人脸检测技术融合算法的研究与实现
|
摘要
人脸的检测是计算机视觉、计算机图形学中的一个研究热点和难点,是一个具有挑战性的课题。人脸具有不同的姿态、尺寸、肤色和表情,而且,其他的因素(例如戴眼镜、头发的有无以及穿戴)都有可能导致检测失败。不同的光照条件、背景的复杂程度都有可能影响人脸检测算法的适用性。本文对人脸的检测技术进行了研究,提出了一种人脸检测技术融合算法的系统框架。
本文首先在对人脸检测、人脸面部特征定位技术的相关文献进行综述的基础上,提出了人脸检测技术融合算法。该算法通过对人脸检测多种算法的优缺点分析,吸取了各算法的优点,并提出一定的改进,使各算法无缝融合在一起,共同发挥各算法的优点,使人脸检测更进一步完善,更进一步准确。算法将人脸检测分为三个层次:首先提出了肤色区域生长分割算法的人脸粗检,即利用颜色信息把彩色图像通过肤色区域生长的分割技术,把皮肤区和背景区分离出来,找到在图像上人脸的大概位置;其次采用改进Adaboost算法学习出基于视图的瀑布型人脸检测器,做人脸位置的精确定位,找到图像上人脸的具体位置。为了提高检测速度,提出了使用了多分辨率的搜索策略;然后再提出了一种根据人的面部特征的几何信息与广义对称算法来具体搜索人脸的脸部器官所在的具体位置。在本算法中后一个层次的检测都以前一个层次的检测结果为初值,受到上一个层次检测结果的约束。
本文提出的人脸检测技术融合算法的框架具有广泛的应用前景,实验证明本算法对于较复杂背景下的人脸图像有较好的检测效果,可以应用于身份认证、人脸表情分析、自然和谐的人机交互等方向。
Face detection is a hot and difficult research area in computer vision and computer graphics. Human face detection is a challenging project because the face can have varying pose, size, skin color, and facial expression. In addition, other factors, such as wearing of glasses, presence or absence of hair, and occlusion can make the appearance of the face unpredictable. Other effects, such as varying lighting conditions and complexity of the scene containing the face can make the generalization of face detection algorithms difficult. In this thesis, I present a novel face detection framework based on a face detection algorithm merged with some advanced algorithms.
I firstly survey basic techniques in face detection and face recognition, then I present a face detection algorithm merged with some advanced algorithms. After analysis of advantages and disadvantages of the face detection algorithm, absorbed some advantages of algorithms,and improved these algorithms certainly and finally merged. The face detection consists of three stages, the first stage is the face detection based on skin region growing, namely to locate facial features of people by skin region growing technology to separate skin image from background image ,the second stage is the the cascade face detector is learnt by using Adaboost algorithm, which finds the number of faces and their approximate positions in the image. For speed up, multi-resolution searching strategies are introduced.; the third stage is the searching of detailed local features using geometric matching models like eye model and mouth model with the feature position in the previously face detection as the initialization, which finally finds the desired feature points. During the final stage, the global searching result serves as the geometry constraints on the local feature detection procedure.
The framework proposed in this thesis has many applications like person identification, facial expression synthesis and analysis, multi-modal human computer interaction, etc. Experimental results show that this algorithm has some detection effect on face image on complex background.
