人面部的代数特征与几何特征的提取及识别
|
摘要
基于生物特征的身份鉴定技术在社会生活中具有越来越重要的地位和作用。在多种生物特征中，基于人面部特征的识别和鉴定因为具有无侵害性、成本低、易于接受等优点，得到广泛的研究和应用。
本论文主要从人面部的代数特征和几何形状特征两个方面，探讨了人面部的特征提取和识别问题。
在代数特征方面，主要从主成分分析和独立成分分析两个角度出发，进行了探讨。主成分分析立足于图像的二阶统计特性，提取图像的灰度特征；它去除了各特征分量之间彼此的相关性，并且可以根据其对应的特征值的大小确定它在整个能量中占据的百分比，从而可以分离出信号中的主要成分和次要成分；独立成分分析从图像的高阶统计特性出发，提取图像的灰度特征。它的各特征分量之间彼此独立，由于不考虑主次关系，因此它难以清楚地反映信号各分量的主、次程度。考虑到这两种方法的不同特点，论文提出了主要独立成分分析方法，即在主成分分析的基础上，进一步做独立成分分析。通过这种方法得到的特征分量的均值、方差的分散性要优于仅做主成分分析的特征分量的均值、方差的分散性，因此聚类效果要更好一些。
对应于既定的特征选取，存在有一个最佳的相似性度量方法的选择问题。在考虑关于人脸的分类算法时，大多是评价分类算法对噪声样本的容错性，而忽视了特征空间维数的选取与相似性度量准则之间的关系。就特征空间选取问题，论文从理论上分析了最近邻法、支持向量机这两种方法的识别性能，由于支持向量机是通过类间超平面进行分类的，最近邻法是通过类间距离进行分类的，因此，论文认为，在一定程度上支持向量机更敏感于特征空间的变化，尤其是特征空间中的细节分量或噪声分量的变化，相比之下，在一定条件下，最近邻法对特征空间中的细节分量并不敏感。因此在论文所提出的人脸识别系统中，在较小的特征空间中支持向量机的识别效果要优于最近邻法。
在模式识别理论中，人脸识别是一种典型的多类判别问题。鉴于支持向量机是一种以两类判别为基本功能的分类函数，在用于多类判别时，本文提出的方案是以1-1判别策略为基础，根据各判别函数的分类间隔的差异对多个判别函数进行排序，对于“拒绝决策”的情形，则可利用判别函数间的冗余再判别来降低识别误差。这种基于支持向量机组的淘汰法对于每个判别函数的使用更加合理和具有选择性。
根据所选择的人脸的代数特征和支持向量机的分类性能，论文提出了一个脸像识别方法，即基于主成分分析对人脸图像进行降维，再用独立成分分析进行独立分量特征提取，最后基于SVM进行多类识别。该脸像识别方法在对ORL人脸图像库和自建的人脸图像库的测试实验中，识别率分别为97.5％、88.17％。
在几何形状特征方面，论文重点研究了人脸主要几何特征点的提取和脸
部主要器官的连续形状的提取。
在人脸几何特征点提取问题中，首先需要准确定位人脸的左右边界。基
于原有的灰度投影曲线定位算法，本论文进一步对原灰度图像做小波分解，
然后仅取垂直分量进行重建，再沿垂直方向做投影，可以对人脸的左右边界
进行更加精确的定位。
分形理论在图像处理中的应用表明，分维图像能够更加有效地抑制噪声，
并能够充分地反映图像纹理的变化。因此，在提取人脸的几何特征点时，采
用脸部图像的分形维数图像取代了传统的灰度图像或二值图像。
在提取面部轮廓及其主要器官的连续形状时，需要采用边缘检测与提取
等手段。
在传统的微分算子的基础上，论文提出了一种广义的计算图像灰度梯度
的方法一一自由差分运算。自由差分运算不仅是一些典型的微分算子的通用
描述，而且它突破了传统微分算子的模板运算模式，可以同时从图像的全局
区域、局部区域两个方面出发，沿若干个直线方向进行计算，以考察象素点
的边缘特征。它把对图像这种二维信号的微分计算转化成一维方式进行，计
算方向具有任意性，同时，便于采用多种手段对象素点的边缘性质进行分析，
使得多种边缘检测方法不再彼此独立，为信息的二次融合提供了可能性、方
便性。从对实际图像的测试效果来看，它也具有很好的抗噪性。把它与Snake
模型相结合，论文提出了正交型Snake模型。
从传统的Snake模型的思想出发，正交型Snake模型利用自由差分运算
的基本原理，通过在正交直线方向上计算灰度梯度，把轮廓变化的信息和图
像灰度变化的信息更紧密地联系在一起。在曲线的演化过程中，以基本多边
形为依托，以目标曲线的特征为指导，让轮廓的变化能够自适应于图像灰度
变化，使得所提取的轮廓曲线的特征不断地逼近目标曲线的特征。在对多种
图像的测试中，取得了比较理想的效果。传统的边缘提取算法是一个由底至
上的过程;传统的Snake模型是一个由上至下的过程，在这两类方法中，信
息处理的基本流程都是单向的;正交型Snake模型通过强调高层视觉和底层
信息之间的相互联系在曲线演化过程中的作用，使得信息的流动过程处于闭
环的状态。
基于正交型Snake模型，分别研究了脸部的轮廓、眼部和嘴部轮廓的提
取。在处理眼的轮廓时，根据眼所具有的独特的类圆特点，把沿正交?
Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. Among the features measured, facial feature identification and verification are gaining popularity and diverse applications for the reason that they are considered to be non-invasive, low cost, and natural biometric technologies.
The paper discusses facial feature extraction and recognition from two aspects ?algebraic and geometrical features.
The paper discusses the algebraic feature adopting principle component analysis (PCA) and independent component analysis (ICA) respectively. Principle component analysis extracts the image gray characteristics considering the second order moments, while independent component analysis accounts for higher order statistics and identifies the independent source component from their linear mixtures. Considering the differences between them, the paper proposes principle independent component analysis (PICA) that is doing ICA based on PCA. PICA can provide a more powerful classification data representation than PCA by comparing their means and variances.
The similarity measurement should match selected features. Most face classification approaches pay more attention to dealing with noise samples, but ignore the influence of selected feature space. Support vector machine (SVM) performs classification by the hyperplane between classes, while the nearest neighbor method (NN) performs classification by the distance between classes. The paper discusses the difference between NN and SVM, finds SVM is more sensitive to the feature space variation than NN, especially for details or noise component. SVM can get better recognition rate only depending on smaller feature space or less approximation components for face recognition.
