基于Contourlet变换的人脸识别技术研究
|
摘要
人脸在社会交往中扮演着十分重要的角色,是人类在确定一个人身份时所采用的最普通的生物特征,研究人脸识别及其相关技术具有十分重要的理论和应用价值。首先对人脸检测问题作了一些探讨,重点对基于积分图像的Adaboost人脸检测方法进行了研究,并采用该算法对人脸图像库中的图像进行了检测实验,验证了该算法的检测效果和性能。
Contourlet(轮廓波)变换是一种新的多尺度几何分析方法,它不仅具有小波变换的多分辨率特性和时频局域特性,还具有很强的方向性和各向异性,能够有效的捕捉图像的几何特征。支持向量机分类器由于其良好的分类能力和鲁棒性,在解决小样本、非线性及高维模式识别问题中表现出许多特有的优势。
本文分析了Contourlet变换的基本原理和变换特性,并研究了支持向量机(Support Vector Machine,SVM)多类别分类器的特性,提出了一种基于Contourlet变换与SVM多类别分类器的人脸识别方法。该方法利用了Contourlet变换后的低频分量系数作为识别特征。低频分量系数可以很好的反映人脸的姿态不变性和面部器官特征。对MIT-CBCL和Yale人脸数据库中人脸图像进行识别实验,结果表明该方法具有很好的识别率。
同时,Contourlet变换后的高频方向子带统计特征则刻画了人脸轮廓与局部器官形状信息,有效的捕捉图像的几何与边缘特征,对人脸图像的阴暗变化不是十分敏感。也具有很好的识别性能。本文也将Contourlet变换的低频分量与高频方向子带特征相结合进行人脸识别,利用欧氏距离求出低频特征向量的相似度,利用K-L距离求出高频分量的相似度,然后再求出两种相似度加权距离,距离越小,相似度越高。实验表明该方法有助于提高识别率。
Face plays an important role in social communication and is the most common biometric feature in personal identity, so face recognition (FR) and the related technologies have important theoretical and practical value.
Face detection is discussed in this paper. Specifically, the Adaboost face detection method which is based on integral image is studied, and some experiments are made to verify the performances of this method.
Contourlet transform is a new kind of multiscale geometric analysis method, which not only has the multiresolution decomposition and time-frequency properties, but also has strong directionality and anisotropy properties. Owning to these properties, Contourlet transform can capture the geometric features of images effectively. Support vector machine classifier due to its excellent classification capacity and robustness, has a good performance in pattern recognition problem with small sample, nonlinear and high dimension.
We analyze the basic principles and characteristics of Contourlet transform, and study the SVM multi-class classifier in this paper. A face recognition method based on Contourlet transformation and SVM multi-class classifier is proposed. The low-frequency coefficients generated by Contourlet transform can well reflect the invariability of face pose and the features of facial organs, so they are used as identification features. The face image recognition experiments on MIT-CBCL and Yale face database show that this method has an ideal performance.
The high frequency directional subband of Contourlet transform can depict the face outline and the local property of organs, and can catch the geometrical characteristics and edge features of face images effectively. The experiments show that the high frequency directional subband of Contourlet transform is also helpful for face recognition. We also try to combine low-frequency characteristic with directional high frequency subband coefficients. The similarity of low-frequency characteristic vectors is measured by Euclidean distance, and that of the high frequency components is measured by Kullback-Leibler (K-L) distance. The weighted similarity measure (WSM)is implemented by computing the weighted average of these two kinds of distances. The experimental results show that weighted similarity measure for contourlet-based face recognition can achieve higher recognition rates.
Contourlet(轮廓波)变换是一种新的多尺度几何分析方法,它不仅具有小波变换的多分辨率特性和时频局域特性,还具有很强的方向性和各向异性,能够有效的捕捉图像的几何特征。支持向量机分类器由于其良好的分类能力和鲁棒性,在解决小样本、非线性及高维模式识别问题中表现出许多特有的优势。
本文分析了Contourlet变换的基本原理和变换特性,并研究了支持向量机(Support Vector Machine,SVM)多类别分类器的特性,提出了一种基于Contourlet变换与SVM多类别分类器的人脸识别方法。该方法利用了Contourlet变换后的低频分量系数作为识别特征。低频分量系数可以很好的反映人脸的姿态不变性和面部器官特征。对MIT-CBCL和Yale人脸数据库中人脸图像进行识别实验,结果表明该方法具有很好的识别率。
同时,Contourlet变换后的高频方向子带统计特征则刻画了人脸轮廓与局部器官形状信息,有效的捕捉图像的几何与边缘特征,对人脸图像的阴暗变化不是十分敏感。也具有很好的识别性能。本文也将Contourlet变换的低频分量与高频方向子带特征相结合进行人脸识别,利用欧氏距离求出低频特征向量的相似度,利用K-L距离求出高频分量的相似度,然后再求出两种相似度加权距离,距离越小,相似度越高。实验表明该方法有助于提高识别率。
Face plays an important role in social communication and is the most common biometric feature in personal identity, so face recognition (FR) and the related technologies have important theoretical and practical value.
