人脸自动识别技术的研究与实现
|
摘要
随着社会的发展，信息化程度的不断提高，各个方面对快速有效的自动身份验证的要求日益迫切。由于生物特征是人的内在属性，具有很强的自身稳定性和个体差异性，因此它是身份验证的最理想依据。利用人脸特征进行身份验证又是最自然直接的手段，人脸相比其它人体生物特征它具有直接、友好、方便的特点，由此人脸自动识别成为身份验证的研究热点。
人脸识别技术有着广泛的应用背景。人脸自动识别系统可应用于公安系统的罪犯身份识别、驾驶执照及护照等证件照片与实际持证人的核对、银行及海关的监控系统及一些保密单位的自动门卫系统等。此外，人脸识别技术在信息安全领域也有着巨大的潜在应用价值。可以进行计算机的安全登录控制、应用程序安全使用、数据库安全访问和文件加密，还可以保护电子商务的安全性，还可用于图像库检索，在大型人脸库中检索与索引图像相同或相近的脸像。美国遭遇恐怖袭击后，这一技术引起更广泛关注。作为最容易隐蔽使用的识别技术，人脸识别成为当今国际反恐和安全防范最重要的手段之一。
本课题主要研究目标是人脸自动识别系统的实现。人脸自动识别系统包括人脸的检测、特征提取、人脸识别三个部分。人脸的检测和定位，即首先从输入图像中找到人脸及人脸存在的位置，并将人脸从背景中分割出来；然后对归一化的人脸图像进行特征提取，有效的抽取识别特征是人脸识别的关键；最后，进行人脸识别。人脸识别是指对给定的包含人脸的输入图像，通过与已知人脸库中存储的模型进行匹配比较，确定是否是库中某一人物，如果是，则给出最佳匹配库中人物。就可以实现自动识别人脸的目的。
With the development of society and the degree of society information improving rapidly, in all aspects the demand for effective automatic identity verification is increasingly urgent. The biological characteristics are the human inherent attributes, which have very strong stability and individual difference, so it is the most ideal basis of identity verification. Make use of the human face characteristics to carry on the identity verification is the most natural and direct means, Comparing with other the human biological characteristics it has direct, friendly and convenient characteristics, therefore automatic human face recognition becomes the research focus of the identity verification.
Human face recognition technology has extensive application backgrounds. Automatic human face recognition system can be applied for criminal identity verification of public security system, check certificate photo with holder , such as driving license and passport ,etc, and the Monitoring system of bank and the customs and the automatic entrance guard systems etc. In addition, human face recognition technology has enormous potential application value in the field of information safety. Human face recognition technology can carry on security log-in controlling, application program using safely, database visiting safely and file encryption of the computer. It can also protect the security of e-commerce, and search the picture storehouse, searching the same as or close face among large-scale human face storehouse. After American is attacked by terrorists, this technology causes more extensive concern. As an easy concealing recognition technology, human face recognition nowadays
becomes international anti-terrorism and one of the most important means of safe precaution. The main goal of this subject is realization of the automatic human face recognition system.
The automatic human face recognition system includes face detection, feature extraction and face recognition, face location and face detection at first find human face and the position from inputting picture in face storehouse, cut apart human face from the background; Then human face picture in normalization carry on feature extraction. Effectively extracting recognition feature is the key of human face recognition; finally, carrying on the face recognition. To giving
the introduction picture which includes the human faces human face recognition technology is compared with and match known human face model that stored in the face storehouse, confirming whether it is one person in the storehouse or not, if yes, providing the best matching person in the storehouse can realize the purpose of human face recognition automatically.