Support vector machine is an advanced classifier, which has demonstrated high generalization capabilities; however, it was developed originally only for two-class classifying. The paper proposes a new multi-step approach to extend SVM capability dealing with the multi-class face recognition problem by incorporating with the elimination strategy. Based on the one-against-one strategy to classify, it sorts the discrimination functions according to their own Vapnik-Chervonenkis confidences and uses the redundancy among them to decrease the discrimination error for the rejecting decision case.
The paper proposes a face recognition approach considering the facial algebraic features and the SVMs's classification capability. It includes three basic parts: PCA ?for reducing dimensions, ICA ?for feature extraction and SVM ?for multi-classification. The face recognition experiments with ORL face database
and a compound database. The recognition rates are 97.5% and 88.17% respectively.
The paper discusses the geometric feature points extraction, face and its main parts contour extraction also.
It is needed locating the left and the right boundaries of face when extracting geometric feature points. Based on the ordinary intensity level vertical projection curve locating algorithm, the paper employees the reconstructed image by the vertical component of wavelet decomposition of the original image to locating more accurately.
The application of fractal theory in image processing shows that fractal image can suppress noise effectively, and reflect the variation of the texture enough. Therefore, the paper substitutes fractal image for intensity image or binary image.
The paper proposes the free difference operation, which is a new method computing the variation of gray level, based on the classical differential operators. Free difference operation is not only a general description of some typical differential operators, but also breaks the template mode of classical differential operators. By computing grey level variation along line direction, it considers each pixel feature in the range of the global and local region of image, not the image block or subimage. It has the advantage of simplicity, operational flexibility and better
本论文主要从人面部的代数特征和几何形状特征两个方面，探讨了人面部的特征提取和识别问题。
在代数特征方面，主要从主成分分析和独立成分分析两个角度出发，进行了探讨。主成分分析立足于图像的二阶统计特性，提取图像的灰度特征；它去除了各特征分量之间彼此的相关性，并且可以根据其对应的特征值的大小确定它在整个能量中占据的百分比，从而可以分离出信号中的主要成分和次要成分；独立成分分析从图像的高阶统计特性出发，提取图像的灰度特征。它的各特征分量之间彼此独立，由于不考虑主次关系，因此它难以清楚地反映信号各分量的主、次程度。考虑到这两种方法的不同特点，论文提出了主要独立成分分析方法，即在主成分分析的基础上，进一步做独立成分分析。通过这种方法得到的特征分量的均值、方差的分散性要优于仅做主成分分析的特征分量的均值、方差的分散性，因此聚类效果要更好一些。
对应于既定的特征选取，存在有一个最佳的相似性度量方法的选择问题。在考虑关于人脸的分类算法时，大多是评价分类算法对噪声样本的容错性，而忽视了特征空间维数的选取与相似性度量准则之间的关系。就特征空间选取问题，论文从理论上分析了最近邻法、支持向量机这两种方法的识别性能，由于支持向量机是通过类间超平面进行分类的，最近邻法是通过类间距离进行分类的，因此，论文认为，在一定程度上支持向量机更敏感于特征空间的变化，尤其是特征空间中的细节分量或噪声分量的变化，相比之下，在一定条件下，最近邻法对特征空间中的细节分量并不敏感。因此在论文所提出的人脸识别系统中，在较小的特征空间中支持向量机的识别效果要优于最近邻法。
在模式识别理论中，人脸识别是一种典型的多类判别问题。鉴于支持向量机是一种以两类判别为基本功能的分类函数，在用于多类判别时，本文提出的方案是以1-1判别策略为基础，根据各判别函数的分类间隔的差异对多个判别函数进行排序，对于“拒绝决策”的情形，则可利用判别函数间的冗余再判别来降低识别误差。这种基于支持向量机组的淘汰法对于每个判别函数的使用更加合理和具有选择性。
根据所选择的人脸的代数特征和支持向量机的分类性能，论文提出了一个脸像识别方法，即基于主成分分析对人脸图像进行降维，再用独立成分分析进行独立分量特征提取，最后基于SVM进行多类识别。该脸像识别方法在对ORL人脸图像库和自建的人脸图像库的测试实验中，识别率分别为97.5％、88.17％。
在几何形状特征方面，论文重点研究了人脸主要几何特征点的提取和脸
部主要器官的连续形状的提取。
在人脸几何特征点提取问题中，首先需要准确定位人脸的左右边界。基
于原有的灰度投影曲线定位算法，本论文进一步对原灰度图像做小波分解，
然后仅取垂直分量进行重建，再沿垂直方向做投影，可以对人脸的左右边界
进行更加精确的定位。
分形理论在图像处理中的应用表明，分维图像能够更加有效地抑制噪声，
并能够充分地反映图像纹理的变化。因此，在提取人脸的几何特征点时，采
用脸部图像的分形维数图像取代了传统的灰度图像或二值图像。
在提取面部轮廓及其主要器官的连续形状时，需要采用边缘检测与提取
等手段。
在传统的微分算子的基础上，论文提出了一种广义的计算图像灰度梯度
的方法一一自由差分运算。自由差分运算不仅是一些典型的微分算子的通用
描述，而且它突破了传统微分算子的模板运算模式，可以同时从图像的全局
区域、局部区域两个方面出发，沿若干个直线方向进行计算，以考察象素点
的边缘特征。它把对图像这种二维信号的微分计算转化成一维方式进行，计
算方向具有任意性，同时，便于采用多种手段对象素点的边缘性质进行分析，
使得多种边缘检测方法不再彼此独立，为信息的二次融合提供了可能性、方
便性。从对实际图像的测试效果来看，它也具有很好的抗噪性。把它与Snake
模型相结合，论文提出了正交型Snake模型。
从传统的Snake模型的思想出发，正交型Snake模型利用自由差分运算
的基本原理，通过在正交直线方向上计算灰度梯度，把轮廓变化的信息和图
像灰度变化的信息更紧密地联系在一起。在曲线的演化过程中，以基本多边
形为依托，以目标曲线的特征为指导，让轮廓的变化能够自适应于图像灰度
变化，使得所提取的轮廓曲线的特征不断地逼近目标曲线的特征。在对多种
图像的测试中，取得了比较理想的效果。传统的边缘提取算法是一个由底至
上的过程;传统的Snake模型是一个由上至下的过程，在这两类方法中，信
息处理的基本流程都是单向的;正交型Snake模型通过强调高层视觉和底层
信息之间的相互联系在曲线演化过程中的作用，使得信息的流动过程处于闭
环的状态。
基于正交型Snake模型，分别研究了脸部的轮廓、眼部和嘴部轮廓的提
取。在处理眼的轮廓时，根据眼所具有的独特的类圆特点，把沿正交?
Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. Among the features measured, facial feature identification and verification are gaining popularity and diverse applications for the reason that they are considered to be non-invasive, low cost, and natural biometric technologies.
The paper discusses facial feature extraction and recognition from two aspects ?algebraic and geometrical features.
The paper discusses the algebraic feature adopting principle component analysis (PCA) and independent component analysis (ICA) respectively. Principle component analysis extracts the image gray characteristics considering the second order moments, while independent component analysis accounts for higher order statistics and identifies the independent source component from their linear mixtures. Considering the differences between them, the paper proposes principle independent component analysis (PICA) that is doing ICA based on PCA. PICA can provide a more powerful classification data representation than PCA by comparing their means and variances.
The similarity measurement should match selected features. Most face classification approaches pay more attention to dealing with noise samples, but ignore the influence of selected feature space. Support vector machine (SVM) performs classification by the hyperplane between classes, while the nearest neighbor method (NN) performs classification by the distance between classes. The paper discusses the difference between NN and SVM, finds SVM is more sensitive to the feature space variation than NN, especially for details or noise component. SVM can get better recognition rate only depending on smaller feature space or less approximation components for face recognition.
Support vector machine is an advanced classifier, which has demonstrated high generalization capabilities; however, it was developed originally only for two-class classifying. The paper proposes a new multi-step approach to extend SVM capability dealing with the multi-class face recognition problem by incorporating with the elimination strategy. Based on the one-against-one strategy to classify, it sorts the discrimination functions according to their own Vapnik-Chervonenkis confidences and uses the redundancy among them to decrease the discrimination error for the rejecting decision case.
The paper proposes a face recognition approach considering the facial algebraic features and the SVMs's classification capability. It includes three basic parts: PCA ?for reducing dimensions, ICA ?for feature extraction and SVM ?for multi-classification. The face recognition experiments with ORL face database
and a compound database. The recognition rates are 97.5% and 88.17% respectively.
The paper discusses the geometric feature points extraction, face and its main parts contour extraction also.
It is needed locating the left and the right boundaries of face when extracting geometric feature points. Based on the ordinary intensity level vertical projection curve locating algorithm, the paper employees the reconstructed image by the vertical component of wavelet decomposition of the original image to locating more accurately.
The application of fractal theory in image processing shows that fractal image can suppress noise effectively, and reflect the variation of the texture enough. Therefore, the paper substitutes fractal image for intensity image or binary image.
The paper proposes the free difference operation, which is a new method computing the variation of gray level, based on the classical differential operators. Free difference operation is not only a general description of some typical differential operators, but also breaks the template mode of classical differential operators. By computing grey level variation along line direction, it considers each pixel feature in the range of the global and local region of image, not the image block or subimage. It has the advantage of simplicity, operational flexibility and better
引文
[1]王蕴红，朱勇，谭铁牛．基于虹膜识别的身份鉴别．自动化学报，2002，28(1)：1-10．
[2]http://www.21ppm.com.cn/htm/about/broadcast_0101_01.htm
[3]孙冬梅，裘正定．生物特征识别技术综述．电子学报，2001，29(12A)：1744-1748．
[4]J G Daugman. High confidence visual recognition of persons by a test of statistical independence. IEEE Trans. PAMI, 19 93, 13(11), 1148-1161.
[5]J G Daugman. Demodulation, predictive coding, and spatial vision. J. Opt. Soc. Am, 1995, 12(4):641-660.
[6]R P Wildes, et al. A machine vision system for iris recognition. Machine Vision Application, 1996,9:1-8.
[7]R P Wildes. Iris recognition: an emerging biometric technology. Proceedings of IEEE, 1997, 85(9):1348-1363.
[8]Wayne Madsen. Biometrics Marches Forward in US Government. Computer Fraud & Security. 2001(5):7-8.
[9]Dieckmann U., Plankensteiner P., Wagner T. SESAM: A biometric person identification system using sensor fusion. Pattern Recognition Letters, 1997,18(9):827-833.
[10]Kittler J., Matas J., Jonsson K., Sánchez M.U. Ramos. Combining evidence in personal identity verification systems. Pattern Recognition Letters, 1997,18(9):845-852.
[11]http://www. oss. com/products/vision. html.
[12]W. Zhao. Face recognition: A literature survey, http:// citeseer. nj. nec. com/cs. 2000.
[13]张翠平，苏光大．人脸识别技术综述．中国图象图形学报．2000，5(11A)：885—894．
[14]Grudin M A. Compact multi-level representation of human faces for recognition. Ph. D dissertation, Liverpool John Moores University, Nov. 1997.
[15]Kanwisher Nancy, Tong Frank, Nakayama Ken. The effect of face inversion on the human fusiform face area. Cognition, 1998, 68(1): B1-B11.
[16]Nastar C, Ayache N. Frequency-based non-rigid motion analys
is. IEEE Trans Pattern Anal and Mach Intell, 1996,18(11):1067-1079.
[17]Alex Pentland, Baback Moghadam, Thad Starner. View-based and modular eigenspace for face recognition. IEEE Conferenceon Computer Vision & Pattern Recognition, 1994,84-91.
[18]周志华，皇甫杰，张宏江，陈祖翰．基于神经网络集成的多视角人脸识别．计算机研究与发展，38(10)：1204-1210．
[19]Tang Ho Man, Sunny. Face Recognition Algorithms Review. http://www. google. com/.
[20]杨长生．图象与声音压缩技术．杭州：浙江大学出版社．2000．
[21]T. Kanade, Picture processing by computer complex and recognition of human faces, PhD thesis, Kyoto University, Department of Information Science, 1973.
[22]山世光，高文，陈熙霖．基于纹理分布和变形模板的面部特征提取技术．软件学报，2001，12(4)：570-577．
[23]Brunelli R, Poggio T. Feature Recognition : Features Versus Templates. IEEE on PAMI, 1993,15(10):1042-1052.
[24]Kwang Nam Choi, Andrew D JCross, Edwin R Hancock. Localizing facial features with matched filters. In:AVBPA' 97. Crans -Montana, Switzerland: Josef Bigün, Gérard Chollet, Gunilla Borgefors (Eds.),1997.11-20.
[25]Karin Sobottka, Ioannis Pitas. A fully automatic approach to facial feature detection and tracking. In:AVBPA'97. Crans -Montana, Switzerland: Josef Bigün, Gérard Chollet, Gunilla Borgefors (Eds.),1997.77-84.
