基于仿生模式识别的人脸身份确认研究
|
摘要
人脸自动识别技术有着广阔的应用前景和迫切的现实需求，是当前模式识别领域最热门的研究方向之一。本文首先对人脸识别技术的研究内容和人脸识别技术的发展做了概括性的介绍，接着对人脸检测和识别技术的研究现状进行了较全面的论述，然后介绍了神经网络技术在人脸识别中的应用，最后详细叙述了基于仿生模式识别的人脸身份确认系统。
本文从以下几个方面对人脸识别技术做了探讨：
1．通过定义图像块的复杂度，快速而又准确地找到人脸图像中的眼睛、鼻子和嘴巴等特征器官，为人脸的姿势校正，特征参数的提取提供了有力的保证。
2．通过寻找各个特征器官的中心，进而提取特征器官周围的细微信息的方法来提取人脸的特征参数，提出了一种新的人脸特征参数提取方法。
3．用三个摄像头摄取图像弥补了用单像头摄取二维图像表达三维人脸的不足，使得通过融合同一时刻采取的多幅图像更加完备地表达同一人脸。
4．运用仿生模式识别理论建立起识别神经网络。仿生模式识别从“认识”而不是“区分”的角度来进行模式识别，是对学习样本的全体在特征空间中形成的复杂几何体“形状”的分析和“认识”，为用高维空间理论建立识别神经网络提供了理论基础。
Automatic human face recognition is attractive in pattern recognition and image processing and has a broad prospect in the application in reality.
In this paper, first, the content and development of automatic human face recognition are introduced briefly; then, a survey of automatic human face detection and recognition is given; second, the application of neural network in automatic human face recognition is talked about; last, it is discussed in detail about the system of human face personal identification based on the biomimetic pattern recognition.
In this paper several views are given as follows:
1. In this paper, the feature are found rapidly and rightly through the definition of the complexity of picture . It provides a strong support for the adjustment of posture and the feature extraction.
2. A new method of the feature extraction from human face is presented. It firstly finds out the centers of organ and the subtle of the features are considered as face features.
3. In this paper, three video cameras are used in order to describe faces more completely than two video cameras.
4. The neural network based on the biomimetic pattern recognition principles is built. The biomimetic pattern recognition makes recognition from the views of "matter cognition" instead of "matter classification", which analyzes and cognizes the high dimensional geometrical distribution that consists of the sample sets in the high dimensional feature space. It provides the theoretic basis of building the neural network based on high dimensional theory.
本文从以下几个方面对人脸识别技术做了探讨：
1．通过定义图像块的复杂度，快速而又准确地找到人脸图像中的眼睛、鼻子和嘴巴等特征器官，为人脸的姿势校正，特征参数的提取提供了有力的保证。
2．通过寻找各个特征器官的中心，进而提取特征器官周围的细微信息的方法来提取人脸的特征参数，提出了一种新的人脸特征参数提取方法。
3．用三个摄像头摄取图像弥补了用单像头摄取二维图像表达三维人脸的不足，使得通过融合同一时刻采取的多幅图像更加完备地表达同一人脸。
4．运用仿生模式识别理论建立起识别神经网络。仿生模式识别从“认识”而不是“区分”的角度来进行模式识别，是对学习样本的全体在特征空间中形成的复杂几何体“形状”的分析和“认识”，为用高维空间理论建立识别神经网络提供了理论基础。
Automatic human face recognition is attractive in pattern recognition and image processing and has a broad prospect in the application in reality.
In this paper, first, the content and development of automatic human face recognition are introduced briefly; then, a survey of automatic human face detection and recognition is given; second, the application of neural network in automatic human face recognition is talked about; last, it is discussed in detail about the system of human face personal identification based on the biomimetic pattern recognition.
In this paper several views are given as follows:
1. In this paper, the feature are found rapidly and rightly through the definition of the complexity of picture . It provides a strong support for the adjustment of posture and the feature extraction.