人脸识别技术有着广泛的应用背景。人脸自动识别系统可应用于公安系统的罪犯身份识别、驾驶执照及护照等证件照片与实际持证人的核对、银行及海关的监控系统及一些保密单位的自动门卫系统等。此外，人脸识别技术在信息安全领域也有着巨大的潜在应用价值。可以进行计算机的安全登录控制、应用程序安全使用、数据库安全访问和文件加密，还可以保护电子商务的安全性，还可用于图像库检索，在大型人脸库中检索与索引图像相同或相近的脸像。美国遭遇恐怖袭击后，这一技术引起更广泛关注。作为最容易隐蔽使用的识别技术，人脸识别成为当今国际反恐和安全防范最重要的手段之一。
本课题主要研究目标是人脸自动识别系统的实现。人脸自动识别系统包括人脸的检测、特征提取、人脸识别三个部分。人脸的检测和定位，即首先从输入图像中找到人脸及人脸存在的位置，并将人脸从背景中分割出来；然后对归一化的人脸图像进行特征提取，有效的抽取识别特征是人脸识别的关键；最后，进行人脸识别。人脸识别是指对给定的包含人脸的输入图像，通过与已知人脸库中存储的模型进行匹配比较，确定是否是库中某一人物，如果是，则给出最佳匹配库中人物。就可以实现自动识别人脸的目的。
With the development of society and the degree of society information improving rapidly, in all aspects the demand for effective automatic identity verification is increasingly urgent. The biological characteristics are the human inherent attributes, which have very strong stability and individual difference, so it is the most ideal basis of identity verification. Make use of the human face characteristics to carry on the identity verification is the most natural and direct means, Comparing with other the human biological characteristics it has direct, friendly and convenient characteristics, therefore automatic human face recognition becomes the research focus of the identity verification.
Human face recognition technology has extensive application backgrounds. Automatic human face recognition system can be applied for criminal identity verification of public security system, check certificate photo with holder , such as driving license and passport ,etc, and the Monitoring system of bank and the customs and the automatic entrance guard systems etc. In addition, human face recognition technology has enormous potential application value in the field of information safety. Human face recognition technology can carry on security log-in controlling, application program using safely, database visiting safely and file encryption of the computer. It can also protect the security of e-commerce, and search the picture storehouse, searching the same as or close face among large-scale human face storehouse. After American is attacked by terrorists, this technology causes more extensive concern. As an easy concealing recognition technology, human face recognition nowadays
becomes international anti-terrorism and one of the most important means of safe precaution. The main goal of this subject is realization of the automatic human face recognition system.
The automatic human face recognition system includes face detection, feature extraction and face recognition, face location and face detection at first find human face and the position from inputting picture in face storehouse, cut apart human face from the background; Then human face picture in normalization carry on feature extraction. Effectively extracting recognition feature is the key of human face recognition; finally, carrying on the face recognition. To giving
the introduction picture which includes the human faces human face recognition technology is compared with and match known human face model that stored in the face storehouse, confirming whether it is one person in the storehouse or not, if yes, providing the best matching person in the storehouse can realize the purpose of human face recognition automatically.
引文
[1] 谭铁牛．现代身份鉴别新技术-生物特征识别技术[J]．中国基础科学．科学前沿．2000，(9)．4～10
[2] Ham F, Kobayashi H. State of the art in component development for interactive communication with humans[J]. Advanced Robotics, 1997, 11(6). 585～604
[3] Zhang Y J, Yao Y R He Y. Automatic face segmentation using color cues for coding typical videophone scenes[A]. In: Proceedings of SPIE, USA, 1997, 3024. 468～479