[26]陈启泉，邱文宇，陈维斌．标准正面人脸图象的特征提取．华侨大学学报(自然科学版)．2000，21(4)：413-418．
[27]Venu Govindaraju, Locating Human Faces in Photographs. International Journal of Computer Vision, 1996,19(2):129-146.
[28]J. Koroec, L. Cyergyék, N. Paveic, M. Vezjak, A. Gere. Face Contour Detection Based on The Hough Transformatio. Automatika, 1990,31(1-2):77-81.
[29]Vezjak. M., Korosec. J., Gyergyek. L., Pavesic. N., Savsek. T., Erjavc. I., Gere. A. System for description and identi fication of individuals. Electrotechnical Conference, 1991. Proceedings. 6th Mediterranean, 1991,2(3):1251-1254.
[30]ZHANG D. Face Detection by Wavelet Transform. IEEE Trans on Image Processing,. 1995, 14(3):187-196.
[31]Ariel Tankus. Hezy Yeshurun and Nathan Intrator. Face Detection by Direct Convexity Estimation. In:AVBPA'97. Crans-Mon
tana, Switzerland: Josef Bigün, Gérard Chollet, Gunilla Borgefors (Eds.)43-50.
[32]Lam Kin-Man, Yan Hong. Locating and Extracting the Eye in Human Face Image. Pattern Recognition, 1996,29(5):771-779.
[33]Kwon Y H, Niels da Vitoria Lobo. Age Classification from Facial Images. Computer Vision and Image Understanding, 1999,74(1) : 1-21.
[34]Xie X, Sudhakar R, Zhuang H. On Improving Eye Feature Extraction Using Deformable Templates. Pattern Recognition, 1994,27 (6):791-799.
[35]Lanzarotti, R.; Borghese, N.A.; Campadelli, P. Robust identification and matching of fiducial points for the reconstruction of 3D human.faces from raw video sequences, ist International Symposium on 3D Data Processing Visualization and Transmission (3DPVT 2002), Padova, Italy, Jun 19-21, 2002:690-693.
[36]Morishima, S. Face image analysis and synthesis for human-computer interaction. Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on, 2000,2:1213-1220.
[37]Ingemar J. Cox, Joumana Ghosn, and Peter N. Yianilos. Feature-based face recognition using mixture-distance. In Computer Vision and Pattern Recognition. IEEE Press. 1996,6:209-216.
[38]M.A. Turk, A.P. Pentland . Eigenfaces for recognition, Journal of Cognitive Neuroscience 1991,3(1):71-86.
[39]高西奇，周洪祥，何振亚．基于小波变换的主元分析人脸图像识别．东南大学学报．1996，26(2)137-141．
[40]Bartlett M.S., Lades H.M., Sejnowski T.J. Independent component representations for face recognition, http://citeseer.nj. nec. com/cs.
[41]Field D J. What is the goal of sensory coding?. Neural Computation, 1994, 6(4),559-601.
[42]孙俊，王文渊，卓晴．基于稀疏编码的提取人脸整体特征算法．清华大学学报(自然科学版)．2002，42(3)：411-413．
[43]SUN Jun, ZHUO Qing, MA Chengyuan, et al. Sparse coding with clustering property and its application to face recognition . Pattern Recognition, 2001,34(9):184-185.
[44]Olshausen B A, Field D J. Emergence of simple-cell receptive-field properties by learning a sparse code for natural, im
ages. Nature, 1996, 381(6583) :607-609.
[45]Olshausen B A, Field D J. Sparse coding with an overcomplete basis set : a strategy employed by Ⅵ?. Vision Research, 1997, 37(23) :3311-3325.
[46]Foley D H, Sammon Jr J W. An optimal set of discriminant vectors. IEEE Trans on Comput, 1975, 24(3) :281-289.
[47]Liu Ke, Cheng Yong- Qing, Yang Jing- Yu. A generalized optimal set of discriminant vectors. Pattern Recognition, 1992,25 (7) : 731-739.
[48]金忠，杨静宇，陆建峰．一种具有统计不相关性的最佳鉴别矢量集．计算机学报，1999，22(10)：1105-1108．
[49]金忠，杨静宇，胡钟山．有效最佳鉴别特征的抽取与维数问题．计算机学报．2000，23(1)：108-112．
[50]Ziquan Hong. Algebraic feature extraction of image for recognition. Pattern Recognition, 1991, 24(3):211-219.
[51]黄修武，郭跃飞，杨静宇．基于代数方法的图像特征抽取和识别．南京理工大学学报．1998，22(1)：1-5．
[52]洪子泉，杨静宇．基于奇异值特征和统计模型的人像识别算法．计算机研究与发展．1994，31(3)：60-65．
[53]Lai JH, Yuen P C, Feng G C. Face recognition using holistic fourier invariantfeatures. Pattern Recognition, 2001,34(1): 95-109.
[54]赖剑煌，颜鑫弘，邓东皋．完善频谱脸人像识别的分类器设计．中国图象图形学报．2002，7(5A)：466-471．
[55]F. Samaria, S. Young. HMM based architecture for face identif ication. Image and Computer Vision. 1994,12(10):537-543.
[56]NEFIAN A V, HAYES M H. Face recognition using an embedded-HMM. Proceedings of IEEE International Conference on Audio and Video-based Biometric Person Authentication. Washington DC :[sn], 1999.19-21.
[57]薛斌党，欧宗瑛．加权合成的嵌入式隐Markov模型人脸识别．大连理工大学学报．2002，42(3)：326-332．
[58]Stefan Eickeler, Stefan Müller, Gerhard Rigoll. Improved face recognition using pseudo 2-D hidden markov models, http://www. google. com.
[59]Ferdinando Silvestro Samaria. Face recognition using hidden markov models. PhD. Paper.
[60]Lades M, Vorbruggen J, Buhmann Jetal. Distortion invarianto bjectrecognition in the dynamic link architecture. IEEE Trans Computers, 1993,42(3):300-311.
[61]Wiskott L , Fellous JM, Krüger N, von der Malsburg. Face recognition by elastic bunch graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997c, 19(7): 775-779.
[62]Chahab Nastar, Baback Moghaddam, Alex Pentland. Flexible Images: Matching and Recognition using Learned Deformations. Computer Vision and Image Understanding (CVIU).1997,65(2):179-191.
[63]陈刚，戚飞虎．基于分形和遗传算法的人脸识别方法．红外与毫米波学报．2000，19(5)：371-376．
[64]David DeMers and G.W. Cottrell. Non-linear dimensionality reduction, http://citeseer. nj. nec. com/cs.
