基于人脸整体特征的证—人判别方法研究
|
摘要
人像识别技术是一个极其复杂和困难的研究课题，它在网络安全、视频会议、人机智能交互等方面有着巨大的应用前景，因而人像识别技术成为当前模式识别和人工智能领域的一个研究热点。近二十年来涌现了各种不同的人脸识别方法和系统，但是并没有一个鲁棒性好，识别率高的识别系统在实际中得到应用。本文分析了这些方法的差异性，建立了一个基于子空间法的人脸识别方法研究环境。重点研究了基于PCA的人脸识别算法和基于Fisher线性判别的人脸识别算法，并将这两种子空间法合并为一个识别算法，对构成特征空间的特征向量个数的选择和不同的相似性度量方法进行了讨论，并提出了扩展维数法选择向量个数的方法。在实验的基础上比较了不同的识别方法和不同的度量方法对识别率的的影响，得出了一些有价值的结论。另外，本文还提出了基于仿射模板的人脸定位算法，实验结果证实了该算法的有效性。
Face recognition is a complex and difficult problem that is important for surveillance and security, telecommunications, digital libraries, and human-computer intelligent interactions,so it is one of the most active research field on Al and pattern recognition.Over the last twenty years different method have been proposed,but there is not a system in application which is robust and high in recognition rate.The difference of these methods is analysized in the paper and a test environment for face recognition is put up.The paper focuses on two basic methods , one is based on PCA algorithms and the other is based on Fisher discriminants These two subspace face recognition algorithms are combined into one in the paper, moreover,the number of eigenvectors used to create the eigenspace and the behavior of similarity measures are discussed and one method called stretching dimension is given to select eigenvectors.experiments are presented comparing recognition rates for different algorithms and different similarity measures. In addition, A method of face location based on affine template matching is presented,and experimental results show the method has good
performance.
Face recognition is a complex and difficult problem that is important for surveillance and security, telecommunications, digital libraries, and human-computer intelligent interactions,so it is one of the most active research field on Al and pattern recognition.Over the last twenty years different method have been proposed,but there is not a system in application which is robust and high in recognition rate.The difference of these methods is analysized in the paper and a test environment for face recognition is put up.The paper focuses on two basic methods , one is based on PCA algorithms and the other is based on Fisher discriminants These two subspace face recognition algorithms are combined into one in the paper, moreover,the number of eigenvectors used to create the eigenspace and the behavior of similarity measures are discussed and one method called stretching dimension is given to select eigenvectors.experiments are presented comparing recognition rates for different algorithms and different similarity measures. In addition, A method of face location based on affine template matching is presented,and experimental results show the method has good
performance.
引文
[1] Wechsler H, Philips P J,Bruce V et al,Face Recognition from Theory to Application,Berlin Heidelberg:Springer Verlag, 1998.402～411,537～546
[2] Samal A,Iyengar P A. Automatic recognition and analysis for human faces and facial expressions:A survey.Pattern Recognition,1992, 25:65～77
[3] Valentin D,et al.Connectionist models of face processing.Pattern Recognition,1994, 27:1209～1230
[4] 陈刚和戚飞虎，实用人脸识别系统的本征脸法实现，计算机研究与发展，2001，38(2)：170～174
[5] 周激流和张晔，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(2)
[6] Yang Y Z,Huang T S,Human face detection in a comples backgraoud,Pattern Recognotion,1994,27(1):705～63
