人脸的几何特征提取与查询
|
摘要
人脸识别在诸如身份识别和公安档案等方面有着十分重要的应用价值。进入90年代以来，国内外研究人脸识别的方法层出不穷，其中包括基于几何特征的方法、基于特征脸的方法、基于弹性模型的方法、基于局部特征的方法、和神经网络方法等等。本文论述了在微机上人脸图像自动识别系统的实现，采用的是基于几何特征的方法。具体包括人脸图像的预处理、人脸图像中眼睛、鼻子、嘴巴各部位的自动定位、人脸的特征提取以及人脸图像的识别等几大功能。人脸图像的预处理包括图像的灰度变换、二值化处理及图像的归一化。在二值化处理时，我们采用的是既可以优化图像质量，又可以完成对图像的二值化处理的二次边缘提取算法。图像的归一化包括图像裁剪和缩放，从而实现了图像的位置校准。在人脸的特征提取方面，本文选取了人眼、鼻子、嘴的大小和位置等十五个特征值，从而使识别的误差大大减小。该算法简单易行而且对人脸的尺寸、脸形、光照、背景复杂性等没有限制，适用于不同质量的图像。
在进行人脸识别时，先求待识别人脸与数据库中人脸图像的Euclidean距离，得出误差最小的前八幅图像，再分别求出待识别人脸与数据库中这八幅人脸图像的左眼睛(含眉毛)、右眼睛(含眉毛)、嘴巴所对应三个点集的最小距离。然后取这三个最小距离中的最大者作为Hausdorff距离进行匹配，所得误差最小者即为目标记录。
The face recognition may be applied in many fields such as identity recognition and public security document management. Since nineties, the methods of studying face recognition have emerged in endlessly, including geometry feature based method, characteristic face method, stretch model based method, local feature method and NN. This paper is about the realization of the automatic recognition system on facial images on computer. The system is based on geometry feature method. The system includes pre-processing of facial images, automatic location of the eye, nose and mouth ,and the character abstraction and recognition of face images. The pre-processing includes grey transformation binalization and unification. In binarization, we use the algorithm of the second brim abstraction with which we not only optimize the quality of the images but also finish the binarization. The unification, which realizes the position calibration of the images, includes cropping and zooming. In character abstraction of facial images, we choose fifteen characters which includes the size and position of eyes, nose, mouth, so that the error of the recognition is greatly reduced. The algorithm is simple and have no restrict to the size, shape, light and background of the face.
When the face recognition is proceeding,we first calculate the Euclidean distance of the facial image to be recognited and the facial images in database,and get the front eight images of the least error margin resemble,and then calculate the minimum distance of the three points gathering respectively of the left eye(contain the eyebrow),right eye(contain the eyebrow) and mouth between the facial image to be recognited and those eight images.Taking the biggest value of these three minimum distances as Hausdorff distance to match.the target record is the least error margin record.
在进行人脸识别时，先求待识别人脸与数据库中人脸图像的Euclidean距离，得出误差最小的前八幅图像，再分别求出待识别人脸与数据库中这八幅人脸图像的左眼睛(含眉毛)、右眼睛(含眉毛)、嘴巴所对应三个点集的最小距离。然后取这三个最小距离中的最大者作为Hausdorff距离进行匹配，所得误差最小者即为目标记录。
The face recognition may be applied in many fields such as identity recognition and public security document management. Since nineties, the methods of studying face recognition have emerged in endlessly, including geometry feature based method, characteristic face method, stretch model based method, local feature method and NN. This paper is about the realization of the automatic recognition system on facial images on computer. The system is based on geometry feature method. The system includes pre-processing of facial images, automatic location of the eye, nose and mouth ,and the character abstraction and recognition of face images. The pre-processing includes grey transformation binalization and unification. In binarization, we use the algorithm of the second brim abstraction with which we not only optimize the quality of the images but also finish the binarization. The unification, which realizes the position calibration of the images, includes cropping and zooming. In character abstraction of facial images, we choose fifteen characters which includes the size and position of eyes, nose, mouth, so that the error of the recognition is greatly reduced. The algorithm is simple and have no restrict to the size, shape, light and background of the face.
When the face recognition is proceeding,we first calculate the Euclidean distance of the facial image to be recognited and the facial images in database,and get the front eight images of the least error margin resemble,and then calculate the minimum distance of the three points gathering respectively of the left eye(contain the eyebrow),right eye(contain the eyebrow) and mouth between the facial image to be recognited and those eight images.Taking the biggest value of these three minimum distances as Hausdorff distance to match.the target record is the least error margin record.