[4] 李刚，高政．人脸识别理论研究进展[J]．计算机与现代化．2003，(3)．1～6
[5] 周杰，卢春雨，张长水．人脸自动识别方法综述[J]．电子学报．2000，28(4)．102～106
[6] 张翠平，苏光大．人脸识别技术综述[J]．中国图象图形学报．2000，5A(11)．885～894
[7] BledsoeW W. The model method in facial recognition[M]. PanoranicResearch Inc,Palo,CA, 1966
[8] Kanade T.picture processing system by computer complex and recognition of human faces [R]. Dept. of Infirmation Science, Kyoto University.1973
[9] Samal A, Iyengar P A. Automatic recognition and analysis of human faces and facial expressions: A survey[J]. Pattern Recognition, 1992, 25 (1). 65～67
[10] Valentin D, Abdi H, O'Toole A J, Cottrell G W. Conectionist models of face processing: A survey[J]. Tattern Recognition, 1994, 27 (9). 1209～1230
[11] Chellappa R, Wilson C L, Sirohey S. Human and machine recognition of faces: A survey Proc[J].IEEE 1995, 83(5). 705～740
[12] Daugman J. Face and gesture recognition, overview[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, 19 (7). 675～676
[13] Grudin M A. On internal representations in face recognition systems[J]. Pattern Recognition. 2000, 33 (7). 1161～1177
[14] 章毓晋．中国图像工程及当前的几个研究热点[J]．计算机辅助设计与图像学学
报．2002，14(6)．492～493
[15] 周激流，张晔．人脸识别理论研究进展[J]．计算机辅助设计与图形学学报．1999，11(2)．180～184
[16] 梁路宏，艾海舟．人脸检测研究综述[J]．计算机学报．2002，25(5)．449～458
[17] Sung K, Poggio T. Example-based learning for view based human face detection[J]. IEEE Trans Pattern Analysis and Machine Intelligence. 1998, 20 (1). 39～51
[18] Lu X G, Zhou J, Zhang C S. A novel algorithm for rotated human face detection[A] In: proc IEEE Conference on Computer Vision and Pattern Recognition[C], Hilton Head Island, South Carolina, USA. 2000. 760～764
[19] 卢春雨，张长水，闻方等．基于区域特征的快速人脸检测法[J]．清华大学学报(自然科学版)．1999，39(1)．101～105
[20] 粱路宏，艾海舟，何克忠．基于多模版匹配的单人脸检测[J]．中国图象图形学报．1999，4A(10)．823～830
[21] Miao J, Yin B C, Wang K Q et al. A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template[J]. Pattern Recognition. 1999, 32 (10) 1237～1248
[22] 邢昕，汪孔桥，沈兰荪．基于器官跟踪的人脸实时跟踪方法[J]．电子学报．2000，28(6)．29～31
[23] 刘明宝，姚鸿勋，高文．彩色图像的实时人脸跟踪方法[J]．计算机学报．1998，21(6)．527～532
[24] Wang J G, Tan T N. A new face detection method based on shape information[J]. Pattern Recognition Letters. 2000, 21 (6-7). 463～471
[25] Yang M H, Kriegman D, Ahuja N, Detecting faces in images: Asurvey. IEEE Trans Pattern Analysis and Machine Intelligence. 2002, 24 (1). 34～58
[26] Terrillon J C, Ahirazi, M N, Fukamachi H et al. Comparative performance of
different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images. In: Proc Conference on Automatic Face and Gesture Recognition. Grenoble. France. 2000.54～61
[27] Jones M J, Rehg J M. Statistical color models with application to skin detection. In: Proc IEEE Conferince on Computer Vision and Pattern Recognition. Fort Collins. Colorado. 1999. 274～280
[28] Yoo T W, Oh I S. A fast algorithm for tracking human faces based on chromatic histograms[J]. Pattern Recognition Letters. 1999, 20(10). 967～978
[29] Wei G, Sethi I K. Face detection for image annotation[J]. Pattern Recognition Letters. 1999, 20(11-13). 1313～1321
[30] Abdel-Mottaleb M, Elgammal A. Face detection in complex environments from color images. In: Proc IEEE Conference on Images Processing. Kobe. Japan. 1999 (3). 622～626
[31] Karlekar J, Desai U B. Finding faces in color images using wavelet transform. In: Proc IEEE Conference on Image Analysis and Processing. Venice. Italy. 1999. 1085～1088
[32] Yang M H, Ahuja N. Detecting human faces in color images. In: Proc IEEE Conference on Image Processing. Chicago. 1998. 127～139
[33] Wu H Y, Chen Q, Yachida M. A fuzzy-theory-based face detector. In: Proc Conference on Pattern Recognition. Vienna. Austria. 1996(3). 406～410