2. A new method of the feature extraction from human face is presented. It firstly finds out the centers of organ and the subtle of the features are considered as face features.
3. In this paper, three video cameras are used in order to describe faces more completely than two video cameras.
4. The neural network based on the biomimetic pattern recognition principles is built. The biomimetic pattern recognition makes recognition from the views of "matter cognition" instead of "matter classification", which analyzes and cognizes the high dimensional geometrical distribution that consists of the sample sets in the high dimensional feature space. It provides the theoretic basis of building the neural network based on high dimensional theory.
引文
[1] YOON K.S, HAM Y.K and PARK R H. Hybrid Approaches to Frontal Viewface Recognition Using the Hidden Markov and Neural Network. Pattern Recognition, 1998, 31: 283-293.
[2] JENG S.H, LIAO H.Y.M, C.C. HAN, CHERN M.Y. and Y.T. LIU. Facial Feature Detection Using Geometrical Face Model: an efficient approach. Pattern Recognition, 1998, 31: 273-282.
[3] Samal A. Automatic recognition and analysis for human faces and facial expressions: A survey. Pattern Recognition, 1992,25:65～77.
[4] Valentin D, Abdi H, O'Toole A J. Connectionist models of face processing. Pattern Recognition, 1994, 27:1209～1230.
[5] 周激流，张晔．人脸识别理论研究进展．计算机辅助设计与图形学学报，1999，11：180-184．
[6] Allen A L. Personal Descriptions. Lodon:Butterworth, 1950.
[7] Kaya Y, Kobayashi K.A Basic Study on Human Recognition. In Frontiers of Pattern Recognition, New York:Academic, 1971:265-289.
[8] Kanad T. Picture processing system by computerand recognition of human face[PhD Dissertation]. Kyoto: Kyoto University, 1973.
[9] Sirovich L, Kirby M. Application of karhunen-loeve procedure for the characterization of human faces. IEEE Transactions on PAMI, 1990,12(1): 103-108.
[10] Turk M, Pentland M.Eigenfaces for Recognition. JCognitive Neurosci, 1991,3(1):71-79.
[11] Bouattour H,Fogelman-Soulie H,Viennet E. Solving the Human face recognition task using neural Nets.Proc Artificial Neural Networks, Aleksander J, Taylor J,eds.Amsterdan:NorthHolland, 1992:1595-1598.
[12] Baron R. Mechanisms of human facial recognition. Int.J.Man-Machine studies, 1989, 2:283-310.
[13] Bruce V.Recognizing facing. London: Erlbaum, 1988.
[14] Bischsel M. Perceiving and recognizing faces, Mind and Language, 1990:342-364.
[15] Ellis H et al. Aspects of face processing, Dordrecht:Nijhoff, 1986
[16] 王守觉，徐健，王宪保，覃鸿．基于仿生模式识别的多镜头人脸身份确认系统研究．电子学报，2003(1)：1-3．
[17] Kannech R.Castleman, Digital Image Processing, Prentice-Hall international, Inc, 1996.
[18] 边肇祺，张学工．模式识别．北京：清华出版社，2000，
[19] 石长有．外貌特征与鉴别．警官教育出版社，1991．
[20] G.Yang, T.S.Huang. Human face detection in a complex background. Pattern Recognition, 1994, Vol.27:53-63.
[21] Bowns L, Morgan M J. Facial feature and axis of symmetry extracted using natural orientation information. Biological Cybernetics, 1993, 70:137-144.
