人脸识别技术在无人监考系统中的应用研究
|
摘要
用计算机进行人脸识别是当今的一个研究热点和难点。本文基于人脸识别算法并以VC++为平台,开发了一个无人监考系统。该系统首先从3台USB摄像头中实时采集考试人员的三个不同方位的正面人脸图像,从图像中检测到人脸区域,再对图像中的人眼进行几何定位,通过特征提取对图像进行降维之后再进行考试人员人脸确认。经实验验证本系统算法简单,眼睛定位准确,识别率较高,适用于无人监考系统。
本系统包括视频捕获模块,人脸检测模块,特征提取模块及人脸识别模块。论文首先介绍了几种常用的人脸识别方法,并对它们的优劣性进行了对比分析。再对各模块的实现进行了研究。
视频捕获利用了微软开发工具VC++提供的VFW(Video For Windows)数字视频软件包,它能够灵活的实现从模拟视频采集数字视频信号,并将其以BMP格式存储到文件中进行后续处理。在人脸检测时,文中首先利用直方图对采集到的图像灰度进行预处理,使图像变得清晰。再利用肤色模型进行肤色分割,将肤色与背景区分开来。最后利用眼睛具有脸部最大复杂度的特点找到眼睛的几何位置。鼻子的位置可根据眼睛的位置轻易地找到。由于通常得到的图像空间维数都非常高,为了对图像进行降维,文中详细介绍并使用了傅里叶变换方法。通过傅里叶变换对检测到的眼睛和鼻子进行特征提取,图像的维数大大降低,计算复杂度的降低使之可以很好地应用于实时系统。最后通过计算特征向量在空间中的几何关系进行人脸识别。
本课题最后完成了一个实时的无人监考系统,并通过实验对系统的性能进行了分析。实验证明该系统速度快、准确率高,对表情变化不敏感,具有较好的实用性。
The face recognition by computer is a hotspot and difficulty nowadays. This paper develops a non-invigilation exam system based on face recognition and VC++ platform. First, this system collects the examinee's front face image of different orientations from three USB cameras in real time. Detect the face area from the images and then locate the geometry position of eyes. At last, reduce the dimension of the image through face feature extraction to conform the face. The experimental result shows that this method is simple to realize, accurate to locate the eyes' position and has high recognition ratio. With the advantages mentioned above, it is fit with the non-invigilation exam system.
This system includes video capture module, the face detect module, the feature extraction module and the face recognition module. Firstly, this paper introduces some typical methods of face detection and face recognition, and analyzes their merits and demerits. Then the paper researches the realization of every module.
The video capture is using the VFW (Video For Windows) data video software package which is provided by the Microsoft development tool VC++. It could aquire data video signal flexibly from simulation video signal, and save images to file as BMP format for the later processing. During the face detection, the paper first preprocesses the gray of the collected images by histogram to make them clear. Then distinguish the face area from background area by the complexion module. Last, locate the eyes' geometry position based on the theory that the eyes have the maximum complexity on the face, and the nose's position could be acquired easily from the position of the eyes.
Usually, the space dimension of the image is high. In order to reduce the dimension, this paper particularly introduces and uses the Fourier transform. Through the transform to extract the feature of the detected eyes and nose, the dimension is reduced greatly. The reduction of the calculation complex make it fit for the real time system. At last, examinee face could be conformed through calculating the geometry relation of eigenvector in the space.
This paper finally completes a real time non-invigilation exam system, and analyzes the system capability by the experimental result. It proves that this system has rapid running time and high recognition ratio. And it has a thick skin to the change face and good practicability.
