人脸识别技术的研究与应用
|
摘要
本文以公安系统的网上追逃为研究背景，着重对人脸正面图像的静态匹配做了深入探讨，在人脸自动定位和人脸特征提取方面做了大量的实验与工作，并独创性地提出了自适应的二级人脸定位算法(HBEL算法+椭圆模板匹配算法)，使用基于特征区域的分析来提取人脸特征进行识别。实验证明，这种新的组合算法具有速度快、特征数据量小、识别率较高、适用于大数据量识别应用等特点，测试结果表明其在人脸有偏转、有微量表情变化的情况下均具有较好的识别效果。作为具有针对性的研究，我们还在算法实用化方面做了大量的工作，开发出了Mandrill人脸识别系统的原型。
In order to satisfy the new requirement of the police on arresting criminals by on-line information, we took deep research in the recognition of human's frontal face, and did lots of experiments in the period of automatic face locating and feature extracting. In this dissertation we proposed a new adaptable two-step face locating algorithm, which combined HBEL algorithm and ellipse-model matching algorithm, and men we use Eigen-Region Analysis(ERA) to extract feature. Experiments show that this method has high processing speed, low data quantity, great performance so, it's a good choice for large-capacity recognition applications. And it can work well even when the faces are acclivitous or with a little expression. As a research of obvious goal, we developed a prototype system named Mandrill.
In order to satisfy the new requirement of the police on arresting criminals by on-line information, we took deep research in the recognition of human's frontal face, and did lots of experiments in the period of automatic face locating and feature extracting. In this dissertation we proposed a new adaptable two-step face locating algorithm, which combined HBEL algorithm and ellipse-model matching algorithm, and men we use Eigen-Region Analysis(ERA) to extract feature. Experiments show that this method has high processing speed, low data quantity, great performance so, it's a good choice for large-capacity recognition applications. And it can work well even when the faces are acclivitous or with a little expression. As a research of obvious goal, we developed a prototype system named Mandrill.
引文
[1] Chellappa,R.;Wilson,C.L.;Sirohey,S.;"Human and Machine Recognition of Faces: A Survey," Proc. of the IEEE, Vol. 83,No. 5,May 1995,pp. 705-741
[2] S.Akanatsu, T.Sasaki, H.Fukamachi, and YSuenage, "A robust face identification scheme-KL expansion of an invariant feature space,"in SPIE Proc.: Intell. Robots and Computer Vision X: Algorithms and Techn.,vol.1607,1991,pp.71-S4
[3] M.Kirby and L.Sirovich, "Application of the Karhunen-Loeve procedure for the characterization of human faces,'TEEE Trans. Patt. Anal. And Mach. Intell.vol. 12,pp. 103-108,1990．
[4] A.Pentland,B.Moghaddam,T.Stamer,and M.Turk, "Viewbased and modular eigenspaces for face recogmtion,"in Proc. IEEE Computer Soc. Conf. On Computer Vision and Patt. Recog.,1994,pp.84-91．
[5] L.Sirovich and M.Kirby, "Low-dimensional procedure for the characterization of human face,"J. Opt Soc. Amer.,vol.4,pp.519-524,1987
[6] M.A.Turk and A.P.Pentland, "Face recognition using eigenfaces,"in Proc. Int. Conf. On Patt. Recog.,1991,pp.586-591
[7] Z.Hong, "Algebraic feature extraction of image for recognition,"Patt. Recog.,vol24,pp.211-219,1991
[8] R.Brunelli and T.Poggio, "HyperBF networks for gender classification," in Proc.,Darpa Image Understanding Workshop, 1992, pp.311-314
[9] B.A.Golomb and T.J.Sejnowski, "SEXNET: A neural network identifies sex from human faces,"in Advances in Neural Information Processing Systems 3,D.S.Touretzky and R.Lipmann,Eds.San Mateo,CA: Morgan Kaufmann,1991,pp.572-577
[10] K.Aizawa et al., "Human facial motion analysis and synthesis with application to model-based coding,"in Motion Analysis and Image Sequence Processing,M.I.Sezan and R.L.Lagendijk,Eds.Boston,MA:Kluwer,1993,pp.317-348
[11] Grudin M A. Compact multi-level representation of human faces for recognition. Ph. D
dissertation. Liverponl Johm Moores University. Nov. 1997
[12] M.Buck and N.Diehl, "Model-based image sequence coding,"in Motion Analysis and Image Sequence Processing,M.I.Sezan and R.L.Lagendijk, Eds.Boston,MA: Kluwer,1993,pp.285-315
[13] H.Li,P.Roivainen,and R.Forchheimer, "3-D motion estimation in model-based facial image coduig,"IEEETrans.Patt.Anal.and Mach.lntell.,vol.l5,pp.545-555,1993
[14] Proc.DARPA Image Understanding Workshop, 1984,-.