[22] D.Reisfeld, H. Wolfson, Y. Yeshurun. Context free attentional operator: the
generalized symmetry transform. International Journal of Computer Vision, 1995, 14: 119-130．
[23] D. Reisfeld, H. Wolfson, Y. Yeshurun. Detection of interest points using symmetry, Processing of the 3rd ICCV, 1990:62-65．
[24] H.Z.Ai L.h.Liang and B.Zhang. Face Detection Based on Multiple Related Template Matching. Pree. Of Japan-China Sysposium on Advanced Information Technology, Tokyo, Japan, 1999:283-294．
[25] Yuille Al, Cohen D S, Hallinan P W. Feature extraction from faces using deformable template, Processing of CVPR, 1989:104-109．
[26] Yuille A L. deformable template for face recognition. Journal of Cognitive Neuroscience,1991, 3(1) :59-70．
[27] Yuille A 1, Hallinan P W, Cohen D S. Feature extraction from faces using deformable template. International Journal of Computer Vision, 1992, 8(2) :99-111．
[28] C.Huang, C.Chen. Human Facial feature extraction for face interpre-tation and recognition. Pattern Recognition, 1999(25) : 1435-1444．
[29] C.Huang,C.Chen. Human Facial feature extraction for face interpre-tation and recognition. Processing of ICPR,1992:204-207．
[30] K,Lam,H.Yan. Locating and extracting the eye in human face image. Pattern Recognition, 1993(26) : 1739-1755．
[31] Lam K-M, Yan H. Locating head boundary by snakes. Processing of international Symposium on Speech, Image Processing and Neural Network, 1994:17-20．
[32] Gerald J.Kaufman,JR.,and Kenneth J.Breeding. The automatic recognition of human faces from profile silhouettes. IEEE Trans, on Systems, Man and Cybernetics, Vol.SMC-6, No.2, February 1976．
[33] R.Brunelli,T.Poggio. Face recognition through geometrical features, proceedings of ECCV, 1992:792-800．
[34] R.Brunelli,T.Poggio. Face recognition: features versus templates. IEEE trans. PAMI, 1993, 15:1042-1052．
[35] Turk Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 1991,3(1) :71-86．
[36] B.Moghaddam and A.Pentland. Probabilistic visual learning for object representation. IEEE Trans. On Pattern Analysis and Machine Intelligence, Vol. 19,No.7,July 1997．
[37] B.Moghaddam, A. Pentland. Maximum Likelihood detection of faces and hands. Proceeding of International Workshop on Automatic Face and Gesture Recognition, 1995:122-128．
[38] Colmenarez A J, Huang T S. Maximum likelihood face detection. Proceeding of International Conference on Automatic Face and Gesture Recognition, 1996:307-311．
[39] Colmenarez A J, Huang T S. Face detection with information-based maximum discrimination. Proceeding of CVRR, 1997: 782-787．
[40] GBurel, D.Carel. Detection and Localization of faces on digital images. Pattern Recognition Lett, 1994,15(10) :963-967．
[41] Vincent J M,Waite J B, Myer D J. Automatic location of visual feature by a system of multilayered perceptrons. IEE proceeding F,1992, 139(6) :405-412．
[42] Julie P, March R.A hierarchical neural network for human face detection, Pattern Recognition, 1996,29(5) ,781-787
[43] Shang-Huang Lin, Sun-Yuan Kung and Long-Ji Lin. Face recognition /detection by probabilistic decision-based neural network. IEEE Trans. On neural networks, Vol.8,No.l, January 1997:114-132．
[44] C.J.C. Surges. A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, Vol 2, Number 2,1998．