本系统包括视频捕获模块,人脸检测模块,特征提取模块及人脸识别模块。论文首先介绍了几种常用的人脸识别方法,并对它们的优劣性进行了对比分析。再对各模块的实现进行了研究。
视频捕获利用了微软开发工具VC++提供的VFW(Video For Windows)数字视频软件包,它能够灵活的实现从模拟视频采集数字视频信号,并将其以BMP格式存储到文件中进行后续处理。在人脸检测时,文中首先利用直方图对采集到的图像灰度进行预处理,使图像变得清晰。再利用肤色模型进行肤色分割,将肤色与背景区分开来。最后利用眼睛具有脸部最大复杂度的特点找到眼睛的几何位置。鼻子的位置可根据眼睛的位置轻易地找到。由于通常得到的图像空间维数都非常高,为了对图像进行降维,文中详细介绍并使用了傅里叶变换方法。通过傅里叶变换对检测到的眼睛和鼻子进行特征提取,图像的维数大大降低,计算复杂度的降低使之可以很好地应用于实时系统。最后通过计算特征向量在空间中的几何关系进行人脸识别。
本课题最后完成了一个实时的无人监考系统,并通过实验对系统的性能进行了分析。实验证明该系统速度快、准确率高,对表情变化不敏感,具有较好的实用性。
The face recognition by computer is a hotspot and difficulty nowadays. This paper develops a non-invigilation exam system based on face recognition and VC++ platform. First, this system collects the examinee's front face image of different orientations from three USB cameras in real time. Detect the face area from the images and then locate the geometry position of eyes. At last, reduce the dimension of the image through face feature extraction to conform the face. The experimental result shows that this method is simple to realize, accurate to locate the eyes' position and has high recognition ratio. With the advantages mentioned above, it is fit with the non-invigilation exam system.
This system includes video capture module, the face detect module, the feature extraction module and the face recognition module. Firstly, this paper introduces some typical methods of face detection and face recognition, and analyzes their merits and demerits. Then the paper researches the realization of every module.
The video capture is using the VFW (Video For Windows) data video software package which is provided by the Microsoft development tool VC++. It could aquire data video signal flexibly from simulation video signal, and save images to file as BMP format for the later processing. During the face detection, the paper first preprocesses the gray of the collected images by histogram to make them clear. Then distinguish the face area from background area by the complexion module. Last, locate the eyes' geometry position based on the theory that the eyes have the maximum complexity on the face, and the nose's position could be acquired easily from the position of the eyes.
Usually, the space dimension of the image is high. In order to reduce the dimension, this paper particularly introduces and uses the Fourier transform. Through the transform to extract the feature of the detected eyes and nose, the dimension is reduced greatly. The reduction of the calculation complex make it fit for the real time system. At last, examinee face could be conformed through calculating the geometry relation of eigenvector in the space.
This paper finally completes a real time non-invigilation exam system, and analyzes the system capability by the experimental result. It proves that this system has rapid running time and high recognition ratio. And it has a thick skin to the change face and good practicability.
引文
铩颷1]王宪保.基于仿生模式识别的人脸身份确认研究[D].杭州:浙江工业大学.2003.6,4-5
[2]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,1999,11:180-184
[3]Yang M.H.,Ahuja N.,Kriegman D..A survey on face detection methods[EB/OL].http://vision.aiuiuc.edu/mhyang/papers/survey.ps,gz,1999
[4]Moghaddam B,Jebara T,Pentland A.Bayesian Face Recognition[J].PatternRecognition Letters,2000,33(11):1771-1782
[5]Rowley H,Baluja S,Kanade T.Neural network-based face detection[J].IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(1):23-38
[6]Rowley H,Baluja S,Kanade T.Rotation invariant neural network-based facedetection[C],in Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition,Santa Barbara,California,USA,1998,963-969
[7]Roth D,Yang M-H,Ahuja N.A Snow-based face detector[C],in Advances in NeuralInformation Processing Systems 12,MIT Press,Cambridge,MA,2000,855-861
[8]Yang G Z,Huang T S.Human face detection in a complex background[J].PatternRecognition,1994,27(1):53-56