[34] Wu H Y, Chen Q, Yachida M. Face detection from color inages using a fuzzy pattern matching method[J]. IEEE Trans Pattern Analysis and Machine Intelligence. 1999, 21 (6). 557～563
[35] Cai J, Goshtasby A. Detecting human faces in color image[J]. Image and Vision Computing. 1999, 18 (1). 63～75
[36] Garcia C, Zikos G, Tziritas G. Face detection in lolor images using wavelet packet analysis[A]. In: Proc Multimedia Computing and Systems[C]. Centro Affari Florence. Italy. 1999 (1). 703～708
[37] Ishii H, Fukumi M, Akamatsu N. Face detiction based on skin color information in visual scenes by neural networks[A]. In: Proc Systems. Man and Cyberetics[C]. Tokyo. Japan. 1999 (5). 350～355
[38] Zarit B D, Super B J, Quek F K H. Comparison of five color models in skin pixel classification[A] In: Proc Workshop on Recognition. Analysis and Tracking of Faces and Gestures in Real-time systems[C]. Corfu. Greece. 1999.58～63
[39] Craw I, Ellis H, Lishman J. Automatic extraction of face features[J]. Pattem Recognition Letters. 1987, 5(2). 183～187
[40] Yang G Z, Human T S. Human face detection in a complex background[J]. Pattern Recognition. 1994, 27(1).53～63
[41] Dai Y, Nakano Y. Face-texture model based on SGLD and its application in face detection in a color scene[J]. Pattern Recognition. 1996, 29 (6). 1007～1017
[42] Kouzani A Z, He F, Sammut K. Commonsense knowledge based face detection[A]. in: Proc Conference on Intelligent Engineering Systems[C]. Budapast. Hungary. 1997. 215～220
[43] Brunelli R, Poggio T. Face recognition in face recognition systems[J]. IEEE Transactions on PAMI. 1993, 15 (10). 1042～1052
[44] Nefian A, Hayes M. Hidden Markov models for face recognition[A]. IEEE International Conference on Acoustics. Speech and Signals Processings[C]. Seattle. Washington. 1998, (5). 2721～2724
[45] Flming M, Cottrell G. Categorization of faces using unsupervised feature extraction[A]. Proceeding of the International Conference on Neural Networks[C]. California Univ San Diego CA USA. 1990.65～70
[46] Intrator N, Reisfeld D, Yeshurun Y. Face recognition by supervised/unsupervised hybrid network[J]. IEEE Transactions on Neural Networks. 1999. 3265～3269
[47] Lawrence S, Giles C L, Tsoi A C et al. Face recognition: A convolutional neural network approach[J]. IEEE Transactions on Neural Networks. 1997, 8 (1) 98～113
[48] Lin S H, Kung S Y, Lin L J. Face recognition/detection by probabilistic decision-
based neural network[J]. IEEE Transactions on Neural Networks. 1997, 8 (1) 114～132
[49] Ricanek Karl Jr, Lebby gary L, Haywood Kirk. Hopfield like networks for pattern recognition with applications to face recognition[A]. Proceedings of the International Joint Conference on Neural Networks[C]. 1999. 3265～3269
[50] Wiskott L. Phantom faces for face analysis[J]. Pattern Recognition. 1997, 30 (6). 837～846
[51] Lee R, Liu J, Face recognition: elastic relation encoding and structural matching[A]. IEEE International Conference on Systems. Man and Cybernetics[C]. 1999.172～177
[52] Jia X, Nixon M S. Analysing front view face profiles for face recognition via the Walsh transform[J]. Pattern Recognition Letters. 1994, 15 (6) 551～558
[53] Lai J H. Face recognition using holistic Fourier invariant features[J]. Pattern Recognition. 2001, 34(1) 95～109
[54] Gordon G. Face recognition based on depth maps and surface Curva-true[A]. Proceedings of SPIE[C]. 1991, 1570. 234～247
[2] Ham F, Kobayashi H. State of the art in component development for interactive communication with humans[J]. Advanced Robotics, 1997, 11(6). 585～604