[45] M.H. Yang and N. Ahuja. Detection human faced in color image, processing of international conference om imaging Processing, MA05． 02,1998．
[46] M.Kapfer, J.Benois-Pinneau. Detection human faced in color image sequences with arbitrary motions for very low bit-rate videophone coding. Pattern Recognition Letters, 1997,Vol.18(14) :1503-1518．
[47] Y.Dai,Y.Nakano. Face-texture model based on SGLD and its application in face detection in a color scene. Pattern Recognition 29(1996) :1007-1017．
[48] K.Mase,Y.Watanable and Y.Ssuenaga. a real time head motion detection system. SPIE, 1990, Vol. 1260:263-269．
[49] M.Turk and A.Pentland. Face recognition using Eigenfaces.CVPR'91: 586-591．
[50] C.H.Lee, J.S.Kim, K,H,Park. Automatic face location in complex bachground using motion and color information. Pattern Recognition 1996,29:1877-1889．
[51] S.Rowe and A.Blake. Statistical mosaic for tracking. Image and vision computing, 1996,Vol. 14: 549-564．
[52] 周杰，卢春雨，张长水，李衍达．人脸自动识别方法综述．电子学报， Vol．28，No．4，April 2000．
[53] 张翠平，苏光大．人脸自动识别技术．中国图像图形学报，Vol．5(A)，No．11， 2000年11月．
[54] X.Jia,MS. IEEErans PAMI. 1995,17:1167-1176．
[55] R.Brunelli, T.Poggio. IEEETrans. PAMI.1993,15:1042-1052．
[56] I,J. Cox, J.Ghosn, P.N. Yianilos. CVPR' 96:209-216．
[57] N.Roder, X.Li.Pattern Recognition, 1996,29:143-157．
[58] Al. Yuille.J.Cognitive Neuroscience, 1989, 3:59-70．
[59] K.M.Lam, H.Yan. Pattern Recognition, 1995,29:771-779．
[60] J.Ydeng, F.Lai. Pattern Recognition, 1997,30:403-419．
[61] B.Moghaddam, A. Pentland.IEEEtrans. PAMI, 1997,19:696:710．
[62] MA.Turk, A.P. Pentland. CVPR'91:586-591．
[63] H.peng, D. Electronics Letters, 1997,33:283-284．
[64] D.L. Swetsandj. Weng. lEEETrans. PAMI, 1996,18:831-836．
[65] P.N.Belhumeuretal. lEEETrans. PAMI,1997,19:711-720．
[66] D.Valentinetal. Pattern Recognition, 1994,27:1209-1230．
[67] 彭辉，张长水，荣钢，边肇祺．基于K-L变换的人脸自动识别方法．清华大学 学报(自然科学版)，1997，37(3) ：67-70．
[68] Moghaddam B,Pentland A.Beyond linear eigenspaces:Bayesian matching for face ecognition.In:Face Recognition from Theory to Applications, NATO ASI series:Series F, 1997:230-243．
[69] Grudin M A.Compactmulti-level representation of human faces for recognition. Ph.
D dissertation, Liverpool John Moores University, Nov. 1997.
[70] Nastar C, Ayache N.Frequency-based non-rigid motion analysis.IEEE Trans Pattern Anal and Mach Intell,1996,18(11): 1067～1079.
[71] 赖剑煌，颜鑫弘，邓东皋，完善频谱脸人像识别的分类器设计，中国图像图形学报，2002，No．5，Vol．7(A)．
[72] M.Ladesetal.IEEE Trans.Computer, 1993,42:300-311.
[72] J.Zhang etal. Proc. IEEE, 1997,85:1423-1435.
[74] L.Wiskott. Pattern Recognition, 1997,30:837-846.
[75] L.Wiskottetal. IEEE Trans. PAMI, 1997,19:775-779.
[76] C.Nastaretal. Computer Vision and Image Understanding, 1997,65:179-191.
[77] B.Moghaddametal. CVPR, 1996.
[78] A.Lanitisetal. Image&Vision Computing, 1995,13:393-401.
[39] A.Lanitisetal. IEEE Trans. PAMI, 1997,19:743-756.
[80] D.Valentinetal. Pattern Recognition, 1994, 27:1209-1230.
[81] N.Intrator, Reisfeld, Y. Yeshurun. PR Letters, 1996, 17:67-76.
[82] S.Y. Lee etal. Pattern Recognition, 1996,29:1863-1876.
[83] S.Lawrence etal. IEEE Trans. NN, 1997,8:98-113.
[84] Y. Dal, Y. Nakano. Pattern Recognition, 1998,31:159-167.
[85] S.Gutta, H. Wechaler. Pattern Recognition, 1997, 30:539-553。
[86] P.J。Phillips. IEEE Tans. Image Processing, 1998,7:1150-1164.
[87] C.Y. Lu etal. ICNNB, 1998,645-648.