[65]Intrator Nathan, Reisfeld Daniel, Yeshurun Yehezkel. Face recognition using a hybrid supervised/unsupervised neural network. Pattern recognition letters. 1996,17(1):67-76.
[66]Shang-Hung Lin; Sun-Yuan Kung; Long-Ji Lin. Face recognition/detection by probabilistic decision-based neural network. IEEE Transactions on Neural Networks. 1997,8(1):114-132.
[67]S. Lawrence, C. Lee Giles, A.C. Tsoi, A.D. Back. Face recognition: a convolutional neural network approach. IEEE Transactions on Neural Networks. 1997,8(1):98-113.
[68]Ying Dai, Yasuaki Nakano. Recognition of facial images with low resolution using a Hopfield memory model. Pattern Recognition. 1998, 31(2):159-167.
[69]Gutta Srinivas, Wechsler Harry. Face recognition using hybrid classifiers. Pattern recognition. 1997,30(4):539-553.
[70]Stan Z. Li, Juwez Lu. Face recognition using the nearest feature line method. IEEE Transactions on neural networks. 1999, 10(2):439-443.
[71]Nakamura O, Mathur S, Minami T. Identification of human faces based on isodensity maps. Pattern Recognition. 1991,24 (3):263-272.
[72]Lanitis A, Taylor C J, Cootes T F. Automatic interpretation and coding of face images using flexible models. IEEE trans. On PAMI, 1997,19(7):746-756.
[73]黄万军，尹宝才，陈通波．等基于三维可变形模板的眼睛特征提取．计算机研究与发展．2002，39(4)：495-501．
[74]P.J. Phillips, P.J. Rauss, S.Z. Der. FERET (Face Recognition Technology) Recognition Algorithm Development and Test Resu Its. http://citeseer. nj. nec. com/cs.
[75]P.J. Phillips, H. Moon, P.J. Rauss, S. Rizvi. The FERET evaluation methodology for face recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000, 22(10):1090-1104.
[76]http://www. itl. nist. gov/iad/humanid/feret/
[77]http://cvc. yale. edu/projects/yalefaces/yalefaces. html
[78]http://images. ee. umist. ac. uk/danny/database. html
[79]http://www. 21ppm. com. cn/htm/about/broadcast_0101_01. htm
[80]边肇祺，张学工著，模式识别．北京：清华大学出版社．2000．7．
[81]余松煜，周源华，吴时光．数字图像处理．北京：电子工业出版社．1989，8．
[82]姜家辉．矩阵理论基础．大连：大连理工大学出版社．1995．
[83]张贤达，保铮．盲信号分离．电子学报．2001，29(12A)：1766-1771．
[84]刘琚，何振亚．盲源分离和盲反卷积．电子学报．2002，30(4)：570-576．
[85]Jutten C, Herault J. Blind separation of sources, Part Ⅰ:Anadaptive algorithm based on neuromimetic. Signal Processing, 1991,24(1):1-10.
[86]Tong L, Liu R, Soon V C, et al. Indeterminacy and identifiability of blind identification. IEEE Trans on circuits and systems. 1991,38(5):499-506.
[87]Cardoso J F. Blind beamforming for non-gaussian signals. IEEE Proceedings-F, 1993,140(6):224-230.
[88]Comon P. Independent component analysis, a new concept?. Signal Processing, 1994,36(3):287-413.
[89]Bell AJ, Senowski T J. An information-maximization approach to blind separation and blind deconvolution. Neural Computatin, 1995,7(6):1129-1159.
[90]Amari S, Cichocki A, Yang H H. A new learning algorithm for blind signal separation. Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press, 1996,8:657-663.
[91]Hyvarinen A, Oja E. A fast fixed-point algorithm for independent component analysis. Neural Computation, 1997, 9(7):1483-1492.
[92]Girolami M, Fyfe C. An extended exploratory projection pursuit network with linear nonlinear anti-Hebbian lateral connections applied to the cocktail party problem. Neural Networks, 1998, 10(9):1607-1618.
[93]Lee T W, Bell A, Orglmeister R. Blind source separation of real world signals, http://www. google. com/.
[94]Karhunen J, Hyvarinen A. Application of neural blind separation to signal and image processing, in Proc ICASSP. Germany:Munich. 1997,131-134.
[95]Makeig S, Jung T P, Bell A J, et al. Blind separation of auditory event-related brain responses into independent components. Ih Proc Natl Acad Sci, 1997,94:10979-10984.
[96]Mckeown M J, Jung T P, Makeig S, et al. Spatially independent activity patterns in functional MRI data during the stroop color-naming task. In Proc Natl Acad Sci, 1998,95:803-810.
[97]Sahlin H, Broman H. Separation of real-world signals. Signal Processing, 199,64(2):103-113.
[98]Tugnait K. Spatio-temporal signal processing for blind separation of multicannel signals. In Proc of SPIE. Orlando:SPIE, 1996,88-103.
[99]T. M. Cover, J.A. Thomas. Elements of Information Theory. NewYork: John Wiley & Sons. 1991.
[100]Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces. J Opt Soc AmerA, 1987,4(3):519- 524.
[101]Chengjun Liu, Harry Wechsler. Comparative Assessment of Independent Component Analysis(ICA) for Face Recognition. In the 2th International Conf. On Audio- and Video-based Biomettic Person Authentication, AVBP' 99, Washington D.C. USA, March 22-24, 1999.
[102]M. Bartlett, T. Senowski. Independent components of face images: A representation forface recognition. In Proc. the 4th Annual Joint Symposium on Neural Computation, Pasadena, CA, May 17, 1997.3-16.
[103]Guodong Guo, Stan.Z. Li, Kap Luk Chan. Support vector machines for face recognition. Image and Vision Computing. 2001, 19(9-10),631-638.
[104]王润生．图像理解．长沙：国防科技大学出版社．1995．
[105]Z.J. Hou, G.W. Wei. A new approach to edge detection. Pattern R ecogniton. 2002,35(7):1559-1570.
[106]邓建中，葛仁杰，程正兴．计算方法．西安：西安交通大学出版社．1987．
[107]吴更石，梁德群，田原．基于分形维数的纹理图像分割．计算机学报．1999，22(10)：1109-1113．
[108]朱同林，彭嘉雄，吕铁英．基于左右导数算子类的边缘提取．红外与激光工程．1999，28(5)：35-38．
[109]李培华，张田文．主动轮廓线模型(蛇模型)综述．软件学报，2000，11(6)：751-757．
[110]Kass M, Witkin A etal. Snake:Active contour models. International Journal of Computer Vision. 1998,1(4):321-331.