[15] Proc.IEEE Workshops on Motion, 1986,1989,1991．
[16] Computer Vision,Graphics and Image Process., 1972,-.
[17] IEEE Trans.Patt.Anal.and Mach.Intell.,1979,-.
[18] Int.J.Compu.Vision,l 988,-.
[19] VBruce,Recognizing Faces,London: Erlbaum,1988．
[20] GDavies,H.Ellis,and E.J.Shepherd,Perceivmg and Remembering Faces,New York: Academic, 1981．
[21] H.Ellis,M.Jeeves,F.Newcombe,and A. Young, Aspects of Face Processing, Dordrecht: Nijhoff,1986
[22] R.Baron, "Mechanisms of human facial recognition,"Int.J.Man-Machine Studies,vol.l5,pp.l37-178,1981
[23] -, "Perceiving and recognizing faces,"in Mind and Language, 1990, pp.342-364
[24] -, "Introduction to aspects of Face Processing: Ten questions in need of answers,"in Aspects of Face Processing,H. Ellis, M.Jeeves, F.Newcombe, and A.Young,Eds.Dordrecht: Nijhoff,1986,pp.3-13
[25] D.C.Hay and A.W.Yound, "The human face,"in Normality and Pathology in Cognitive Function,A.W.Ellis,Ed.London: Academic, 1982,pp. 173-202
[26] D.Perkins, "A definition of caricature and recognition,"Studies in the Anthropology of Visual Commun.,vol.2,pp. 1-24,1975
[27] A.P.Ginsburg, "Visual informatino processing based on spatial filters constrained by biological data,"AMRL Tech.Rep.,pp.78-129,1978
[28] L.D.Harmon, "The recognition of faces,"Scientific American,vol.229, pp.71-82,1973
[29] W Bledsoe. Man-machine facial recognition. Panotemic Research Inc. Palo Alto,CA, 1966,Rep PRI:22
[30]Berto R.Poggio T. Face recognition: Feature versus templates. IEEE Trans. on PAMI. 1993, 15(10), 1042-1052
[31]Ziquan Hong. Algebraic feature extraction of image for recognition. Pattern Recognition. 1991, 24(3), 211-219
[32]Nakamura O. Mathur S. Minami T. Identification of human faces based on isodensity maps. Pattern Recognition, 1991, 24(3), 263-272
[33]Lades M. Vorhuggen J. Buhmann J et al. Distortion invariant object recognition in the dynamic link architecture. IEEE Trans. on Computers. 1991, 42(3), 300-311.
[34]Samaria F. Young S. HMM-based architecture for face identification. Image and Vision Computing, 1994, 12(8).
[35]Lam K M. Yah H. An analytic-to-holisfc approach for face recognition based on a single frontal view. IEEE Trans. on PAMI. 1998, 20(7).
[36]Lanitis A. Taylor C J. Cooles T F. Automatic interpretation and coding of face images using flexible models. IEEE Trans. on PAMI. 1997, 19(7)
[37]游素亚，彭振云，“允许姿态变化的快速人脸特征检测”，《中国图象图形学报》1997，2(4)，p225-229
[38]Milan Sonka, Vaclav Hlavac, and Roger Boyle, Image processing, analysis, and machine vision, Chapman & Hall Computing, London, 1993.