[88] 金忠．人脸图像的自动校准算法．数据采集与处理，1999，14(2)：171-174
[89] 王宪保，王辛刚，冯浩，王守觉．基于面部器官的人脸特征提取方法．第一次神经网络与计算智能学术会议，杭州，2002(10)：250-254．
[90] 徐兆涵，王辛刚，冯浩，王守觉，一种人脸识别中寻找图像结构对称性的快速算法．第一次神经网络与计算智能学术会议，杭州，2002(10)：255-259．
[91] 邵虹，徐全生，崔文成．基于即神经网络的人脸图像识别方法的研究．沈阳工业大学学报，2000(8)，Vol 22，No．4．
[92] 张悦，周春光．基于径向基函数网络人脸识别的研究．系统仿真学报，2001(11)，Vol．13 Suppl．
[93] 陈刚，戚飞虎．基于差别特征的神经网络人脸识别．计算机工程，2000(8)，Vol．26，No．8．
[94] 赵振宇，徐用懋．模糊理论与神经网络的基础与应用．清华大学出版社，1996。
[95] W.S.McCulloch, and W. Pitts. A logic Calculus of the Ideas Imminent in Nerves Activity"[J].Bulletin of Mathematical Biophysics, 1943,5:115-133.
[96] 王守觉，李兆渊．通用神经网络硬件中神经元基本数学模型的讨论．电子学报，2001，Vol．29，No．5：276-280．
[97] M.A.Cohen, and S. Grossberg. Absolute Stability of global Pattern Formation and Parallel Memory Storage by Competitive Neural Networks. [J] IEEE Trans. Syst. Man Cybern, 1983,SMC-13: 815-826.
[98] R.LHardy. Multiquadric equations of topography and other irregular surfaces. [J] J.Grephys. Res., Vol.76:1905-1915.
[99] M.J.D.Powell. Radial basis functions for multivariable interpolation: A review, [A] in J.C.Mason and M.G.Cox, editors, Algorithms for Approximation. Clarendon Press,
Oxford, 1987.
[100] 王守觉．仿生模式识别(拓扑模式识别)—一种模式识别新模型的理论与应用．电子学报，2002，Vol．30，No．10．
[101] Ryszard Engelking. Dimension Theory [M], PWM-Polish Scientific Publishers-Warszawa, 1978.
[2] JENG S.H, LIAO H.Y.M, C.C. HAN, CHERN M.Y. and Y.T. LIU. Facial Feature Detection Using Geometrical Face Model: an efficient approach. Pattern Recognition, 1998, 31: 273-282.
[3] Samal A. Automatic recognition and analysis for human faces and facial expressions: A survey. Pattern Recognition, 1992,25:65～77.
[4] Valentin D, Abdi H, O'Toole A J. Connectionist models of face processing. Pattern Recognition, 1994, 27:1209～1230.
[5] 周激流，张晔．人脸识别理论研究进展．计算机辅助设计与图形学学报，1999，11：180-184．
[6] Allen A L. Personal Descriptions. Lodon:Butterworth, 1950.
[7] Kaya Y, Kobayashi K.A Basic Study on Human Recognition. In Frontiers of Pattern Recognition, New York:Academic, 1971:265-289.
[8] Kanad T. Picture processing system by computerand recognition of human face[PhD Dissertation]. Kyoto: Kyoto University, 1973.
[9] Sirovich L, Kirby M. Application of karhunen-loeve procedure for the characterization of human faces. IEEE Transactions on PAMI, 1990,12(1): 103-108.
[10] Turk M, Pentland M.Eigenfaces for Recognition. JCognitive Neurosci, 1991,3(1):71-79.
[11] Bouattour H,Fogelman-Soulie H,Viennet E. Solving the Human face recognition task using neural Nets.Proc Artificial Neural Networks, Aleksander J, Taylor J,eds.Amsterdan:NorthHolland, 1992:1595-1598.