[111]Cohen L D. On active Contour models and balloons. CVGIP: Image Understanding, 1991, 53(2):211-218.
[112]Cohen L D, Cohen I. Finite element methods for active contour models and balloons for 3 D and 3 D images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993,15 (1):1131-1147.
[113]Amini A A, Weymouth T E, Jain R C. Using dynamic programming for solving variational problems in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1990,12 (9):855-867.
[114]Williams D J, Shab M. A fast algorithm for active contours and curvature estimation. CVGIP:Image Understanding, 1992,55 (1):14～26.
[115]Caselles V, Carte F, Coll T etal. A geometric model for active contours in image processing. Numerische Mathematik, 1993, 66(1):1-32.
[116]Donald Hearn．计算机图形学．北京：清华大学出版社．1998．
[117]吴文俊．《九章算术》与刘徽．北京：北京师范大学出版社．1982．
[118]马峰，唐泽圣，夏绍玮．多尺度几何活动曲线及MR图像边界提取．计算机学报．2000，23(8)：829-834．
[119]王坚军，庄天戈．分形理论在医学图像边缘增强中的应用．合肥：中国科技大学出版社．1993．
[120]张欣，徐彦君，杜利民．彩色图象中主要人脸特征位置的全自动标定．中国图象图形学报．2000，5(2A)：138-143．
[121]于东亮，苏光大．人面像下颌轮廓线提取的研究．模式识别与人工智能．2002，15(1)：75-79．
[2]http://www.21ppm.com.cn/htm/about/broadcast_0101_01.htm
[3]孙冬梅，裘正定．生物特征识别技术综述．电子学报，2001，29(12A)：1744-1748．
[4]J G Daugman. High confidence visual recognition of persons by a test of statistical independence. IEEE Trans. PAMI, 19 93, 13(11), 1148-1161.
[5]J G Daugman. Demodulation, predictive coding, and spatial vision. J. Opt. Soc. Am, 1995, 12(4):641-660.
[6]R P Wildes, et al. A machine vision system for iris recognition. Machine Vision Application, 1996,9:1-8.
[7]R P Wildes. Iris recognition: an emerging biometric technology. Proceedings of IEEE, 1997, 85(9):1348-1363.
[8]Wayne Madsen. Biometrics Marches Forward in US Government. Computer Fraud & Security. 2001(5):7-8.
[9]Dieckmann U., Plankensteiner P., Wagner T. SESAM: A biometric person identification system using sensor fusion. Pattern Recognition Letters, 1997,18(9):827-833.
[10]Kittler J., Matas J., Jonsson K., Sánchez M.U. Ramos. Combining evidence in personal identity verification systems. Pattern Recognition Letters, 1997,18(9):845-852.
[11]http://www. oss. com/products/vision. html.
[12]W. Zhao. Face recognition: A literature survey, http:// citeseer. nj. nec. com/cs. 2000.
[13]张翠平，苏光大．人脸识别技术综述．中国图象图形学报．2000，5(11A)：885—894．
[14]Grudin M A. Compact multi-level representation of human faces for recognition. Ph. D dissertation, Liverpool John Moores University, Nov. 1997.
[15]Kanwisher Nancy, Tong Frank, Nakayama Ken. The effect of face inversion on the human fusiform face area. Cognition, 1998, 68(1): B1-B11.
[16]Nastar C, Ayache N. Frequency-based non-rigid motion analys
is. IEEE Trans Pattern Anal and Mach Intell, 1996,18(11):1067-1079.
[17]Alex Pentland, Baback Moghadam, Thad Starner. View-based and modular eigenspace for face recognition. IEEE Conferenceon Computer Vision & Pattern Recognition, 1994,84-91.
[18]周志华，皇甫杰，张宏江，陈祖翰．基于神经网络集成的多视角人脸识别．计算机研究与发展，38(10)：1204-1210．
[19]Tang Ho Man, Sunny. Face Recognition Algorithms Review. http://www. google. com/.
[20]杨长生．图象与声音压缩技术．杭州：浙江大学出版社．2000．
[21]T. Kanade, Picture processing by computer complex and recognition of human faces, PhD thesis, Kyoto University, Department of Information Science, 1973.
[22]山世光，高文，陈熙霖．基于纹理分布和变形模板的面部特征提取技术．软件学报，2001，12(4)：570-577．
[23]Brunelli R, Poggio T. Feature Recognition : Features Versus Templates. IEEE on PAMI, 1993,15(10):1042-1052.
[24]Kwang Nam Choi, Andrew D JCross, Edwin R Hancock. Localizing facial features with matched filters. In:AVBPA' 97. Crans -Montana, Switzerland: Josef Bigün, Gérard Chollet, Gunilla Borgefors (Eds.),1997.11-20.
[25]Karin Sobottka, Ioannis Pitas. A fully automatic approach to facial feature detection and tracking. In:AVBPA'97. Crans -Montana, Switzerland: Josef Bigün, Gérard Chollet, Gunilla Borgefors (Eds.),1997.77-84.
[26]陈启泉，邱文宇，陈维斌．标准正面人脸图象的特征提取．华侨大学学报(自然科学版)．2000，21(4)：413-418．
[27]Venu Govindaraju, Locating Human Faces in Photographs. International Journal of Computer Vision, 1996,19(2):129-146.
[28]J. Koroec, L. Cyergyék, N. Paveic, M. Vezjak, A. Gere. Face Contour Detection Based on The Hough Transformatio. Automatika, 1990,31(1-2):77-81.
[29]Vezjak. M., Korosec. J., Gyergyek. L., Pavesic. N., Savsek. T., Erjavc. I., Gere. A. System for description and identi fication of individuals. Electrotechnical Conference, 1991. Proceedings. 6th Mediterranean, 1991,2(3):1251-1254.
[30]ZHANG D. Face Detection by Wavelet Transform. IEEE Trans on Image Processing,. 1995, 14(3):187-196.
[31]Ariel Tankus. Hezy Yeshurun and Nathan Intrator. Face Detection by Direct Convexity Estimation. In:AVBPA'97. Crans-Mon
tana, Switzerland: Josef Bigün, Gérard Chollet, Gunilla Borgefors (Eds.)43-50.
[32]Lam Kin-Man, Yan Hong. Locating and Extracting the Eye in Human Face Image. Pattern Recognition, 1996,29(5):771-779.
[33]Kwon Y H, Niels da Vitoria Lobo. Age Classification from Facial Images. Computer Vision and Image Understanding, 1999,74(1) : 1-21.