[39]H.D.Cheng, JIM-Rong Chen, JiGuang Li, "Threshold selection based on fuzzy c-partition entropy approach", Pattern Recognition, Vol. 31, No. 7, pp.857-870, 1998
[40]Sirovich L, Kirby M, "Low-dimensional procedure for the characterization of human face", J Opt Soc Amer A, 1957, 4(3), 519-524
[41]Turk M, Pentland A, "Eigenfaces for recognition", Journal of Cognitive Neuroscience, 1991, 3(1), 71-86
[42]奥亚 E，子空间法模式识别，蔡国廉，杨文瑜译，北京，科学出版社，1987
[43]孙羽，董洪斌，“人脸图象的模糊识别方法”，哈尔滨师范大学自然科学学报，1997，13(1)．-65-68
[44]彭辉，张长水，“基于K-L变换的人脸自动识别方法”，清华大学学报：自科版，1997，37(3)．-67-70
[45]王华，李介谷，“人脸视图象的特征提取与恢复”，上海交通大学学报，1997，31(1)．-101-104
[46]彭振云，游素亚，“允许姿态变化的快速人脸特征检测”，中国图象图形学报，1997，2(4)，-225-229
[47]高西奇，周洪祥等，“基于小波变换的主元分析人脸图象识别”，东南大学学报，1996，26(2)．-137-141
[48]张辉，周洪祥等，“基于主元分析神经网络的人脸特征提取及识别研究”，模式识别与人工智能，1996，9(1)．-52-58
[49]游素亚，张永越等，“一种基于多视点图像的可变姿态人脸识别系统”，中国图象图形学报，1996，1(3)．-185-190
[50]荆仁杰等，《计算机图象处理》，浙江大学出版社，1990
[51]黄智编著，《图象处理与识别使用程序库》，天津科学技术出版社，1987
[52]郑南宁著，《计算机视觉与模式识别》，国防工业出版社，1998
[53]杨建刚编著，《人工神经网络实用教程》，浙江大学出版社，2001
[2] S.Akanatsu, T.Sasaki, H.Fukamachi, and YSuenage, "A robust face identification scheme-KL expansion of an invariant feature space,"in SPIE Proc.: Intell. Robots and Computer Vision X: Algorithms and Techn.,vol.1607,1991,pp.71-S4
[3] M.Kirby and L.Sirovich, "Application of the Karhunen-Loeve procedure for the characterization of human faces,'TEEE Trans. Patt. Anal. And Mach. Intell.vol. 12,pp. 103-108,1990．
[4] A.Pentland,B.Moghaddam,T.Stamer,and M.Turk, "Viewbased and modular eigenspaces for face recogmtion,"in Proc. IEEE Computer Soc. Conf. On Computer Vision and Patt. Recog.,1994,pp.84-91．
[5] L.Sirovich and M.Kirby, "Low-dimensional procedure for the characterization of human face,"J. Opt Soc. Amer.,vol.4,pp.519-524,1987
[6] M.A.Turk and A.P.Pentland, "Face recognition using eigenfaces,"in Proc. Int. Conf. On Patt. Recog.,1991,pp.586-591
[7] Z.Hong, "Algebraic feature extraction of image for recognition,"Patt. Recog.,vol24,pp.211-219,1991
[8] R.Brunelli and T.Poggio, "HyperBF networks for gender classification," in Proc.,Darpa Image Understanding Workshop, 1992, pp.311-314
[9] B.A.Golomb and T.J.Sejnowski, "SEXNET: A neural network identifies sex from human faces,"in Advances in Neural Information Processing Systems 3,D.S.Touretzky and R.Lipmann,Eds.San Mateo,CA: Morgan Kaufmann,1991,pp.572-577
[10] K.Aizawa et al., "Human facial motion analysis and synthesis with application to model-based coding,"in Motion Analysis and Image Sequence Processing,M.I.Sezan and R.L.Lagendijk,Eds.Boston,MA:Kluwer,1993,pp.317-348
[11] Grudin M A. Compact multi-level representation of human faces for recognition. Ph. D
dissertation. Liverponl Johm Moores University. Nov. 1997
[12] M.Buck and N.Diehl, "Model-based image sequence coding,"in Motion Analysis and Image Sequence Processing,M.I.Sezan and R.L.Lagendijk, Eds.Boston,MA: Kluwer,1993,pp.285-315
[13] H.Li,P.Roivainen,and R.Forchheimer, "3-D motion estimation in model-based facial image coduig,"IEEETrans.Patt.Anal.and Mach.lntell.,vol.l5,pp.545-555,1993
[14] Proc.DARPA Image Understanding Workshop, 1984,-.
[15] Proc.IEEE Workshops on Motion, 1986,1989,1991．
[16] Computer Vision,Graphics and Image Process., 1972,-.
[17] IEEE Trans.Patt.Anal.and Mach.Intell.,1979,-.
[18] Int.J.Compu.Vision,l 988,-.