[9]Lv X.G.,Zhou J.,Zhang C.S..A novel algorithm for rotated human face detection[A].In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition[C].Hilton HeadIsland,South Carolina,USA,2000:760-764
[10]卢春雨.人脸自动识别若干问题研究与系统实现[D].清华大学博士论文,1998
[11]卢春雨,张长水,闻方,阎平凡.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
[12]梁路宏,艾海舟,何克忠.基于多匹配的单人脸检测[J].中国图像图形学报,1999,4(10):823-830
[13]Ai H.Z.,Liang L.H.,Xu G.Y..A general framework for face detection[R].3rd Conf.on Multimodal Interfaces,Lecture Notes in Computer Science,Vol.1948,Springer-Verlag,
2000:119-126
铩颷14]Mial J.,Yin B.C.,Wang K.Q.,et al.A hierachical multiscale and multiangle system forhuman face detection in a complex background using gravity-center template[J].Pattern Recongnition,1999,32(10):1237-1248
[15]刑昕,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
[16]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
[17]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
[18]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
[19]周激流,张晔,郭晶,等.基于活动轮廓模型的人脸特征提取方法的研究[J].中国图像图形学报,2000,5(4):341-344
[20]Kanade,T..Computer Recgnition of Human Faces[J].Birkhuser Verlag,Stuttgart,1977
[21]R.Brunelli,T.Poggio.Face recognition:features versus templates.IEEE Trans[A].onPattern Recognition and Machine Intelligence,1993,15(10):1042-1052
[22]A.Pentland,T.Choudhury.Face recognition for smart environments[J].IEEEComputer,2000:50-55
[23]J.Zhang,Y.Yan,M.Lades.Face recognition:eigenface,elastic matching and neuralnets[J].Proceedings of the IEEE,1997,85(9):1423-1435
[24]M.A.Turk.Interactive-time vision:face recognition as a visual behavior[J].PhDthesis,Massachusetts Institute of Technology,School of Architecture and Planning,September 1991
[25]Sire,T.Baker,S.,Bsat,M..The CMU pose,illumination,and expression database.IEEE Trans.Pattern Anal.Machine Intell,2003,25(12),1615-1618
[26]Riccio,D.,Nappi,M..Defering fange/domain comparisons in fractal imagecompression.In:Proc.12~(th)Internat.Conf.on Image Analysis and Processing,2003,Vol.1(September),412-417
铩颷27]W.Zhao,R.Chellappa,A.Rosenfeld and P.J.Phillips.Face recognition:aliteraturesurvey[R].CS-Tech Report-4167,University of Maryland,2000
[28]Http://www.cnl.salk.edu/～wiskott/Bibliographies/FaceCodingAnimation.html
[29]张翠平,苏光大.人脸识别技术综述[J].中国图像图形学报,2000,5(11):885-894
[30]Xu,C.,Wang,Y.,Tan,T.,Quan,L..[J].Depth vs.intensity:Which is more important forface recognition? Proc.17~(th)Internat.Conf.On Pattern Recognition(ICPR 2004),Vol.4(August),342-345.
[31]M.Lades,J.C.Vorbuggen,J.Buhmann,ect.Distortion invariant object recognition inthe dynamic link architecture[J].IEEE Trans.on Computers,1993,42(3):300-311
[32]P.S.Pencv,J.Atick.Local feature analysis:a general statistical theory for objectrepresentation[J].Net work:Computation in Neural System,1996,7(3):477-500
[33]M.Bichsel,A.P.Pentland.Human face recognition and the face image set' s topology[J].CVGIP:Image Understanding,1994,59:254-261
[34]G.Edwards,A.Lanitis,C.Taylor,t.Cootes.Statistical models of face images-improvingspecificity[N].In British Machine Vision Conference,Edinburgh,Scotland 1996,2:765-774
[35]I.Craw,N.Costen,T.Kato,S.Akamatsu.How should we represent faces for automaticrecognition[J].IEEE Trans.Pattern Analysis and Machine Intelligence[A].1999,21:725-736
[36]Z.M.Haled,M.D.Levine.Face recognition using the discrete cosine transform[J].International Journal of Computer Vision,2001,43(3):167-188
[37]Y.Liu,R.L.Weaver,K.Schmidt,N.Servan,J.Cohn..Facial asymmetry:a newbiometric[R].Technical Report of the Robotics Institute of CMU NO.CMU-RI-TR-01-23,2001
[38]X.Liu,Y.Chen,B.V.K.V.Kumar.Robust face authentication for multiple subjectsusing eigenflow[R].Technical Report of Advanced Multimedia processing Lab ofCMU,No.AMP 01-05,2001
[39]The 3D Face Database.http://www-users.cs.york.ac.uk/～ne/tomh.2003.