Face detection is discussed in this paper. Specifically, the Adaboost face detection method which is based on integral image is studied, and some experiments are made to verify the performances of this method.
Contourlet transform is a new kind of multiscale geometric analysis method, which not only has the multiresolution decomposition and time-frequency properties, but also has strong directionality and anisotropy properties. Owning to these properties, Contourlet transform can capture the geometric features of images effectively. Support vector machine classifier due to its excellent classification capacity and robustness, has a good performance in pattern recognition problem with small sample, nonlinear and high dimension.
We analyze the basic principles and characteristics of Contourlet transform, and study the SVM multi-class classifier in this paper. A face recognition method based on Contourlet transformation and SVM multi-class classifier is proposed. The low-frequency coefficients generated by Contourlet transform can well reflect the invariability of face pose and the features of facial organs, so they are used as identification features. The face image recognition experiments on MIT-CBCL and Yale face database show that this method has an ideal performance.
The high frequency directional subband of Contourlet transform can depict the face outline and the local property of organs, and can catch the geometrical characteristics and edge features of face images effectively. The experiments show that the high frequency directional subband of Contourlet transform is also helpful for face recognition. We also try to combine low-frequency characteristic with directional high frequency subband coefficients. The similarity of low-frequency characteristic vectors is measured by Euclidean distance, and that of the high frequency components is measured by Kullback-Leibler (K-L) distance. The weighted similarity measure (WSM)is implemented by computing the weighted average of these two kinds of distances. The experimental results show that weighted similarity measure for contourlet-based face recognition can achieve higher recognition rates.
引文
[1]张翠平,苏光.人脸识别技术综述.中国图像图形学报,2000(10)
[2]刘向东,陈兆乾.人脸识别技术研究.计算机研究与发展,2007(7)
[3] Yuille A L,Hallinan PW,Cohen D S.Feature extraction from faces using deformable templates.International Journal Computer Vision,1989.99-111
[4]董长虹.MATLAB神经网络与应用.第一版.北京:国防工业出版社,2005
[5]罗振波,丁晓青,方驰等.一种对光照鲁棒的人脸图像预处理算法[J].视频技术应用与工程,2006 (9)
[6]郭晶,周激流,张晔,朱辉,张乐.人脸识别系统中的BP网分类方法.四川大学学报(自然科学版),1999,36(3):518-522
[7]崔国勤,李锦涛,高文,焦锋.基于支持向量机的人脸识别方法.北京:中国科学院计算技术研究所数字化技术研究室,2003
[8] Chun-Hung Lin,Ja-Ling Wu.Automatic Facial Feature Extraction by Genetic Algorithms. IEEE Transactions on image processing, 1999,8(6):
[9]刘文卿,朱俊青,王林泉.基于积分投影的快速人脸定位.计算机辅助工程,No.2, Jun, 2003
[10]陈爱斌.复杂背景下基于Hough变换的人脸位. Information Technology, Apr, 2004
[11]朱俊青,王林泉,葛元.基于模板匹配的快速人脸定位.Computer Engineering, 2002,28(9)
[12]张俊,何昕,李介谷.基于面部几何特征点提取的人脸识别方法.红外与激光工程, 1999. 8, 28(4)
[13] Turk M, Pentland A.Face recognition using eigenfaces. IEEE Comput.Soc.Conf. On CVPR,1991,586-591
[14] Peter N B, Joao P H, David J K.Eigenfaces vs.Fisherfaces[J]. IEEE Transactions on Patten Analysis and Machine Intelligence,1997,19(7):711-720
[15] Moghaddam B, et al.Beyond Eigenfaces : Probabilistic Matching for Face Recognition [C]. Proceedings of the International Conference on Automatic Face andGesture Recognition,Nara,Japan,1998,30-35