[12] Baron R. Mechanisms of human facial recognition. Int.J.Man-Machine studies, 1989, 2:283-310.
[13] Bruce V.Recognizing facing. London: Erlbaum, 1988.
[14] Bischsel M. Perceiving and recognizing faces, Mind and Language, 1990:342-364.
[15] Ellis H et al. Aspects of face processing, Dordrecht:Nijhoff, 1986
[16] 王守觉，徐健，王宪保，覃鸿．基于仿生模式识别的多镜头人脸身份确认系统研究．电子学报，2003(1)：1-3．
[17] Kannech R.Castleman, Digital Image Processing, Prentice-Hall international, Inc, 1996.
[18] 边肇祺，张学工．模式识别．北京：清华出版社，2000，
[19] 石长有．外貌特征与鉴别．警官教育出版社，1991．
[20] G.Yang, T.S.Huang. Human face detection in a complex background. Pattern Recognition, 1994, Vol.27:53-63.
[21] Bowns L, Morgan M J. Facial feature and axis of symmetry extracted using natural orientation information. Biological Cybernetics, 1993, 70:137-144.
[22] D.Reisfeld, H. Wolfson, Y. Yeshurun. Context free attentional operator: the
generalized symmetry transform. International Journal of Computer Vision, 1995, 14: 119-130．
[23] D. Reisfeld, H. Wolfson, Y. Yeshurun. Detection of interest points using symmetry, Processing of the 3rd ICCV, 1990:62-65．
[24] H.Z.Ai L.h.Liang and B.Zhang. Face Detection Based on Multiple Related Template Matching. Pree. Of Japan-China Sysposium on Advanced Information Technology, Tokyo, Japan, 1999:283-294．
[25] Yuille Al, Cohen D S, Hallinan P W. Feature extraction from faces using deformable template, Processing of CVPR, 1989:104-109．
[26] Yuille A L. deformable template for face recognition. Journal of Cognitive Neuroscience,1991, 3(1) :59-70．
[27] Yuille A 1, Hallinan P W, Cohen D S. Feature extraction from faces using deformable template. International Journal of Computer Vision, 1992, 8(2) :99-111．
[28] C.Huang, C.Chen. Human Facial feature extraction for face interpre-tation and recognition. Pattern Recognition, 1999(25) : 1435-1444．
[29] C.Huang,C.Chen. Human Facial feature extraction for face interpre-tation and recognition. Processing of ICPR,1992:204-207．
[30] K,Lam,H.Yan. Locating and extracting the eye in human face image. Pattern Recognition, 1993(26) : 1739-1755．
[31] Lam K-M, Yan H. Locating head boundary by snakes. Processing of international Symposium on Speech, Image Processing and Neural Network, 1994:17-20．
[32] Gerald J.Kaufman,JR.,and Kenneth J.Breeding. The automatic recognition of human faces from profile silhouettes. IEEE Trans, on Systems, Man and Cybernetics, Vol.SMC-6, No.2, February 1976．
[33] R.Brunelli,T.Poggio. Face recognition through geometrical features, proceedings of ECCV, 1992:792-800．
[34] R.Brunelli,T.Poggio. Face recognition: features versus templates. IEEE trans. PAMI, 1993, 15:1042-1052．
[35] Turk Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 1991,3(1) :71-86．
[36] B.Moghaddam and A.Pentland. Probabilistic visual learning for object representation. IEEE Trans. On Pattern Analysis and Machine Intelligence, Vol. 19,No.7,July 1997．
[37] B.Moghaddam, A. Pentland. Maximum Likelihood detection of faces and hands. Proceeding of International Workshop on Automatic Face and Gesture Recognition, 1995:122-128．
[38] Colmenarez A J, Huang T S. Maximum likelihood face detection. Proceeding of International Conference on Automatic Face and Gesture Recognition, 1996:307-311．