[40]O.Vel,S.Aeberhard.Face recognition under varying pose[J].1EEE Trans.on PatternAnalysis and Machine Intelligence[A],1999,21(10):1081-1088
铩颷41]S.Minut,S.Mahadevan,J Henderson,F.Dyer.Face recognition using foveal vision[R].Lecture Notes in Computer Science-LNCS 1811,2000:424-433
[42]M.Tistarelli,E.Grosso.Active vision-based face authentication[J].Image and VisionComputing,2000,18(4):299-314
[43]S.Y.Lee,Y.K.Ham,R.H.Park.Recognition of human front faces usingknowledge-based feature extraction and neuro-fuzzy algorithm[J].Pattern Recognition,1996,29(11):1863-1867
[44]Y.Dai,Y,Nakano.Recognition of facial images with low resolution using a Hopfieldmemory model[J].Pattern Recognition,1998,32(2):159-167
[45]P.J.Philips.Support vector machine applied to face recognition[J].Technical ReportNISTIR 6241,1999
[46]K.Jonsson,J.Kittler,Y.P Li,J.Matas.Support vector machines for face authentication.In Proceedings of British Machine Vision Conference[J],T.Pridmore and D.Elliman,Ed.,1999:543-553
[47]F.Samaria,S.Young.Hmm-based architecture for face identification[J].Image andVision Computing,1994,12(8):537-543
[48]C.Beunier,M.Acheroy.Automatic 3D face authention[J].Image and VisionComputing,2000,18(4):315-321
[49]P.W.Hallinan,G.G.Gordon,A.L.Yuille and et al.Two - and three-dimensional patternsof face[M].AK Peters Press,Natick Massachusetts,1999
[50]Face VACS homepage:http://.cognitec-systems.de/index.html
[51]BioID homepage:http://www.bioid.com
[52]FaceIt homepage:http://www.identix.com/products/pro_sdks_faceit_what.html
[53]ID2000 homepage:http://www.imagistechnologies.com/Product/ID2000SDK.htm
[54]FaceTools homepage:http://www.viisage.com/facetools.htm
[55]上海银晨智能识别科技有限公司:http://www.isvision.com
[56]广州超越软件公司:http://www.erercominc.com
[57]石长有.外貌特征与鉴别[M].警官教育出版社,1991
[58]Bruneli R.,Poggio T..Face recognition:features versus templates[J].IEEE Transactionson pattern analysis and macine intelligence,1993,15(10):1042-1052
铩颷59]Yullie A.,Hallinan P.,Cohen D..Feature exaction from faces using deformabletemplates[J].International Journal of Computing Vision,1992,8(2):99-111
[60]Youw K-C,Cipolla R.Feature-based human face detection[A].Image and VisionComputing,1997,15(9):713-735
[61]Kouzani A.Z.,He E,Sammut K..Commonsense knowledge-based face detection[J].In:Proc.Conf.on Intelligent Engineering Systems[A],Budapast,Hungary,1997:215-220
[62]Wu H.Y.,Chert Q.,Yachida M..A fuzzy-theory-based face detector.In:Proc.Conf.onPattern Recognition,Vienna,Austria,1996,3:406-410
[63]Kalekar J.,Desai U.B..Finding faces in color images using wavelet transform.In:Proc.IEEE Conf.on Image Analysis and Processing,Venice,Italy,1999:1085-1088
[64]马颂德,张正友.计算机视觉[M].科学出版社,1998
[65]M.Kirby,L.Sirovich.Application of the karhunen-loeve procedure for thecharacterization of human faces[J].IEEE Trans.On Pattern Analysis and MacineIntelligence,1990,12(1):103-108