[16] Lades M,Vorbrueggen J C,et al.Distortion Invariant Object Recognition in the Dynamic Link Architecture[J].IEEE Transactions on Computers,1993,42(3):300-311
[17] Wiskott L.Phantom Faces for Face Analysis[J].Pattern Recognition,1997,30:837-846
[18] Wiskott L,Fellous J M,Krüer N,et al.Face Recognition by Elastic Bunch Graph Matching[J]. IEEE Transations on Pattern Analysis and Maching Intelligence,1997,9(7):775-779
[19] Lee R,et al. Face Recognition:Elastic Relation Encoding and Structural Matching [C]. Proceedings of the IEEE International Conference on Systems, Man,and Cybernetics,1999,172-177
[20] Valentin D,et al.Connectionist Models of Face Processing:A Survey[J]. Pattern Recognition,1994,27(9):1209-1230
[21] 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
[22] Lin S H,Kung S Y,Lin L J.Face Recognition/Detection by Probabilistic Decision2 based Nerual Network[J]. IEEE Transactions on Neural Networks,1997,8(1):114-132
[23] Nefian A,Hayes M.Hidden Markov Models for Face Recognition[C]. IEEE International Conference on Acoustics,Speech and Signals Processings,Seattle,Washington,1998,2721-2724
[24] Samaria A S.Face Recognition Using Hidden Markov Models.PhD thesis,Trinity College, University of Cambridge,UK.1994
[25] Lanit.is, C. Taylor, T. F. Cootes. Automatic Interpretation and Coding of Face Images Using Flexible Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7):743-756.
[26] Sami Romdhani, Volker alanz, Thomas Vetter. Face Identification by Fitting a 3D Morphable Model Using linear Shape and Texture Error Functions [A].In 7th European Conference on Computer Vision Copenhagen, Denmark[C]. 2002. 05.
[27] Chengjun Liu and Wechsler H.A Gabor feature classifier for face recognition[C]. In:Proceedings. Eighth IEEE International Conference on Computer Vision,2001,2:270–275
[28] Jen-Tzung Chien and Chia-Chen Wu,Discriminant waveletfaces and nearest feature classifiers for face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24:1644–1649
[29] Dihua Xi,Podolak I.T.and Seong-Whan Lee.Facial Component Extraction and Face Recognition with Support Vector Machines[C]. In : Proceedings.Fifth IEEE International Conference on Automatic Face and Gesture Recognition,2002,76–81
[30] Xiaoling Wang and Hairong Qi. Face recognition using optimal non-orthogonal wavelet basis evaluated by information complexity[C]. In:Proceedings of 16th International Conference on Pattern Recognition,2002, 1:164-167
[31]焦李成,谭山.图像多尺度几何分析:回顾和展望[J].电子学报, 2003, 31(12):1975-1981
[32] M.N. Do, Directional Multiresolution Image Representations, Ph.D Desertation October 23, 2001
[33] P.J. Burt, E.H. Adelson, The Laplacian pyramid as acompact image code, Traps. Communication, 1983,31(4): 532-540
[34] M. N. Do. M. Vetterli. Framing pyramids. IEEE Trans. Signal Proc. September 2003, 2329-2342
[35] P P. Vaidyanathan. Multirate systems and filter banks. Prentice-Hall, Englewood Cliffs, NJ, 1993
[36] M. Vetterli and J. KovaCevic. Wavelets and subband coding. Prentice-Hall. Englewood Cliffs, NJ, 1995
[37] M. N. Do and M. Vetterli. The contourlet transform: image representation. IEEE Transaction on Image Processing, 2005, 2091-2106
[38] C.W Hsuand, C J Lin, A comparison of methods for multi-class support vector machines, IEEE Transaction on Neural Networks, 2002, 13:415-425
[39] Burges J C. A tutorial on support vector machines for pattern recognition, Data Mining and Knowledge Discovery, 1998, 2(2):1-47