[3] Zhang Y J, Yao Y R He Y. Automatic face segmentation using color cues for coding typical videophone scenes[A]. In: Proceedings of SPIE, USA, 1997, 3024. 468～479
[4] 李刚，高政．人脸识别理论研究进展[J]．计算机与现代化．2003，(3)．1～6
[5] 周杰，卢春雨，张长水．人脸自动识别方法综述[J]．电子学报．2000，28(4)．102～106
[6] 张翠平，苏光大．人脸识别技术综述[J]．中国图象图形学报．2000，5A(11)．885～894
[7] BledsoeW W. The model method in facial recognition[M]. PanoranicResearch Inc,Palo,CA, 1966
[8] Kanade T.picture processing system by computer complex and recognition of human faces [R]. Dept. of Infirmation Science, Kyoto University.1973
[9] Samal A, Iyengar P A. Automatic recognition and analysis of human faces and facial expressions: A survey[J]. Pattern Recognition, 1992, 25 (1). 65～67
[10] Valentin D, Abdi H, O'Toole A J, Cottrell G W. Conectionist models of face processing: A survey[J]. Tattern Recognition, 1994, 27 (9). 1209～1230
[11] Chellappa R, Wilson C L, Sirohey S. Human and machine recognition of faces: A survey Proc[J].IEEE 1995, 83(5). 705～740
[12] Daugman J. Face and gesture recognition, overview[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, 19 (7). 675～676
[13] Grudin M A. On internal representations in face recognition systems[J]. Pattern Recognition. 2000, 33 (7). 1161～1177
[14] 章毓晋．中国图像工程及当前的几个研究热点[J]．计算机辅助设计与图像学学
报．2002，14(6)．492～493
[15] 周激流，张晔．人脸识别理论研究进展[J]．计算机辅助设计与图形学学报．1999，11(2)．180～184
[16] 梁路宏，艾海舟．人脸检测研究综述[J]．计算机学报．2002，25(5)．449～458
[17] Sung K, Poggio T. Example-based learning for view based human face detection[J]. IEEE Trans Pattern Analysis and Machine Intelligence. 1998, 20 (1). 39～51
[18] Lu X G, Zhou J, Zhang C S. A novel algorithm for rotated human face detection[A] In: proc IEEE Conference on Computer Vision and Pattern Recognition[C], Hilton Head Island, South Carolina, USA. 2000. 760～764
[19] 卢春雨，张长水，闻方等．基于区域特征的快速人脸检测法[J]．清华大学学报(自然科学版)．1999，39(1)．101～105
[20] 粱路宏，艾海舟，何克忠．基于多模版匹配的单人脸检测[J]．中国图象图形学报．1999，4A(10)．823～830
[21] Miao J, Yin B C, Wang K Q et al. A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template[J]. Pattern Recognition. 1999, 32 (10) 1237～1248
[22] 邢昕，汪孔桥，沈兰荪．基于器官跟踪的人脸实时跟踪方法[J]．电子学报．2000，28(6)．29～31
[23] 刘明宝，姚鸿勋，高文．彩色图像的实时人脸跟踪方法[J]．计算机学报．1998，21(6)．527～532
[24] Wang J G, Tan T N. A new face detection method based on shape information[J]. Pattern Recognition Letters. 2000, 21 (6-7). 463～471
[25] Yang M H, Kriegman D, Ahuja N, Detecting faces in images: Asurvey. IEEE Trans Pattern Analysis and Machine Intelligence. 2002, 24 (1). 34～58
[26] Terrillon J C, Ahirazi, M N, Fukamachi H et al. Comparative performance of
different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images. In: Proc Conference on Automatic Face and Gesture Recognition. Grenoble. France. 2000.54～61
[27] Jones M J, Rehg J M. Statistical color models with application to skin detection. In: Proc IEEE Conferince on Computer Vision and Pattern Recognition. Fort Collins. Colorado. 1999. 274～280
[28] Yoo T W, Oh I S. A fast algorithm for tracking human faces based on chromatic histograms[J]. Pattern Recognition Letters. 1999, 20(10). 967～978
[29] Wei G, Sethi I K. Face detection for image annotation[J]. Pattern Recognition Letters. 1999, 20(11-13). 1313～1321
[30] Abdel-Mottaleb M, Elgammal A. Face detection in complex environments from color images. In: Proc IEEE Conference on Images Processing. Kobe. Japan. 1999 (3). 622～626
[31] Karlekar J, Desai U B. Finding faces in color images using wavelet transform. In: Proc IEEE Conference on Image Analysis and Processing. Venice. Italy. 1999. 1085～1088
[32] Yang M H, Ahuja N. Detecting human faces in color images. In: Proc IEEE Conference on Image Processing. Chicago. 1998. 127～139