[66]M.Turk,A.Pentland,Eigenfaces for recognition.J.Cognitive Neuroscience[J].1991,3(1):71-86
[67]王育坚.Visual C++面向对象编程教程[M].北京:清华大学出版社,2003,1-2
[68]刘袆玮.Visual C++视频/音频开发实用工程案例精选[M].北京:人民邮电出版社,2004.68-87
[69]何芳.应用Video For Window进行视频捕获的开发[M].智能多媒体,38-39
[70]黄福珍,苏剑波.人脸检测[M].上海交通大学出版社,2006,150-165
[71]杨淑莹.VC++图像处理程序设计(第二版)[M].清华大学出版社,北京.200,70
[72]苏彦华.Visual C++数字图像识别技术典型案例[M].求是科技,人民邮电出版社,2004.21-22
[73]Energy[C].Cambridge:IEEE Proceedings of the 5th international conference onComputer Vision(ICCV' 95),1995,360-367
[74]欧珊瑚,王倩丽,朱哲瑜.数字图像处理技术与应用[M],清华大学出版社,2004,183-186
[75]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[J]. 电子学报,2002.10,Vol.30,No.10
铩颷76]Vladimir N Vapnik著,张学工译.统计学习理论的本质[M].北京:清华大学出版社,12
[77]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
[78]王守觉,王柏南.人工神经网络的多维空间几何分析及其理论.电子学报,2002,30(1):1-4
[2]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,1999,11:180-184
[3]Yang M.H.,Ahuja N.,Kriegman D..A survey on face detection methods[EB/OL].http://vision.aiuiuc.edu/mhyang/papers/survey.ps,gz,1999
[4]Moghaddam B,Jebara T,Pentland A.Bayesian Face Recognition[J].PatternRecognition Letters,2000,33(11):1771-1782
[5]Rowley H,Baluja S,Kanade T.Neural network-based face detection[J].IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(1):23-38
[6]Rowley H,Baluja S,Kanade T.Rotation invariant neural network-based facedetection[C],in Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition,Santa Barbara,California,USA,1998,963-969
[7]Roth D,Yang M-H,Ahuja N.A Snow-based face detector[C],in Advances in NeuralInformation Processing Systems 12,MIT Press,Cambridge,MA,2000,855-861
[8]Yang G Z,Huang T S.Human face detection in a complex background[J].PatternRecognition,1994,27(1):53-56
[9]Lv X.G.,Zhou J.,Zhang C.S..A novel algorithm for rotated human face detection[A].In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition[C].Hilton HeadIsland,South Carolina,USA,2000:760-764
[10]卢春雨.人脸自动识别若干问题研究与系统实现[D].清华大学博士论文,1998
[11]卢春雨,张长水,闻方,阎平凡.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
[12]梁路宏,艾海舟,何克忠.基于多匹配的单人脸检测[J].中国图像图形学报,1999,4(10):823-830
[13]Ai H.Z.,Liang L.H.,Xu G.Y..A general framework for face detection[R].3rd Conf.on Multimodal Interfaces,Lecture Notes in Computer Science,Vol.1948,Springer-Verlag,
2000:119-126
铩颷14]Mial J.,Yin B.C.,Wang K.Q.,et al.A hierachical multiscale and multiangle system forhuman face detection in a complex background using gravity-center template[J].Pattern Recongnition,1999,32(10):1237-1248
[15]刑昕,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
[16]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
[17]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
[18]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