[40] N. Cristianini, J. Shawe Taylor. An Introduction to Support Vector Machines andOther Kernel-based Learning Methods[M]. Cambridge: Cambridge University Press, 2000.69-138
[41] Jie Lin; Jian-Ping Li; Ming Ji," Robust Face Recognition by Wavelet Features and Model Adaptation," International Conference on Wavelet Analysis and Pattern Recognition, 2007, ICWAPR'07, 4, p.1638-1643
[42] Do M N,Vetterli M.Wavelet-Based Texture Retrieval Using Generalized Gaussian Density and Kullback-Leibler Distance[J].IEEE Transactions on Image Processing, 2002,11(2):146-158
[43] M Vetterli. Multidimensional subband coding: Some theory and algorithms, Signal Proc, 1984, 6(2):97-112
[44] Krebel Ulrich H G. Pairwise classification and support vector machines. Schokopf Bernhard Advances in Kernel Methods:Support Vector Learning, Massachusetts, The MIT Press, 1999.255-268
[45] Bennett K, Blue J. A support vector machine approach to decision trees. Rensselaer Poly technical Institute. Trov.NY:1997.97-100
[46] Mallat S.A theory for multiresolution signal decomposition : the wavelet representation[J].IEEE Transactions on Pattern Analyse and Machine Intelligence, 1989, 11(7):674-693
[47]郁梅,易文娟,蒋刚毅.基于Contourlet变换尺度间相关的图像去噪[J].光电工程,2006,33(6):73-77
[48]金炜,魏彪,潘英俊等一种新颖的Contourlet域中子辐射图像降噪方法[J].光子学报,2006,35(5):760-765
[49]邓承志,曹汉强,汪胜前.非高斯双变量模型Contourlet图像去噪[J].红外与激光工程,2006,35(2):234-237
[50]张绘,张弓,郭琦南.基于Contourlet域S0T结构的SAR图像相干斑抑制算法[J].南京航空航天大学学报,2006,38(6):746-748
[51]易文娟,郁梅,蒋刚毅. Contourlet:一种有效的方向多尺度变换分析方法[J].计算机应用研究,2006,23(9):18-22
[52] Yang G,Huang T S.Human Face Detection in Complex Background[J].Pattern Recognition 1994,27(1):53-63
[53] Sung K K,Poggio T.Example Based Learning for View Based Human Face Detection[J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 20(1):39-51
[54] Schneiderman H.A Statistical Approach to 3D Object Detection Applied to Faces and Cars[D].PhD Thesis,CMU-RI-TR-00-06,2002
[55]刘志镜,李夏忠,武芒.基于三维模型的多姿态人脸识别[J].西安电子科技大学学报, 2004,31(2):208-222
[56] Jain A K,Zhong Y.Deformable Template Model[J].A Review Signal Processing, 1998,71(2):109-129
[57]李军峰,姜翌明.具有真实感的虚拟人脸合成[J].西安电子科技大学学报, 2003,30(4):525-529
[58]王科俊,姚向辉.人脸图像检测和识别方法综述[J],自动化技术与应用, 2004,23(12):5-6
[59] Yang M H,Kriegman D,Ahujia N.Detection Faces in Images:A Survey[J]. IEEE Transaction.Pattern Analysis and Machine Intelligence. 2002,24(1):34-58
[60] Haritaoglu I} Harwood D and Davis L. W4: real-time surveillance of people and their activities [J]. IEEE Trans Pattern Analysis and Machine Intelligence 2000,22 (8):809-830
[61] McKenna S et al, Tracking groups of people. Computer Vision and Image Understanding, 2000, 80(1):42-56
[62] Stauffer C and Crimson W. Adaptive background mixture models for real-time tracking. In:Froc IEEE Conference on Computer Vision and Pattern Recognition Fort Collins } Colorado 1999,2:246-252
[63] Karmann K and Brandt A. Moving object recognition using an adaptive background memory. In:Cappellini, Ved, Time-varying Image Processing and Moving Object Recognition. Elsevier, Amsterdam, The Netherlands, 1990
[64] Mumay D W } Buxton B F. Scene segmentation from visual motion using global optimization. IEEE Trans. On Pattern Analysis and Machine Intelligence. 1987,9(2):220-228
[65] Bamon J} Fleet D,Beauchernin S. Performance of optical flow techniques. International Journal of Computer Vision 1994,12(1):42-77
[66] Lipton A} Fujiyoshi H} Patil R. Moving target classification and tracking from real-time video. In:Froc IEEE Workshop on Applications of Computer Vision Princeton NJ} 1998,8-14.