[19] VBruce,Recognizing Faces,London: Erlbaum,1988．
[20] GDavies,H.Ellis,and E.J.Shepherd,Perceivmg and Remembering Faces,New York: Academic, 1981．
[21] H.Ellis,M.Jeeves,F.Newcombe,and A. Young, Aspects of Face Processing, Dordrecht: Nijhoff,1986
[22] R.Baron, "Mechanisms of human facial recognition,"Int.J.Man-Machine Studies,vol.l5,pp.l37-178,1981
[23] -, "Perceiving and recognizing faces,"in Mind and Language, 1990, pp.342-364
[24] -, "Introduction to aspects of Face Processing: Ten questions in need of answers,"in Aspects of Face Processing,H. Ellis, M.Jeeves, F.Newcombe, and A.Young,Eds.Dordrecht: Nijhoff,1986,pp.3-13
[25] D.C.Hay and A.W.Yound, "The human face,"in Normality and Pathology in Cognitive Function,A.W.Ellis,Ed.London: Academic, 1982,pp. 173-202
[26] D.Perkins, "A definition of caricature and recognition,"Studies in the Anthropology of Visual Commun.,vol.2,pp. 1-24,1975
[27] A.P.Ginsburg, "Visual informatino processing based on spatial filters constrained by biological data,"AMRL Tech.Rep.,pp.78-129,1978
[28] L.D.Harmon, "The recognition of faces,"Scientific American,vol.229, pp.71-82,1973
[29] W Bledsoe. Man-machine facial recognition. Panotemic Research Inc. Palo Alto,CA, 1966,Rep PRI:22
[30]Berto R.Poggio T. Face recognition: Feature versus templates. IEEE Trans. on PAMI. 1993, 15(10), 1042-1052
[31]Ziquan Hong. Algebraic feature extraction of image for recognition. Pattern Recognition. 1991, 24(3), 211-219
[32]Nakamura O. Mathur S. Minami T. Identification of human faces based on isodensity maps. Pattern Recognition, 1991, 24(3), 263-272
[33]Lades M. Vorhuggen J. Buhmann J et al. Distortion invariant object recognition in the dynamic link architecture. IEEE Trans. on Computers. 1991, 42(3), 300-311.
[34]Samaria F. Young S. HMM-based architecture for face identification. Image and Vision Computing, 1994, 12(8).
[35]Lam K M. Yah H. An analytic-to-holisfc approach for face recognition based on a single frontal view. IEEE Trans. on PAMI. 1998, 20(7).
[36]Lanitis A. Taylor C J. Cooles T F. Automatic interpretation and coding of face images using flexible models. IEEE Trans. on PAMI. 1997, 19(7)
[37]游素亚，彭振云，“允许姿态变化的快速人脸特征检测”，《中国图象图形学报》1997，2(4)，p225-229
[38]Milan Sonka, Vaclav Hlavac, and Roger Boyle, Image processing, analysis, and machine vision, Chapman & Hall Computing, London, 1993.
[39]H.D.Cheng, JIM-Rong Chen, JiGuang Li, "Threshold selection based on fuzzy c-partition entropy approach", Pattern Recognition, Vol. 31, No. 7, pp.857-870, 1998
[40]Sirovich L, Kirby M, "Low-dimensional procedure for the characterization of human face", J Opt Soc Amer A, 1957, 4(3), 519-524
[41]Turk M, Pentland A, "Eigenfaces for recognition", Journal of Cognitive Neuroscience, 1991, 3(1), 71-86
[42]奥亚 E，子空间法模式识别，蔡国廉，杨文瑜译，北京，科学出版社，1987
[43]孙羽，董洪斌，“人脸图象的模糊识别方法”，哈尔滨师范大学自然科学学报，1997，13(1)．-65-68
[44]彭辉，张长水，“基于K-L变换的人脸自动识别方法”，清华大学学报：自科版，1997，37(3)．-67-70
[45]王华，李介谷，“人脸视图象的特征提取与恢复”，上海交通大学学报，1997，31(1)．-101-104
[46]彭振云，游素亚，“允许姿态变化的快速人脸特征检测”，中国图象图形学报，1997，2(4)，-225-229
[47]高西奇，周洪祥等，“基于小波变换的主元分析人脸图象识别”，东南大学学报，1996，26(2)．-137-141
[48]张辉，周洪祥等，“基于主元分析神经网络的人脸特征提取及识别研究”，模式识别与人工智能，1996，9(1)．-52-58
[49]游素亚，张永越等，“一种基于多视点图像的可变姿态人脸识别系统”，中国图象图形学报，1996，1(3)．-185-190
[50]荆仁杰等，《计算机图象处理》，浙江大学出版社，1990
[51]黄智编著，《图象处理与识别使用程序库》，天津科学技术出版社，1987
[52]郑南宁著，《计算机视觉与模式识别》，国防工业出版社，1998
[53]杨建刚编著，《人工神经网络实用教程》，浙江大学出版社，2001