[34]Xie X, Sudhakar R, Zhuang H. On Improving Eye Feature Extraction Using Deformable Templates. Pattern Recognition, 1994,27 (6):791-799.
[35]Lanzarotti, R.; Borghese, N.A.; Campadelli, P. Robust identification and matching of fiducial points for the reconstruction of 3D human.faces from raw video sequences, ist International Symposium on 3D Data Processing Visualization and Transmission (3DPVT 2002), Padova, Italy, Jun 19-21, 2002:690-693.
[36]Morishima, S. Face image analysis and synthesis for human-computer interaction. Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on, 2000,2:1213-1220.
[37]Ingemar J. Cox, Joumana Ghosn, and Peter N. Yianilos. Feature-based face recognition using mixture-distance. In Computer Vision and Pattern Recognition. IEEE Press. 1996,6:209-216.
[38]M.A. Turk, A.P. Pentland . Eigenfaces for recognition, Journal of Cognitive Neuroscience 1991,3(1):71-86.
[39]高西奇，周洪祥，何振亚．基于小波变换的主元分析人脸图像识别．东南大学学报．1996，26(2)137-141．
[40]Bartlett M.S., Lades H.M., Sejnowski T.J. Independent component representations for face recognition, http://citeseer.nj. nec. com/cs.
[41]Field D J. What is the goal of sensory coding?. Neural Computation, 1994, 6(4),559-601.
[42]孙俊，王文渊，卓晴．基于稀疏编码的提取人脸整体特征算法．清华大学学报(自然科学版)．2002，42(3)：411-413．
[43]SUN Jun, ZHUO Qing, MA Chengyuan, et al. Sparse coding with clustering property and its application to face recognition . Pattern Recognition, 2001,34(9):184-185.
[44]Olshausen B A, Field D J. Emergence of simple-cell receptive-field properties by learning a sparse code for natural, im
ages. Nature, 1996, 381(6583) :607-609.
[45]Olshausen B A, Field D J. Sparse coding with an overcomplete basis set : a strategy employed by Ⅵ?. Vision Research, 1997, 37(23) :3311-3325.
[46]Foley D H, Sammon Jr J W. An optimal set of discriminant vectors. IEEE Trans on Comput, 1975, 24(3) :281-289.
[47]Liu Ke, Cheng Yong- Qing, Yang Jing- Yu. A generalized optimal set of discriminant vectors. Pattern Recognition, 1992,25 (7) : 731-739.
[48]金忠，杨静宇，陆建峰．一种具有统计不相关性的最佳鉴别矢量集．计算机学报，1999，22(10)：1105-1108．
[49]金忠，杨静宇，胡钟山．有效最佳鉴别特征的抽取与维数问题．计算机学报．2000，23(1)：108-112．
[50]Ziquan Hong. Algebraic feature extraction of image for recognition. Pattern Recognition, 1991, 24(3):211-219.
[51]黄修武，郭跃飞，杨静宇．基于代数方法的图像特征抽取和识别．南京理工大学学报．1998，22(1)：1-5．
[52]洪子泉，杨静宇．基于奇异值特征和统计模型的人像识别算法．计算机研究与发展．1994，31(3)：60-65．
[53]Lai JH, Yuen P C, Feng G C. Face recognition using holistic fourier invariantfeatures. Pattern Recognition, 2001,34(1): 95-109.
[54]赖剑煌，颜鑫弘，邓东皋．完善频谱脸人像识别的分类器设计．中国图象图形学报．2002，7(5A)：466-471．
[55]F. Samaria, S. Young. HMM based architecture for face identif ication. Image and Computer Vision. 1994,12(10):537-543.
[56]NEFIAN A V, HAYES M H. Face recognition using an embedded-HMM. Proceedings of IEEE International Conference on Audio and Video-based Biometric Person Authentication. Washington DC :[sn], 1999.19-21.
[57]薛斌党，欧宗瑛．加权合成的嵌入式隐Markov模型人脸识别．大连理工大学学报．2002，42(3)：326-332．
[58]Stefan Eickeler, Stefan Müller, Gerhard Rigoll. Improved face recognition using pseudo 2-D hidden markov models, http://www. google. com.
[59]Ferdinando Silvestro Samaria. Face recognition using hidden markov models. PhD. Paper.
[60]Lades M, Vorbruggen J, Buhmann Jetal. Distortion invarianto bjectrecognition in the dynamic link architecture. IEEE Trans Computers, 1993,42(3):300-311.
[61]Wiskott L , Fellous JM, Krüger N, von der Malsburg. Face recognition by elastic bunch graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997c, 19(7): 775-779.
[62]Chahab Nastar, Baback Moghaddam, Alex Pentland. Flexible Images: Matching and Recognition using Learned Deformations. Computer Vision and Image Understanding (CVIU).1997,65(2):179-191.
[63]陈刚，戚飞虎．基于分形和遗传算法的人脸识别方法．红外与毫米波学报．2000，19(5)：371-376．
[64]David DeMers and G.W. Cottrell. Non-linear dimensionality reduction, http://citeseer. nj. nec. com/cs.
[65]Intrator Nathan, Reisfeld Daniel, Yeshurun Yehezkel. Face recognition using a hybrid supervised/unsupervised neural network. Pattern recognition letters. 1996,17(1):67-76.
[66]Shang-Hung Lin; Sun-Yuan Kung; Long-Ji Lin. Face recognition/detection by probabilistic decision-based neural network. IEEE Transactions on Neural Networks. 1997,8(1):114-132.
[67]S. Lawrence, C. Lee Giles, A.C. Tsoi, A.D. Back. Face recognition: a convolutional neural network approach. IEEE Transactions on Neural Networks. 1997,8(1):98-113.
[68]Ying Dai, Yasuaki Nakano. Recognition of facial images with low resolution using a Hopfield memory model. Pattern Recognition. 1998, 31(2):159-167.
[69]Gutta Srinivas, Wechsler Harry. Face recognition using hybrid classifiers. Pattern recognition. 1997,30(4):539-553.
[70]Stan Z. Li, Juwez Lu. Face recognition using the nearest feature line method. IEEE Transactions on neural networks. 1999, 10(2):439-443.
[71]Nakamura O, Mathur S, Minami T. Identification of human faces based on isodensity maps. Pattern Recognition. 1991,24 (3):263-272.
[72]Lanitis A, Taylor C J, Cootes T F. Automatic interpretation and coding of face images using flexible models. IEEE trans. On PAMI, 1997,19(7):746-756.