引文
[1]王伟，马建光，人脸识别常用方法及其发展现状，自动检测技术2002，Vol．21，No．1
[2]张翠平，苏光大，人脸识别技术综述，中国图像图形学报，Vol．5(A)，No．11．Nov．2000
[3]浙江公安高等专科学校吴洪森，浙江大学计算机系王申康，机器自动人脸识别的研究和机器自动人脸识别技术的进展，文章收藏号：TP391．41
[4]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
[5]陈刚，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Vol．38，NO．2，Feb．2001
[6]甘俊英，黄宇明，用于人脸识别的人脸图像标准化算法，五邑大学学报(自然科学版)，Vol．16，No．2，June．2002
[7]王光辉，梁毅军，贺朋令，人脸识别中的眼睛定位，信号处理Vol．15，Dec．1999
[8]杜平，张燕昆，刘重庆，基于不变矩的人脸识别方法的研究，计算机仿真，Vol．19，No．3，May．2002
[9]郭宝峰，Hausdorff距离和小波分析在人脸识别中的应用，中国科学院博士学位论文，2001
[10]鲁秀青，人脸的特征提取与查询，硕士学位论文，山东大学，2001
[11]刘小军，人脸识别技术研究，中国科学院电子所博士学位论文，2001
[12]王宏伟，人脸识别技术的研究与应用，浙江大学硕士学位论文，2002
[13]李华胜，杨桦，袁保宗，人脸识别系统中的特征提取，北方交通大学学报，Vol．25，No．2，Apri．2001
[14]张林，胡波，凌燮亭，基于主元分析和Fuzzy ART模型的人脸识别算法，电路与系统学报，Vol．4，No．3，Sep．1999
[15]Tony Jebara, "Action-Reaction Learning:Analysis and Synthesis of Human Behaviour" MIT Media Laboratory, Perceptual Computing Technical Report #507
[16]Roberto Brunelli and Tomaso Poggio,"Face Recognition:Features vers-us Templates" IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,Vol.15, No.10, OCTOBER1993
[17]Jocelyn Scheirer, Raul Fernandez and Rosalind W. Picard, "Expression Glasses: A Wearable Device for Facial Expression Recognition" in M.I.T Media Laboratory Perceptual Computing Section Technical Report No.484, Submitted to CHI99
[18]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(2)
[19]姜军，张桂林，一种基于知识快速人脸检测方法．华中科技大学图像识别与人工智能研究所图像信息处理与智能控制国家教育部开放实验室，中国图像图形学报，2002．7(1)
[20]丁嵘，苏光大，特征脸和弹性匹配人脸识别算法的比较，计算机工程与应用，2002．38(7)．-1-2，19
[21]R.Brunelli and T.Poggio, "Face recognition:features versus templates", IEEE Trans. Pattern Analysis and Machine Intelligence,vol.15,no.10,pp.1042-1052,Oct.1993.
[22]K.M.Lam and H.Yan, "An analytic-to-holistic approach for face recogni-tion based on a single front view" ,IEEE Trans. Pattern Analysis and Ma-chine Intelligence,vol.20,no.7,pp.673-686,1998.
[23]M.Turk and A.Pentland, "Eigenfaces for Recognition",Journal of Cognitive Neuroscience,vol. 3,no. 1 ,pp.81-86,1991.
[24]J.Zhang,Y.Yan and M.Lades, "Face recognition:eigenface,elastic matching,and neural nets",Proceedings of the IEEE,vol.85,no.9,pp.1423-1435,Sept.1997.
[25]Maxim Arnoldovich Grudin, "A Compact Multi-Level Model for the Recognition of Facial Images" ,A thesis submitted in partial fulfillment of the requirements of Liverpool John Moores University for the Degree of Doctor of Philosophy, November 1997.
[26]Wiskott, L.;Fellous,J-M.;Kuiger, N.;von der Malsburg,C., "Face recognition by elastic bunch graph matching" IEEE Transactions on Pattern Analysi-s and Machine Intelligence,Volume:197,July1997,Page(s):775-779
[27]Lades, M.;Vorbruggen,J.C.;Buhmann,J.;Lange,J. ;von der Malsburg,C. ;Wurtz,R.P.;Konen,W, "Distortion invariant object recognition in the dynamic li-nk architecture" ,IEEE Transactions on Computers,Volume:423,March 1993,Pa-ge(s):300-311
[28]F.Samaria, "Face recognition using Hidden Marklv Models" ,A PH.D.Dissertation at the University of Cambridge,Oct1994.
[29]P.Belhumeur, J.Hespanha,and D.Kriegman, "Eigenfaces vs.fisherfaces:recognition using class specific linear projection" ,IEEE Trans. Pattern Analysis and Machine Intelligence,vol.19,no.7,pp.711-720,1997.
[30]G.W.Cottrell and M.Fleming, "Face recognition using unsupervised feature extraction," Proc.Int.Neural Network Conf in signal processing,and di-gital communications,vol. 1 ,Paris,France,July9-13,1990,pp.322-325.