[7] Dai Y,Nakano Y,Face-texture model based on SGLD and its applition in face dectection in a color scence,Pattern Recognition,1996,29(6):1007～1017
[8] Juelll P,Marsh R,A hierarchical neural network for human face detection,Pattern Recognition,1996,29(5),781～787
[9] 梁路宏，艾海舟等，基于多关联模板匹配的人脸检测，软件学报，2001，12(1)：94～109
[10] 梁路宏，艾海舟等，基于仿射模板匹配的多角度单人脸定位，计算机学报，2000，23(6)：640～645
[11] 梁路宏，艾海舟等，基于多模板匹配的单人脸检测，中国图象图形学报，1999，4(10)：825～829
[12] 卢春雨，张长水等，局域区域特征的快速人脸检测法，清华大学学报，1999，39(1)：101～105
[13] 彭震云，游素亚，徐光祐，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)：225～228
[14] 章高请，王申康等，基于特征曲线的自动人脸识别研究，软件学报，2000，11(3)372～378
[15] Goldstion R J,Harmon L D,Lesk A B,Man-machine interaction in human face identification,Bell Syst Tech Journal,1972, 51:399～427
[16] Kaya Y,Kobayashi K,A Basic Study on Human Recognition,In Frontiers of Pattern Recognition,New York:Academic,1971,265～289
[17] Sirovich L,Kirby M,Application of karhunen-loeve procedure for the characterization of human faces,IEEE Transactions on PAMI,1990,12(1):103～108
[18] Turk M,Pentland M,Eigenfaces for Recognition,J Cognitive Neurosci,1991,3(1):71～79
[19] Tistarelli M, Grosso E,Active face recognition with a hybrid approach,Pattern Recognition Letters,1997, (18):933～946
[20] Zhang Jun,Yan Yong.Lades M,Face recognition:eigenface,elastic matching,and neural nets, Proc of the IEEE,1997,85(9):1423～1435
[21] Foggia P,Sansone C,Multiclassification:Peject criteris for the Bayesian combiner, Pattern Recognition,1999,32:1435～1447
[22] 张辉，周洪祥，何振亚，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)：52～57
[23] Mase K,Recognition of facial expressions for optical flow,IEICE Transactions,Special Issue on Computer Vision and its Application,E,1991,74(10):3474～3483
[24] Rosenblum M,Yacoob Y,Davis L,Human emotion recognition from motion using aradial basis function network architecture,Proceedings of the IEEE workshop on Motion of Nonrigid and Articulated Objects,Austin,TX,1994,43～49
[25] Essa I A,Pentland A P,Coding,analysis,interpretation,and recognition of facial expressions,MIT Media Laboratory:Perceptual Computing Section Technical Report 325,1995
[26] 金辉，高文，人脸面部混合表情识别系统，计算机学报，2000，23(6)：602～608
[27] 高文，金辉，面部表情的分析与识别，计算机学报，1997，20(9)：782～789
[28] Allen A L,Personal Descriptions,Lodon:Butterworth,1950
[29] Parke F I,Computer Generated Animation of Faces,In:Proceedings ACM ann Conference 1972,1:451～457
[30] Kanad T,Picture processing system by computer and recognition of human face [Ph D Dissertation,Kyoto: Kyoto University,1973
[31] W Bledsoe,Man-machine facial recognition,Panoramic Research Inc,Palo Alto,CA,1996,Rep PRI:22
[32] 郭跃飞和杨靖宇，求解广义最佳鉴别矢量集的一种迭代算法及人脸识别，计算机学报，2000, 23(11):1189～1195
[33] 孙兴华，郭跃飞，杨靖宇，求解广义最佳鉴别矢量集的一种改进算法，中国图象图形学报，2000，5(11)：895～900
[34] Hong Ziquan,Algebraic feature extraction of image for recognition,Patternecognition,1991,24(3):211～219
[35] Lades M,Vorbuggen J,Buhmann J,Distortion invariant object recognition in the dynamic link architecture,IEEE trans.On Computer,1991,42(3):300～311
[36] 艾海舟，王栓和何克忠，基于差分图像的人脸检测，中国图象图形学报，1998，3(12)：987～992
[37] 程云鹏，矩阵论，西北工业大学出版社，1999
[38] Moon H.and Phillips J.,Analysis of PCA-based Faced Recognition Algorithms, In Boyer K.and Phillips J.,editors,Empirical Evaluation Techniques In Computer Vision, IEEE Computer Society Press, Los Alamitos,CA, 1998.