[19]周激流,张晔,郭晶,等.基于活动轮廓模型的人脸特征提取方法的研究[J].中国图像图形学报,2000,5(4):341-344
[20]Kanade,T..Computer Recgnition of Human Faces[J].Birkhuser Verlag,Stuttgart,1977
[21]R.Brunelli,T.Poggio.Face recognition:features versus templates.IEEE Trans[A].onPattern Recognition and Machine Intelligence,1993,15(10):1042-1052
[22]A.Pentland,T.Choudhury.Face recognition for smart environments[J].IEEEComputer,2000:50-55
[23]J.Zhang,Y.Yan,M.Lades.Face recognition:eigenface,elastic matching and neuralnets[J].Proceedings of the IEEE,1997,85(9):1423-1435
[24]M.A.Turk.Interactive-time vision:face recognition as a visual behavior[J].PhDthesis,Massachusetts Institute of Technology,School of Architecture and Planning,September 1991
[25]Sire,T.Baker,S.,Bsat,M..The CMU pose,illumination,and expression database.IEEE Trans.Pattern Anal.Machine Intell,2003,25(12),1615-1618
[26]Riccio,D.,Nappi,M..Defering fange/domain comparisons in fractal imagecompression.In:Proc.12~(th)Internat.Conf.on Image Analysis and Processing,2003,Vol.1(September),412-417
铩颷27]W.Zhao,R.Chellappa,A.Rosenfeld and P.J.Phillips.Face recognition:aliteraturesurvey[R].CS-Tech Report-4167,University of Maryland,2000
[28]Http://www.cnl.salk.edu/～wiskott/Bibliographies/FaceCodingAnimation.html
[29]张翠平,苏光大.人脸识别技术综述[J].中国图像图形学报,2000,5(11):885-894
[30]Xu,C.,Wang,Y.,Tan,T.,Quan,L..[J].Depth vs.intensity:Which is more important forface recognition? Proc.17~(th)Internat.Conf.On Pattern Recognition(ICPR 2004),Vol.4(August),342-345.
[31]M.Lades,J.C.Vorbuggen,J.Buhmann,ect.Distortion invariant object recognition inthe dynamic link architecture[J].IEEE Trans.on Computers,1993,42(3):300-311
[32]P.S.Pencv,J.Atick.Local feature analysis:a general statistical theory for objectrepresentation[J].Net work:Computation in Neural System,1996,7(3):477-500
[33]M.Bichsel,A.P.Pentland.Human face recognition and the face image set' s topology[J].CVGIP:Image Understanding,1994,59:254-261
[34]G.Edwards,A.Lanitis,C.Taylor,t.Cootes.Statistical models of face images-improvingspecificity[N].In British Machine Vision Conference,Edinburgh,Scotland 1996,2:765-774
[35]I.Craw,N.Costen,T.Kato,S.Akamatsu.How should we represent faces for automaticrecognition[J].IEEE Trans.Pattern Analysis and Machine Intelligence[A].1999,21:725-736
[36]Z.M.Haled,M.D.Levine.Face recognition using the discrete cosine transform[J].International Journal of Computer Vision,2001,43(3):167-188
[37]Y.Liu,R.L.Weaver,K.Schmidt,N.Servan,J.Cohn..Facial asymmetry:a newbiometric[R].Technical Report of the Robotics Institute of CMU NO.CMU-RI-TR-01-23,2001
[38]X.Liu,Y.Chen,B.V.K.V.Kumar.Robust face authentication for multiple subjectsusing eigenflow[R].Technical Report of Advanced Multimedia processing Lab ofCMU,No.AMP 01-05,2001
[39]The 3D Face Database.http://www-users.cs.york.ac.uk/～ne/tomh.2003.