[67]陈朝阳,张桂林.基于图像对称差分运算的运动小日标检测方法[[J].华中理工大学学报,1998 26(9):34-36
[68] Munchurl K} Jae G C,Dachee K} et al. A VOP Generation Tool:Automatic Segmentation of Moving Objects in Image Sequences Based on Spation-Temporal Information [J]. IEEE Trans on Circuits and systems for Video Technology 1999,9(8):1216-1226
[69] Collins R T. A system for video surveillance and monitoring. Technical Report CMU-RI-TR-00-12} Robotics Institute Carnegie Mellon Universtiy} 2000
[70]夏利民,谷士文.基于形变模型的图像分割和非刚性日标的跟踪[J].模式识别与人工智能,2000 13(1):64-68
[71] Friedman N and Russell S. Image segmentation in video sequences:a probabilistic approach. In:Froc the Thirteenth Conference on Uncertainty in Artificial Intelligence, Rhode Island, USA, 1997.
[72] Stringa E. Morphological change detection algorithms for surveillance application. In:British Machine Vision Conference> Bristol> IJK> 2000> 402-411
[73] Viola P, Jones M. Rapid[J]. In proceedings IEEE USA, 2001:511-518. Object Detection using a Boosted conf. on Computer Vision and Pattern Cascade of Simple Features Recognition, Kauai, Hawaii.
[2]刘向东,陈兆乾.人脸识别技术研究.计算机研究与发展,2007(7)
[3] Yuille A L,Hallinan PW,Cohen D S.Feature extraction from faces using deformable templates.International Journal Computer Vision,1989.99-111
[4]董长虹.MATLAB神经网络与应用.第一版.北京:国防工业出版社,2005
[5]罗振波,丁晓青,方驰等.一种对光照鲁棒的人脸图像预处理算法[J].视频技术应用与工程,2006 (9)
[6]郭晶,周激流,张晔,朱辉,张乐.人脸识别系统中的BP网分类方法.四川大学学报(自然科学版),1999,36(3):518-522
[7]崔国勤,李锦涛,高文,焦锋.基于支持向量机的人脸识别方法.北京:中国科学院计算技术研究所数字化技术研究室,2003
[8] Chun-Hung Lin,Ja-Ling Wu.Automatic Facial Feature Extraction by Genetic Algorithms. IEEE Transactions on image processing, 1999,8(6):
[9]刘文卿,朱俊青,王林泉.基于积分投影的快速人脸定位.计算机辅助工程,No.2, Jun, 2003
[10]陈爱斌.复杂背景下基于Hough变换的人脸位. Information Technology, Apr, 2004
[11]朱俊青,王林泉,葛元.基于模板匹配的快速人脸定位.Computer Engineering, 2002,28(9)
[12]张俊,何昕,李介谷.基于面部几何特征点提取的人脸识别方法.红外与激光工程, 1999. 8, 28(4)
[13] Turk M, Pentland A.Face recognition using eigenfaces. IEEE Comput.Soc.Conf. On CVPR,1991,586-591
[14] Peter N B, Joao P H, David J K.Eigenfaces vs.Fisherfaces[J]. IEEE Transactions on Patten Analysis and Machine Intelligence,1997,19(7):711-720
[15] Moghaddam B, et al.Beyond Eigenfaces : Probabilistic Matching for Face Recognition [C]. Proceedings of the International Conference on Automatic Face andGesture Recognition,Nara,Japan,1998,30-35
[16] Lades M,Vorbrueggen J C,et al.Distortion Invariant Object Recognition in the Dynamic Link Architecture[J].IEEE Transactions on Computers,1993,42(3):300-311
[17] Wiskott L.Phantom Faces for Face Analysis[J].Pattern Recognition,1997,30:837-846
[18] Wiskott L,Fellous J M,Krüer N,et al.Face Recognition by Elastic Bunch Graph Matching[J]. IEEE Transations on Pattern Analysis and Maching Intelligence,1997,9(7):775-779
[19] Lee R,et al. Face Recognition:Elastic Relation Encoding and Structural Matching [C]. Proceedings of the IEEE International Conference on Systems, Man,and Cybernetics,1999,172-177
[20] Valentin D,et al.Connectionist Models of Face Processing:A Survey[J]. Pattern Recognition,1994,27(9):1209-1230
[21] 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
[22] Lin S H,Kung S Y,Lin L J.Face Recognition/Detection by Probabilistic Decision2 based Nerual Network[J]. IEEE Transactions on Neural Networks,1997,8(1):114-132
[23] Nefian A,Hayes M.Hidden Markov Models for Face Recognition[C]. IEEE International Conference on Acoustics,Speech and Signals Processings,Seattle,Washington,1998,2721-2724
[24] Samaria A S.Face Recognition Using Hidden Markov Models.PhD thesis,Trinity College, University of Cambridge,UK.1994
[25] Lanit.is, C. Taylor, T. F. Cootes. Automatic Interpretation and Coding of Face Images Using Flexible Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7):743-756.
