces and Gestures.Beijing,China,2005:109-124
[61]Ishiyama R,Hamanaka M,Sakamoto S.An Appearance Model Constructed on 3-D Surface for Robust Face Recognition against Pose and Illumination Variations.IEEE Trans on Systems,Man,and Cybernetics:Applications and Reviews,2005,35(3):326-334
[62]Yin B C,Zhang Z,Sun Y F,et al.Pose Variant Face Recognition Based on 3D Morphable Model.Journal of Beijing University of Technology,2007,33(3):320-325(in Chinese)(尹宝才,张壮,孙艳丰,等.基于三维形变模型的多姿态人脸识别.北京工业大学学报,2007,33(3):320-325)
[63]Zhang X Z,Zhao S Q,Gao Y S.On Averaging Face Images for Recognition under Pose Variations//Proc of the 19th International Conference on Pattern Recognition.Tampa,USA,2008.DOI:10.1109/ICPR.2008.4761890
[64]Prabhu U,Heo J,Savvides M.Unconstrained Pose-Invariant Face Recognition Using 3D Generic Elastic Models.IEEE Trans on Pattern Analysis and Machine Intelligence,2011,33(10):1952-1961
[65]Passalis G,Perakis P,Theoharis T,et al.Using Facial Symmetry to Handle Pose Variations in Real-World 3D Face Recognition.IEEE Trans on Pattern Analysis and Machine Intelligence,2011,33(10):1938-1951
[66]Ye C M,Jiang J G,Zhan S,et al.3D Facial Depth Map Recognition in Different Poses with Surface Contour Feature.Pattern Recognition and Artificial Intelligence,2013,26(2):219-224(in Chinese)(叶长明,蒋建国,詹曙,等.基于曲面等高线特征的不同姿态三维人脸深度图识别.模式识别与人工智能,2013,26(2):219-224)
[67]Zhang Y N,Guo Z,Xia Y,et al.2D Representation of Facial Surfaces for Multi-pose 3D Face Recognition.Pattern Recognition Letters,2012,33(5):530-536