[40]O.Vel,S.Aeberhard.Face recognition under varying pose[J].1EEE Trans.on PatternAnalysis and Machine Intelligence[A],1999,21(10):1081-1088
铩颷41]S.Minut,S.Mahadevan,J Henderson,F.Dyer.Face recognition using foveal vision[R].Lecture Notes in Computer Science-LNCS 1811,2000:424-433
[42]M.Tistarelli,E.Grosso.Active vision-based face authentication[J].Image and VisionComputing,2000,18(4):299-314
[43]S.Y.Lee,Y.K.Ham,R.H.Park.Recognition of human front faces usingknowledge-based feature extraction and neuro-fuzzy algorithm[J].Pattern Recognition,1996,29(11):1863-1867
[44]Y.Dai,Y,Nakano.Recognition of facial images with low resolution using a Hopfieldmemory model[J].Pattern Recognition,1998,32(2):159-167
[45]P.J.Philips.Support vector machine applied to face recognition[J].Technical ReportNISTIR 6241,1999
[46]K.Jonsson,J.Kittler,Y.P Li,J.Matas.Support vector machines for face authentication.In Proceedings of British Machine Vision Conference[J],T.Pridmore and D.Elliman,Ed.,1999:543-553
[47]F.Samaria,S.Young.Hmm-based architecture for face identification[J].Image andVision Computing,1994,12(8):537-543
[48]C.Beunier,M.Acheroy.Automatic 3D face authention[J].Image and VisionComputing,2000,18(4):315-321
[49]P.W.Hallinan,G.G.Gordon,A.L.Yuille and et al.Two - and three-dimensional patternsof face[M].AK Peters Press,Natick Massachusetts,1999
[50]Face VACS homepage:http://.cognitec-systems.de/index.html
[51]BioID homepage:http://www.bioid.com
[52]FaceIt homepage:http://www.identix.com/products/pro_sdks_faceit_what.html
[53]ID2000 homepage:http://www.imagistechnologies.com/Product/ID2000SDK.htm
[54]FaceTools homepage:http://www.viisage.com/facetools.htm
[55]上海银晨智能识别科技有限公司:http://www.isvision.com
[56]广州超越软件公司:http://www.erercominc.com
[57]石长有.外貌特征与鉴别[M].警官教育出版社,1991
[58]Bruneli R.,Poggio T..Face recognition:features versus templates[J].IEEE Transactionson pattern analysis and macine intelligence,1993,15(10):1042-1052
铩颷59]Yullie A.,Hallinan P.,Cohen D..Feature exaction from faces using deformabletemplates[J].International Journal of Computing Vision,1992,8(2):99-111
[60]Youw K-C,Cipolla R.Feature-based human face detection[A].Image and VisionComputing,1997,15(9):713-735
[61]Kouzani A.Z.,He E,Sammut K..Commonsense knowledge-based face detection[J].In:Proc.Conf.on Intelligent Engineering Systems[A],Budapast,Hungary,1997:215-220
[62]Wu H.Y.,Chert Q.,Yachida M..A fuzzy-theory-based face detector.In:Proc.Conf.onPattern Recognition,Vienna,Austria,1996,3:406-410
[63]Kalekar J.,Desai U.B..Finding faces in color images using wavelet transform.In:Proc.IEEE Conf.on Image Analysis and Processing,Venice,Italy,1999:1085-1088
[64]马颂德,张正友.计算机视觉[M].科学出版社,1998
[65]M.Kirby,L.Sirovich.Application of the karhunen-loeve procedure for thecharacterization of human faces[J].IEEE Trans.On Pattern Analysis and MacineIntelligence,1990,12(1):103-108
[66]M.Turk,A.Pentland,Eigenfaces for recognition.J.Cognitive Neuroscience[J].1991,3(1):71-86
[67]王育坚.Visual C++面向对象编程教程[M].北京:清华大学出版社,2003,1-2
[68]刘袆玮.Visual C++视频/音频开发实用工程案例精选[M].北京:人民邮电出版社,2004.68-87
[69]何芳.应用Video For Window进行视频捕获的开发[M].智能多媒体,38-39
[70]黄福珍,苏剑波.人脸检测[M].上海交通大学出版社,2006,150-165
[71]杨淑莹.VC++图像处理程序设计(第二版)[M].清华大学出版社,北京.200,70
[72]苏彦华.Visual C++数字图像识别技术典型案例[M].求是科技,人民邮电出版社,2004.21-22
[73]Energy[C].Cambridge:IEEE Proceedings of the 5th international conference onComputer Vision(ICCV' 95),1995,360-367
[74]欧珊瑚,王倩丽,朱哲瑜.数字图像处理技术与应用[M],清华大学出版社,2004,183-186
[75]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[J]. 电子学报,2002.10,Vol.30,No.10
铩颷76]Vladimir N Vapnik著,张学工译.统计学习理论的本质[M].北京:清华大学出版社,12
[77]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
[78]王守觉,王柏南.人工神经网络的多维空间几何分析及其理论.电子学报,2002,30(1):1-4