[26] Sami Romdhani, Volker alanz, Thomas Vetter. Face Identification by Fitting a 3D Morphable Model Using linear Shape and Texture Error Functions [A].In 7th European Conference on Computer Vision Copenhagen, Denmark[C]. 2002. 05.
[27] Chengjun Liu and Wechsler H.A Gabor feature classifier for face recognition[C]. In:Proceedings. Eighth IEEE International Conference on Computer Vision,2001,2:270–275
[28] Jen-Tzung Chien and Chia-Chen Wu,Discriminant waveletfaces and nearest feature classifiers for face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24:1644–1649
[29] Dihua Xi,Podolak I.T.and Seong-Whan Lee.Facial Component Extraction and Face Recognition with Support Vector Machines[C]. In : Proceedings.Fifth IEEE International Conference on Automatic Face and Gesture Recognition,2002,76–81
[30] Xiaoling Wang and Hairong Qi. Face recognition using optimal non-orthogonal wavelet basis evaluated by information complexity[C]. In:Proceedings of 16th International Conference on Pattern Recognition,2002, 1:164-167
[31]焦李成,谭山.图像多尺度几何分析:回顾和展望[J].电子学报, 2003, 31(12):1975-1981
[32] M.N. Do, Directional Multiresolution Image Representations, Ph.D Desertation October 23, 2001
[33] P.J. Burt, E.H. Adelson, The Laplacian pyramid as acompact image code, Traps. Communication, 1983,31(4): 532-540
[34] M. N. Do. M. Vetterli. Framing pyramids. IEEE Trans. Signal Proc. September 2003, 2329-2342
[35] P P. Vaidyanathan. Multirate systems and filter banks. Prentice-Hall, Englewood Cliffs, NJ, 1993
[36] M. Vetterli and J. KovaCevic. Wavelets and subband coding. Prentice-Hall. Englewood Cliffs, NJ, 1995
[37] M. N. Do and M. Vetterli. The contourlet transform: image representation. IEEE Transaction on Image Processing, 2005, 2091-2106
[38] C.W Hsuand, C J Lin, A comparison of methods for multi-class support vector machines, IEEE Transaction on Neural Networks, 2002, 13:415-425
[39] Burges J C. A tutorial on support vector machines for pattern recognition, Data Mining and Knowledge Discovery, 1998, 2(2):1-47
[40] N. Cristianini, J. Shawe Taylor. An Introduction to Support Vector Machines andOther Kernel-based Learning Methods[M]. Cambridge: Cambridge University Press, 2000.69-138
[41] Jie Lin; Jian-Ping Li; Ming Ji," Robust Face Recognition by Wavelet Features and Model Adaptation," International Conference on Wavelet Analysis and Pattern Recognition, 2007, ICWAPR'07, 4, p.1638-1643
[42] Do M N,Vetterli M.Wavelet-Based Texture Retrieval Using Generalized Gaussian Density and Kullback-Leibler Distance[J].IEEE Transactions on Image Processing, 2002,11(2):146-158
[43] M Vetterli. Multidimensional subband coding: Some theory and algorithms, Signal Proc, 1984, 6(2):97-112
[44] Krebel Ulrich H G. Pairwise classification and support vector machines. Schokopf Bernhard Advances in Kernel Methods:Support Vector Learning, Massachusetts, The MIT Press, 1999.255-268
[45] Bennett K, Blue J. A support vector machine approach to decision trees. Rensselaer Poly technical Institute. Trov.NY:1997.97-100
[46] Mallat S.A theory for multiresolution signal decomposition : the wavelet representation[J].IEEE Transactions on Pattern Analyse and Machine Intelligence, 1989, 11(7):674-693
[47]郁梅,易文娟,蒋刚毅.基于Contourlet变换尺度间相关的图像去噪[J].光电工程,2006,33(6):73-77
[48]金炜,魏彪,潘英俊等一种新颖的Contourlet域中子辐射图像降噪方法[J].光子学报,2006,35(5):760-765