[33] Wu H Y, Chen Q, Yachida M. A fuzzy-theory-based face detector. In: Proc Conference on Pattern Recognition. Vienna. Austria. 1996(3). 406～410
[34] Wu H Y, Chen Q, Yachida M. Face detection from color inages using a fuzzy pattern matching method[J]. IEEE Trans Pattern Analysis and Machine Intelligence. 1999, 21 (6). 557～563
[35] Cai J, Goshtasby A. Detecting human faces in color image[J]. Image and Vision Computing. 1999, 18 (1). 63～75
[36] Garcia C, Zikos G, Tziritas G. Face detection in lolor images using wavelet packet analysis[A]. In: Proc Multimedia Computing and Systems[C]. Centro Affari Florence. Italy. 1999 (1). 703～708
[37] Ishii H, Fukumi M, Akamatsu N. Face detiction based on skin color information in visual scenes by neural networks[A]. In: Proc Systems. Man and Cyberetics[C]. Tokyo. Japan. 1999 (5). 350～355
[38] Zarit B D, Super B J, Quek F K H. Comparison of five color models in skin pixel classification[A] In: Proc Workshop on Recognition. Analysis and Tracking of Faces and Gestures in Real-time systems[C]. Corfu. Greece. 1999.58～63
[39] Craw I, Ellis H, Lishman J. Automatic extraction of face features[J]. Pattem Recognition Letters. 1987, 5(2). 183～187
[40] Yang G Z, Human T S. Human face detection in a complex background[J]. Pattern Recognition. 1994, 27(1).53～63
[41] Dai Y, Nakano Y. Face-texture model based on SGLD and its application in face detection in a color scene[J]. Pattern Recognition. 1996, 29 (6). 1007～1017
[42] Kouzani A Z, He F, Sammut K. Commonsense knowledge based face detection[A]. in: Proc Conference on Intelligent Engineering Systems[C]. Budapast. Hungary. 1997. 215～220
[43] Brunelli R, Poggio T. Face recognition in face recognition systems[J]. IEEE Transactions on PAMI. 1993, 15 (10). 1042～1052
[44] Nefian A, Hayes M. Hidden Markov models for face recognition[A]. IEEE International Conference on Acoustics. Speech and Signals Processings[C]. Seattle. Washington. 1998, (5). 2721～2724
[45] Flming M, Cottrell G. Categorization of faces using unsupervised feature extraction[A]. Proceeding of the International Conference on Neural Networks[C]. California Univ San Diego CA USA. 1990.65～70
[46] Intrator N, Reisfeld D, Yeshurun Y. Face recognition by supervised/unsupervised hybrid network[J]. IEEE Transactions on Neural Networks. 1999. 3265～3269
[47] Lawrence S, Giles C L, Tsoi A C et al. Face recognition: A convolutional neural network approach[J]. IEEE Transactions on Neural Networks. 1997, 8 (1) 98～113
[48] Lin S H, Kung S Y, Lin L J. Face recognition/detection by probabilistic decision-
based neural network[J]. IEEE Transactions on Neural Networks. 1997, 8 (1) 114～132
[49] Ricanek Karl Jr, Lebby gary L, Haywood Kirk. Hopfield like networks for pattern recognition with applications to face recognition[A]. Proceedings of the International Joint Conference on Neural Networks[C]. 1999. 3265～3269
[50] Wiskott L. Phantom faces for face analysis[J]. Pattern Recognition. 1997, 30 (6). 837～846
[51] Lee R, Liu J, Face recognition: elastic relation encoding and structural matching[A]. IEEE International Conference on Systems. Man and Cybernetics[C]. 1999.172～177
[52] Jia X, Nixon M S. Analysing front view face profiles for face recognition via the Walsh transform[J]. Pattern Recognition Letters. 1994, 15 (6) 551～558
[53] Lai J H. Face recognition using holistic Fourier invariant features[J]. Pattern Recognition. 2001, 34(1) 95～109
[54] Gordon G. Face recognition based on depth maps and surface Curva-true[A]. Proceedings of SPIE[C]. 1991, 1570. 234～247