本文首先在对人脸检测、人脸面部特征定位技术的相关文献进行综述的基础上,提出了人脸检测技术融合算法。该算法通过对人脸检测多种算法的优缺点分析,吸取了各算法的优点,并提出一定的改进,使各算法无缝融合在一起,共同发挥各算法的优点,使人脸检测更进一步完善,更进一步准确。算法将人脸检测分为三个层次:首先提出了肤色区域生长分割算法的人脸粗检,即利用颜色信息把彩色图像通过肤色区域生长的分割技术,把皮肤区和背景区分离出来,找到在图像上人脸的大概位置;其次采用改进Adaboost算法学习出基于视图的瀑布型人脸检测器,做人脸位置的精确定位,找到图像上人脸的具体位置。为了提高检测速度,提出了使用了多分辨率的搜索策略;然后再提出了一种根据人的面部特征的几何信息与广义对称算法来具体搜索人脸的脸部器官所在的具体位置。在本算法中后一个层次的检测都以前一个层次的检测结果为初值,受到上一个层次检测结果的约束。
本文提出的人脸检测技术融合算法的框架具有广泛的应用前景,实验证明本算法对于较复杂背景下的人脸图像有较好的检测效果,可以应用于身份认证、人脸表情分析、自然和谐的人机交互等方向。
Face detection is a hot and difficult research area in computer vision and computer graphics. Human face detection is a challenging project because the face can have varying pose, size, skin color, and facial expression. In addition, other factors, such as wearing of glasses, presence or absence of hair, and occlusion can make the appearance of the face unpredictable. Other effects, such as varying lighting conditions and complexity of the scene containing the face can make the generalization of face detection algorithms difficult. In this thesis, I present a novel face detection framework based on a face detection algorithm merged with some advanced algorithms.
I firstly survey basic techniques in face detection and face recognition, then I present a face detection algorithm merged with some advanced algorithms. After analysis of advantages and disadvantages of the face detection algorithm, absorbed some advantages of algorithms,and improved these algorithms certainly and finally merged. The face detection consists of three stages, the first stage is the face detection based on skin region growing, namely to locate facial features of people by skin region growing technology to separate skin image from background image ,the second stage is the the cascade face detector is learnt by using Adaboost algorithm, which finds the number of faces and their approximate positions in the image. For speed up, multi-resolution searching strategies are introduced.; the third stage is the searching of detailed local features using geometric matching models like eye model and mouth model with the feature position in the previously face detection as the initialization, which finally finds the desired feature points. During the final stage, the global searching result serves as the geometry constraints on the local feature detection procedure.
The framework proposed in this thesis has many applications like person identification, facial expression synthesis and analysis, multi-modal human computer interaction, etc. Experimental results show that this algorithm has some detection effect on face image on complex background.
引文
[1]梁路宏,艾海舟,徐光祜,等.人脸检测研究综述[J].计算机学报,2002,25(5):449-458.
[2]潘志庚,邹鹏程,梁荣华.基于特征人脸和肤色统计的人脸检测[J].系统仿真学报,2002,16(6).
[3]刘党辉,沈兰荪,LAM K-M,等.人脸检测研究进展[J].计算机工程与应用,2003,23(3).
[4]YANG G,HUANG TS.Human Face Detection in Complex Back-ground[J].Pattern Recongnition,1994,27(1):53-63.
[5]MIAO J,YIN BC,WANG KQ,etal.AHierarchicalMultiscale and Multiangle System forHuman Face Detection in a Complex Back-ground Using Gravity-Center Template[J].Pattern Recongnition,1999,32(7):1237-1248.
[6]WU LF,SHEN LS,JIA KB,et al.ISO/IEC JTC1 /SC29 /WG11 MPEG2000 /m6536,ImprovementofAutomaticHuman FaceDetec-tion[Sl,2000.
[7]TURKM,PENTLAND A.Eigenfaces forRecognition[J].Cognitive Neuro-science,1991,3(1):71-86.
[8]SUNG KK,POGGIO Z.Example-BasedLearing forView-Based Human Face Detection[J].IEEE Transactions on Pattern Analysis andMachine Intelligence,1998,20(1):39-51.
[9]SCHNEIDERMANH,KANADE T.ProbabilisticModeling of Local Appearance and Spatial Relationships for Object Recognition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],1998.45-51.
[10]YOO T-W,OH Ⅱ-S.A fast algorithm for tracking human faces based chromatic histograms[J].Pattern ReCognition Letters,1999,20(10):967-968.
[11]HSU R-L,ABDEL-MOTTALEBM,JAIN A-K.Face detection in color images[J].IEEE Transactions on Pattern Analysis andMa-chine Intelligence,2002,24(5):696-706.