[39] 边肇祺，张学工等编，模式识别，清华大学出版社，2000
[40] 余松熠，周源华等编，数字图像处理，电子工业出版社，1989
[2] Samal A,Iyengar P A. Automatic recognition and analysis for human faces and facial expressions:A survey.Pattern Recognition,1992, 25:65～77
[3] Valentin D,et al.Connectionist models of face processing.Pattern Recognition,1994, 27:1209～1230
[4] 陈刚和戚飞虎，实用人脸识别系统的本征脸法实现，计算机研究与发展，2001，38(2)：170～174
[5] 周激流和张晔，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(2)
[6] Yang Y Z,Huang T S,Human face detection in a comples backgraoud,Pattern Recognotion,1994,27(1):705～63
[7] Dai Y,Nakano Y,Face-texture model based on SGLD and its applition in face dectection in a color scence,Pattern Recognition,1996,29(6):1007～1017
[8] Juelll P,Marsh R,A hierarchical neural network for human face detection,Pattern Recognition,1996,29(5),781～787
[9] 梁路宏，艾海舟等，基于多关联模板匹配的人脸检测，软件学报，2001，12(1)：94～109
[10] 梁路宏，艾海舟等，基于仿射模板匹配的多角度单人脸定位，计算机学报，2000，23(6)：640～645
[11] 梁路宏，艾海舟等，基于多模板匹配的单人脸检测，中国图象图形学报，1999，4(10)：825～829
[12] 卢春雨，张长水等，局域区域特征的快速人脸检测法，清华大学学报，1999，39(1)：101～105
[13] 彭震云，游素亚，徐光祐，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)：225～228
[14] 章高请，王申康等，基于特征曲线的自动人脸识别研究，软件学报，2000，11(3)372～378
[15] Goldstion R J,Harmon L D,Lesk A B,Man-machine interaction in human face identification,Bell Syst Tech Journal,1972, 51:399～427
[16] Kaya Y,Kobayashi K,A Basic Study on Human Recognition,In Frontiers of Pattern Recognition,New York:Academic,1971,265～289
[17] Sirovich L,Kirby M,Application of karhunen-loeve procedure for the characterization of human faces,IEEE Transactions on PAMI,1990,12(1):103～108
[18] Turk M,Pentland M,Eigenfaces for Recognition,J Cognitive Neurosci,1991,3(1):71～79
[19] Tistarelli M, Grosso E,Active face recognition with a hybrid approach,Pattern Recognition Letters,1997, (18):933～946
[20] Zhang Jun,Yan Yong.Lades M,Face recognition:eigenface,elastic matching,and neural nets, Proc of the IEEE,1997,85(9):1423～1435
[21] Foggia P,Sansone C,Multiclassification:Peject criteris for the Bayesian combiner, Pattern Recognition,1999,32:1435～1447
[22] 张辉，周洪祥，何振亚，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)：52～57
[23] Mase K,Recognition of facial expressions for optical flow,IEICE Transactions,Special Issue on Computer Vision and its Application,E,1991,74(10):3474～3483
[24] Rosenblum M,Yacoob Y,Davis L,Human emotion recognition from motion using aradial basis function network architecture,Proceedings of the IEEE workshop on Motion of Nonrigid and Articulated Objects,Austin,TX,1994,43～49
[25] Essa I A,Pentland A P,Coding,analysis,interpretation,and recognition of facial expressions,MIT Media Laboratory:Perceptual Computing Section Technical Report 325,1995
[26] 金辉，高文，人脸面部混合表情识别系统，计算机学报，2000，23(6)：602～608
[27] 高文，金辉，面部表情的分析与识别，计算机学报，1997，20(9)：782～789
[28] Allen A L,Personal Descriptions,Lodon:Butterworth,1950
[29] Parke F I,Computer Generated Animation of Faces,In:Proceedings ACM ann Conference 1972,1:451～457
[30] Kanad T,Picture processing system by computer and recognition of human face [Ph D Dissertation,Kyoto: Kyoto University,1973
[31] W Bledsoe,Man-machine facial recognition,Panoramic Research Inc,Palo Alto,CA,1996,Rep PRI:22
[32] 郭跃飞和杨靖宇，求解广义最佳鉴别矢量集的一种迭代算法及人脸识别，计算机学报，2000, 23(11):1189～1195
[33] 孙兴华，郭跃飞，杨靖宇，求解广义最佳鉴别矢量集的一种改进算法，中国图象图形学报，2000，5(11)：895～900
[34] Hong Ziquan,Algebraic feature extraction of image for recognition,Patternecognition,1991,24(3):211～219
[35] Lades M,Vorbuggen J,Buhmann J,Distortion invariant object recognition in the dynamic link architecture,IEEE trans.On Computer,1991,42(3):300～311
[36] 艾海舟，王栓和何克忠，基于差分图像的人脸检测，中国图象图形学报，1998，3(12)：987～992
[37] 程云鹏，矩阵论，西北工业大学出版社，1999
[38] Moon H.and Phillips J.,Analysis of PCA-based Faced Recognition Algorithms, In Boyer K.and Phillips J.,editors,Empirical Evaluation Techniques In Computer Vision, IEEE Computer Society Press, Los Alamitos,CA, 1998.
[39] 边肇祺，张学工等编，模式识别，清华大学出版社，2000
[40] 余松熠，周源华等编，数字图像处理，电子工业出版社，1989