[73]黄万军，尹宝才，陈通波．等基于三维可变形模板的眼睛特征提取．计算机研究与发展．2002，39(4)：495-501．
[74]P.J. Phillips, P.J. Rauss, S.Z. Der. FERET (Face Recognition Technology) Recognition Algorithm Development and Test Resu Its. http://citeseer. nj. nec. com/cs.
[75]P.J. Phillips, H. Moon, P.J. Rauss, S. Rizvi. The FERET evaluation methodology for face recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000, 22(10):1090-1104.
[76]http://www. itl. nist. gov/iad/humanid/feret/
[77]http://cvc. yale. edu/projects/yalefaces/yalefaces. html
[78]http://images. ee. umist. ac. uk/danny/database. html
[79]http://www. 21ppm. com. cn/htm/about/broadcast_0101_01. htm
[80]边肇祺，张学工著，模式识别．北京：清华大学出版社．2000．7．
[81]余松煜，周源华，吴时光．数字图像处理．北京：电子工业出版社．1989，8．
[82]姜家辉．矩阵理论基础．大连：大连理工大学出版社．1995．
[83]张贤达，保铮．盲信号分离．电子学报．2001，29(12A)：1766-1771．
[84]刘琚，何振亚．盲源分离和盲反卷积．电子学报．2002，30(4)：570-576．
[85]Jutten C, Herault J. Blind separation of sources, Part Ⅰ:Anadaptive algorithm based on neuromimetic. Signal Processing, 1991,24(1):1-10.
[86]Tong L, Liu R, Soon V C, et al. Indeterminacy and identifiability of blind identification. IEEE Trans on circuits and systems. 1991,38(5):499-506.
[87]Cardoso J F. Blind beamforming for non-gaussian signals. IEEE Proceedings-F, 1993,140(6):224-230.
[88]Comon P. Independent component analysis, a new concept?. Signal Processing, 1994,36(3):287-413.
[89]Bell AJ, Senowski T J. An information-maximization approach to blind separation and blind deconvolution. Neural Computatin, 1995,7(6):1129-1159.
[90]Amari S, Cichocki A, Yang H H. A new learning algorithm for blind signal separation. Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press, 1996,8:657-663.
[91]Hyvarinen A, Oja E. A fast fixed-point algorithm for independent component analysis. Neural Computation, 1997, 9(7):1483-1492.
[92]Girolami M, Fyfe C. An extended exploratory projection pursuit network with linear nonlinear anti-Hebbian lateral connections applied to the cocktail party problem. Neural Networks, 1998, 10(9):1607-1618.
[93]Lee T W, Bell A, Orglmeister R. Blind source separation of real world signals, http://www. google. com/.
[94]Karhunen J, Hyvarinen A. Application of neural blind separation to signal and image processing, in Proc ICASSP. Germany:Munich. 1997,131-134.
[95]Makeig S, Jung T P, Bell A J, et al. Blind separation of auditory event-related brain responses into independent components. Ih Proc Natl Acad Sci, 1997,94:10979-10984.
[96]Mckeown M J, Jung T P, Makeig S, et al. Spatially independent activity patterns in functional MRI data during the stroop color-naming task. In Proc Natl Acad Sci, 1998,95:803-810.
[97]Sahlin H, Broman H. Separation of real-world signals. Signal Processing, 199,64(2):103-113.
[98]Tugnait K. Spatio-temporal signal processing for blind separation of multicannel signals. In Proc of SPIE. Orlando:SPIE, 1996,88-103.
[99]T. M. Cover, J.A. Thomas. Elements of Information Theory. NewYork: John Wiley & Sons. 1991.
[100]Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces. J Opt Soc AmerA, 1987,4(3):519- 524.
[101]Chengjun Liu, Harry Wechsler. Comparative Assessment of Independent Component Analysis(ICA) for Face Recognition. In the 2th International Conf. On Audio- and Video-based Biomettic Person Authentication, AVBP' 99, Washington D.C. USA, March 22-24, 1999.
[102]M. Bartlett, T. Senowski. Independent components of face images: A representation forface recognition. In Proc. the 4th Annual Joint Symposium on Neural Computation, Pasadena, CA, May 17, 1997.3-16.
[103]Guodong Guo, Stan.Z. Li, Kap Luk Chan. Support vector machines for face recognition. Image and Vision Computing. 2001, 19(9-10),631-638.
[104]王润生．图像理解．长沙：国防科技大学出版社．1995．
[105]Z.J. Hou, G.W. Wei. A new approach to edge detection. Pattern R ecogniton. 2002,35(7):1559-1570.
[106]邓建中，葛仁杰，程正兴．计算方法．西安：西安交通大学出版社．1987．
[107]吴更石，梁德群，田原．基于分形维数的纹理图像分割．计算机学报．1999，22(10)：1109-1113．
[108]朱同林，彭嘉雄，吕铁英．基于左右导数算子类的边缘提取．红外与激光工程．1999，28(5)：35-38．
[109]李培华，张田文．主动轮廓线模型(蛇模型)综述．软件学报，2000，11(6)：751-757．
[110]Kass M, Witkin A etal. Snake:Active contour models. International Journal of Computer Vision. 1998,1(4):321-331.
[111]Cohen L D. On active Contour models and balloons. CVGIP: Image Understanding, 1991, 53(2):211-218.
[112]Cohen L D, Cohen I. Finite element methods for active contour models and balloons for 3 D and 3 D images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993,15 (1):1131-1147.
[113]Amini A A, Weymouth T E, Jain R C. Using dynamic programming for solving variational problems in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1990,12 (9):855-867.
[114]Williams D J, Shab M. A fast algorithm for active contours and curvature estimation. CVGIP:Image Understanding, 1992,55 (1):14～26.
[115]Caselles V, Carte F, Coll T etal. A geometric model for active contours in image processing. Numerische Mathematik, 1993, 66(1):1-32.
[116]Donald Hearn．计算机图形学．北京：清华大学出版社．1998．
[117]吴文俊．《九章算术》与刘徽．北京：北京师范大学出版社．1982．
[118]马峰，唐泽圣，夏绍玮．多尺度几何活动曲线及MR图像边界提取．计算机学报．2000，23(8)：829-834．
[119]王坚军，庄天戈．分形理论在医学图像边缘增强中的应用．合肥：中国科技大学出版社．1993．
[120]张欣，徐彦君，杜利民．彩色图象中主要人脸特征位置的全自动标定．中国图象图形学报．2000，5(2A)：138-143．
[121]于东亮，苏光大．人面像下颌轮廓线提取的研究．模式识别与人工智能．2002，15(1)：75-79．