[39] Colmenarez A J, Huang T S. Face detection with information-based maximum discrimination. Proceeding of CVRR, 1997: 782-787．
[40] GBurel, D.Carel. Detection and Localization of faces on digital images. Pattern Recognition Lett, 1994,15(10) :963-967．
[41] Vincent J M,Waite J B, Myer D J. Automatic location of visual feature by a system of multilayered perceptrons. IEE proceeding F,1992, 139(6) :405-412．
[42] Julie P, March R.A hierarchical neural network for human face detection, Pattern Recognition, 1996,29(5) ,781-787
[43] Shang-Huang Lin, Sun-Yuan Kung and Long-Ji Lin. Face recognition /detection by probabilistic decision-based neural network. IEEE Trans. On neural networks, Vol.8,No.l, January 1997:114-132．
[44] C.J.C. Surges. A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, Vol 2, Number 2,1998．
[45] M.H. Yang and N. Ahuja. Detection human faced in color image, processing of international conference om imaging Processing, MA05． 02,1998．
[46] M.Kapfer, J.Benois-Pinneau. Detection human faced in color image sequences with arbitrary motions for very low bit-rate videophone coding. Pattern Recognition Letters, 1997,Vol.18(14) :1503-1518．
[47] Y.Dai,Y.Nakano. Face-texture model based on SGLD and its application in face detection in a color scene. Pattern Recognition 29(1996) :1007-1017．
[48] K.Mase,Y.Watanable and Y.Ssuenaga. a real time head motion detection system. SPIE, 1990, Vol. 1260:263-269．
[49] M.Turk and A.Pentland. Face recognition using Eigenfaces.CVPR'91: 586-591．
[50] C.H.Lee, J.S.Kim, K,H,Park. Automatic face location in complex bachground using motion and color information. Pattern Recognition 1996,29:1877-1889．
[51] S.Rowe and A.Blake. Statistical mosaic for tracking. Image and vision computing, 1996,Vol. 14: 549-564．
[52] 周杰，卢春雨，张长水，李衍达．人脸自动识别方法综述．电子学报， Vol．28，No．4，April 2000．
[53] 张翠平，苏光大．人脸自动识别技术．中国图像图形学报，Vol．5(A)，No．11， 2000年11月．
[54] X.Jia,MS. IEEErans PAMI. 1995,17:1167-1176．
[55] R.Brunelli, T.Poggio. IEEETrans. PAMI.1993,15:1042-1052．
[56] I,J. Cox, J.Ghosn, P.N. Yianilos. CVPR' 96:209-216．
[57] N.Roder, X.Li.Pattern Recognition, 1996,29:143-157．
[58] Al. Yuille.J.Cognitive Neuroscience, 1989, 3:59-70．
[59] K.M.Lam, H.Yan. Pattern Recognition, 1995,29:771-779．
[60] J.Ydeng, F.Lai. Pattern Recognition, 1997,30:403-419．
[61] B.Moghaddam, A. Pentland.IEEEtrans. PAMI, 1997,19:696:710．
[62] MA.Turk, A.P. Pentland. CVPR'91:586-591．
[63] H.peng, D. Electronics Letters, 1997,33:283-284．
[64] D.L. Swetsandj. Weng. lEEETrans. PAMI, 1996,18:831-836．
[65] P.N.Belhumeuretal. lEEETrans. PAMI,1997,19:711-720．
[66] D.Valentinetal. Pattern Recognition, 1994,27:1209-1230．
[67] 彭辉，张长水，荣钢，边肇祺．基于K-L变换的人脸自动识别方法．清华大学 学报(自然科学版)，1997，37(3) ：67-70．
[68] Moghaddam B,Pentland A.Beyond linear eigenspaces:Bayesian matching for face ecognition.In:Face Recognition from Theory to Applications, NATO ASI series:Series F, 1997:230-243．
[69] Grudin M A.Compactmulti-level representation of human faces for recognition. Ph.
D dissertation, Liverpool John Moores University, Nov. 1997.
[70] Nastar C, Ayache N.Frequency-based non-rigid motion analysis.IEEE Trans Pattern Anal and Mach Intell,1996,18(11): 1067～1079.