[49]邓承志,曹汉强,汪胜前.非高斯双变量模型Contourlet图像去噪[J].红外与激光工程,2006,35(2):234-237
[50]张绘,张弓,郭琦南.基于Contourlet域S0T结构的SAR图像相干斑抑制算法[J].南京航空航天大学学报,2006,38(6):746-748
[51]易文娟,郁梅,蒋刚毅. Contourlet:一种有效的方向多尺度变换分析方法[J].计算机应用研究,2006,23(9):18-22
[52] Yang G,Huang T S.Human Face Detection in Complex Background[J].Pattern Recognition 1994,27(1):53-63
[53] Sung K K,Poggio T.Example Based Learning for View Based Human Face Detection[J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 20(1):39-51
[54] Schneiderman H.A Statistical Approach to 3D Object Detection Applied to Faces and Cars[D].PhD Thesis,CMU-RI-TR-00-06,2002
[55]刘志镜,李夏忠,武芒.基于三维模型的多姿态人脸识别[J].西安电子科技大学学报, 2004,31(2):208-222
[56] Jain A K,Zhong Y.Deformable Template Model[J].A Review Signal Processing, 1998,71(2):109-129
[57]李军峰,姜翌明.具有真实感的虚拟人脸合成[J].西安电子科技大学学报, 2003,30(4):525-529
[58]王科俊,姚向辉.人脸图像检测和识别方法综述[J],自动化技术与应用, 2004,23(12):5-6
[59] Yang M H,Kriegman D,Ahujia N.Detection Faces in Images:A Survey[J]. IEEE Transaction.Pattern Analysis and Machine Intelligence. 2002,24(1):34-58
[60] Haritaoglu I} Harwood D and Davis L. W4: real-time surveillance of people and their activities [J]. IEEE Trans Pattern Analysis and Machine Intelligence 2000,22 (8):809-830
[61] McKenna S et al, Tracking groups of people. Computer Vision and Image Understanding, 2000, 80(1):42-56
[62] Stauffer C and Crimson W. Adaptive background mixture models for real-time tracking. In:Froc IEEE Conference on Computer Vision and Pattern Recognition Fort Collins } Colorado 1999,2:246-252
[63] Karmann K and Brandt A. Moving object recognition using an adaptive background memory. In:Cappellini, Ved, Time-varying Image Processing and Moving Object Recognition. Elsevier, Amsterdam, The Netherlands, 1990
[64] Mumay D W } Buxton B F. Scene segmentation from visual motion using global optimization. IEEE Trans. On Pattern Analysis and Machine Intelligence. 1987,9(2):220-228
[65] Bamon J} Fleet D,Beauchernin S. Performance of optical flow techniques. International Journal of Computer Vision 1994,12(1):42-77
[66] Lipton A} Fujiyoshi H} Patil R. Moving target classification and tracking from real-time video. In:Froc IEEE Workshop on Applications of Computer Vision Princeton NJ} 1998,8-14.
[67]陈朝阳,张桂林.基于图像对称差分运算的运动小日标检测方法[[J].华中理工大学学报,1998 26(9):34-36
[68] Munchurl K} Jae G C,Dachee K} et al. A VOP Generation Tool:Automatic Segmentation of Moving Objects in Image Sequences Based on Spation-Temporal Information [J]. IEEE Trans on Circuits and systems for Video Technology 1999,9(8):1216-1226
[69] Collins R T. A system for video surveillance and monitoring. Technical Report CMU-RI-TR-00-12} Robotics Institute Carnegie Mellon Universtiy} 2000
[70]夏利民,谷士文.基于形变模型的图像分割和非刚性日标的跟踪[J].模式识别与人工智能,2000 13(1):64-68
[71] Friedman N and Russell S. Image segmentation in video sequences:a probabilistic approach. In:Froc the Thirteenth Conference on Uncertainty in Artificial Intelligence, Rhode Island, USA, 1997.
[72] Stringa E. Morphological change detection algorithms for surveillance application. In:British Machine Vision Conference> Bristol> IJK> 2000> 402-411
[73] Viola P, Jones M. Rapid[J]. In proceedings IEEE USA, 2001:511-518. Object Detection using a Boosted conf. on Computer Vision and Pattern Cascade of Simple Features Recognition, Kauai, Hawaii.