[31]孙家广等编著，计算机图形学(第三版)，清华大学出版社，2000
[32]孙兆林编著，MATLAB 6-X图像处理，清华大学出版社，2002
[2]张翠平，苏光大，人脸识别技术综述，中国图像图形学报，Vol．5(A)，No．11．Nov．2000
[3]浙江公安高等专科学校吴洪森，浙江大学计算机系王申康，机器自动人脸识别的研究和机器自动人脸识别技术的进展，文章收藏号：TP391．41
[4]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
[5]陈刚，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Vol．38，NO．2，Feb．2001
[6]甘俊英，黄宇明，用于人脸识别的人脸图像标准化算法，五邑大学学报(自然科学版)，Vol．16，No．2，June．2002
[7]王光辉，梁毅军，贺朋令，人脸识别中的眼睛定位，信号处理Vol．15，Dec．1999
[8]杜平，张燕昆，刘重庆，基于不变矩的人脸识别方法的研究，计算机仿真，Vol．19，No．3，May．2002
[9]郭宝峰，Hausdorff距离和小波分析在人脸识别中的应用，中国科学院博士学位论文，2001
[10]鲁秀青，人脸的特征提取与查询，硕士学位论文，山东大学，2001
[11]刘小军，人脸识别技术研究，中国科学院电子所博士学位论文，2001
[12]王宏伟，人脸识别技术的研究与应用，浙江大学硕士学位论文，2002
[13]李华胜，杨桦，袁保宗，人脸识别系统中的特征提取，北方交通大学学报，Vol．25，No．2，Apri．2001
[14]张林，胡波，凌燮亭，基于主元分析和Fuzzy ART模型的人脸识别算法，电路与系统学报，Vol．4，No．3，Sep．1999
[15]Tony Jebara, "Action-Reaction Learning:Analysis and Synthesis of Human Behaviour" MIT Media Laboratory, Perceptual Computing Technical Report #507
[16]Roberto Brunelli and Tomaso Poggio,"Face Recognition:Features vers-us Templates" IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,Vol.15, No.10, OCTOBER1993
[17]Jocelyn Scheirer, Raul Fernandez and Rosalind W. Picard, "Expression Glasses: A Wearable Device for Facial Expression Recognition" in M.I.T Media Laboratory Perceptual Computing Section Technical Report No.484, Submitted to CHI99
[18]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(2)
[19]姜军，张桂林，一种基于知识快速人脸检测方法．华中科技大学图像识别与人工智能研究所图像信息处理与智能控制国家教育部开放实验室，中国图像图形学报，2002．7(1)
[20]丁嵘，苏光大，特征脸和弹性匹配人脸识别算法的比较，计算机工程与应用，2002．38(7)．-1-2，19
[21]R.Brunelli and T.Poggio, "Face recognition:features versus templates", IEEE Trans. Pattern Analysis and Machine Intelligence,vol.15,no.10,pp.1042-1052,Oct.1993.
[22]K.M.Lam and H.Yan, "An analytic-to-holistic approach for face recogni-tion based on a single front view" ,IEEE Trans. Pattern Analysis and Ma-chine Intelligence,vol.20,no.7,pp.673-686,1998.
[23]M.Turk and A.Pentland, "Eigenfaces for Recognition",Journal of Cognitive Neuroscience,vol. 3,no. 1 ,pp.81-86,1991.
[24]J.Zhang,Y.Yan and M.Lades, "Face recognition:eigenface,elastic matching,and neural nets",Proceedings of the IEEE,vol.85,no.9,pp.1423-1435,Sept.1997.
[25]Maxim Arnoldovich Grudin, "A Compact Multi-Level Model for the Recognition of Facial Images" ,A thesis submitted in partial fulfillment of the requirements of Liverpool John Moores University for the Degree of Doctor of Philosophy, November 1997.
[26]Wiskott, L.;Fellous,J-M.;Kuiger, N.;von der Malsburg,C., "Face recognition by elastic bunch graph matching" IEEE Transactions on Pattern Analysi-s and Machine Intelligence,Volume:197,July1997,Page(s):775-779
[27]Lades, M.;Vorbruggen,J.C.;Buhmann,J.;Lange,J. ;von der Malsburg,C. ;Wurtz,R.P.;Konen,W, "Distortion invariant object recognition in the dynamic li-nk architecture" ,IEEE Transactions on Computers,Volume:423,March 1993,Pa-ge(s):300-311
[28]F.Samaria, "Face recognition using Hidden Marklv Models" ,A PH.D.Dissertation at the University of Cambridge,Oct1994.
[29]P.Belhumeur, J.Hespanha,and D.Kriegman, "Eigenfaces vs.fisherfaces:recognition using class specific linear projection" ,IEEE Trans. Pattern Analysis and Machine Intelligence,vol.19,no.7,pp.711-720,1997.
[30]G.W.Cottrell and M.Fleming, "Face recognition using unsupervised feature extraction," Proc.Int.Neural Network Conf in signal processing,and di-gital communications,vol. 1 ,Paris,France,July9-13,1990,pp.322-325.
[31]孙家广等编著，计算机图形学(第三版)，清华大学出版社，2000
[32]孙兆林编著，MATLAB 6-X图像处理，清华大学出版社，2002