[71] 赖剑煌，颜鑫弘，邓东皋，完善频谱脸人像识别的分类器设计，中国图像图形学报，2002，No．5，Vol．7(A)．
[72] M.Ladesetal.IEEE Trans.Computer, 1993,42:300-311.
[72] J.Zhang etal. Proc. IEEE, 1997,85:1423-1435.
[74] L.Wiskott. Pattern Recognition, 1997,30:837-846.
[75] L.Wiskottetal. IEEE Trans. PAMI, 1997,19:775-779.
[76] C.Nastaretal. Computer Vision and Image Understanding, 1997,65:179-191.
[77] B.Moghaddametal. CVPR, 1996.
[78] A.Lanitisetal. Image&Vision Computing, 1995,13:393-401.
[39] A.Lanitisetal. IEEE Trans. PAMI, 1997,19:743-756.
[80] D.Valentinetal. Pattern Recognition, 1994, 27:1209-1230.
[81] N.Intrator, Reisfeld, Y. Yeshurun. PR Letters, 1996, 17:67-76.
[82] S.Y. Lee etal. Pattern Recognition, 1996,29:1863-1876.
[83] S.Lawrence etal. IEEE Trans. NN, 1997,8:98-113.
[84] Y. Dal, Y. Nakano. Pattern Recognition, 1998,31:159-167.
[85] S.Gutta, H. Wechaler. Pattern Recognition, 1997, 30:539-553。
[86] P.J。Phillips. IEEE Tans. Image Processing, 1998,7:1150-1164.
[87] C.Y. Lu etal. ICNNB, 1998,645-648.
[88] 金忠．人脸图像的自动校准算法．数据采集与处理，1999，14(2)：171-174
[89] 王宪保，王辛刚，冯浩，王守觉．基于面部器官的人脸特征提取方法．第一次神经网络与计算智能学术会议，杭州，2002(10)：250-254．
[90] 徐兆涵，王辛刚，冯浩，王守觉，一种人脸识别中寻找图像结构对称性的快速算法．第一次神经网络与计算智能学术会议，杭州，2002(10)：255-259．
[91] 邵虹，徐全生，崔文成．基于即神经网络的人脸图像识别方法的研究．沈阳工业大学学报，2000(8)，Vol 22，No．4．
[92] 张悦，周春光．基于径向基函数网络人脸识别的研究．系统仿真学报，2001(11)，Vol．13 Suppl．
[93] 陈刚，戚飞虎．基于差别特征的神经网络人脸识别．计算机工程，2000(8)，Vol．26，No．8．
[94] 赵振宇，徐用懋．模糊理论与神经网络的基础与应用．清华大学出版社，1996。
[95] W.S.McCulloch, and W. Pitts. A logic Calculus of the Ideas Imminent in Nerves Activity"[J].Bulletin of Mathematical Biophysics, 1943,5:115-133.
[96] 王守觉，李兆渊．通用神经网络硬件中神经元基本数学模型的讨论．电子学报，2001，Vol．29，No．5：276-280．
[97] M.A.Cohen, and S. Grossberg. Absolute Stability of global Pattern Formation and Parallel Memory Storage by Competitive Neural Networks. [J] IEEE Trans. Syst. Man Cybern, 1983,SMC-13: 815-826.
[98] R.LHardy. Multiquadric equations of topography and other irregular surfaces. [J] J.Grephys. Res., Vol.76:1905-1915.
[99] M.J.D.Powell. Radial basis functions for multivariable interpolation: A review, [A] in J.C.Mason and M.G.Cox, editors, Algorithms for Approximation. Clarendon Press,
Oxford, 1987.
[100] 王守觉．仿生模式识别(拓扑模式识别)—一种模式识别新模型的理论与应用．电子学报，2002，Vol．30，No．10．
[101] Ryszard Engelking. Dimension Theory [M], PWM-Polish Scientific Publishers-Warszawa, 1978.