[12]TERRILLON J-C,SHIRAZIM-N,FUKAMACHIH,et al.Com-parative Performance of Different Skin Chrominance Models and Chrominance Spaces for theAutomaticDetection of Human Faces in Color Images[A].Proceedings of the Fourth IEEE International Conference onAutomatic Face and Gesture Recognition[el,2000.54-60.
[13]Coots T.F,Taylor C.J.Locating Faces using Statistical Feature Detectors in:Proc.Automatic Face an Gesture Recognition,1996;204-209
[14]Wiskott L.,Fellous J.-M Kuger N.Von derMalsburg C.Face Recognition by elastic bunch graph matching.IEEE Trans.On Pattern Analysis and Machine Intelligence,1997,19(7);775-779
[15]kin C.Y.Cipollar R.A Probablistic Framework for perceptual grouping of features for human facedetection.In Proc.Automatic Face and Gesture Recognition,1996,16-21;
[16]艾海舟、肖习攀、徐光祜,人脸检测与检索,计算机学报,2003 Vol.26 No.07[17]王良民、张建明、詹永照、宋顺林人脸检测研究现状和发展江苏大学学报(自然科学版),2003 Vol.24 No.3
[17]Amaryllis Raouzaiou,Nicolas Tsapatsoulis,Stefanos Kollias Parameterized Facial Expression Synthesis For Videoconferencing Applications
[18]Dan Witzner Hansen,John Paulin Hansen,Mads Nielsen,Anders Sewerin Johansen and Mikkel B.Stegmann "Eye Typing using Markov and Active Appearance Models" "IEEE Workshop on Applications on Computer Vision",2002,pp.132-136.
[19]John Paulin Hansen,Dan Witzner Hansen and Anders Sewerin Johansen " Bringing Gaze-based Interaction Back to Basics" in " Universal Access In HCI",C.Stephanidis(ed.),Lawrence Erlbaum Associates.2001,pp.325-328
[20]陶亮、庄镇泉,一种基于个人身份认证的正下面人脸识别算法,中国图象图形学报A,2003 Vol.8 No.08
[21]高文金辉面部表情图像的分析与识别计算机学报.1997,20(9).-782-789
[22]Terrillon J C,Shirazi M N,Fukamachi H,et al.Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images.In:Proc.Conf.on Automatic Face and Gesture Recognition,Grenoble,France,2000,54-61.
[23]Jones M J,Rehg J M.Statistical color models with application to skin detection.In Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Fort Collins,Colorado,1999,274-280
[24]YANG J,LUW,WAIBELA.Skin-colormodeling and adaptation[A].LectureNotes in ComputerScience[C],1998.1352.
[25]陈忠林,刘智明,周激流.复杂背景图像中彩色人脸的检测[J].成都理工大学学报(自然科学版),2004,31(1):86-90.
[26]LI SZ,JAINAK.Handbook ofFaceRecognition "FacialSkin Col-orModeling"[A].Springer Pattern Recognition Book[C],2004.109-131.
[27]Ishii H,Fukumi M,Akamatsu N.Face detection based on skin color information in visual scenes by neural networks.In Proc.Systems,Man,and Cybernetics,Tokyo,Japan,1999 Vol.5:350-355
[28]Zarit B D,Super B J,Quek F K H.Comparison of five color models in skin pixel classification.In:Proc.Workshop on Recognition,Analysis,and Tracking of Faces and Gestures in Real-Time systems,Corfu,Greece,1999,58-63
[29]I.Craw,H.Ellis and J.Lishman.Automatic extraction of face features.Pattern Recognition Letters,1987,5(2):183-187
[30]Wang J G;Tan T N.A new face detection method based on shape information.Pattern Recognition Letters,2000,21(6-7):463-471.
[31]Yang G Z,Huang T S.Human face detection in a complex background.PatternRecognition,1994,27(1):53-63
[32]Lv X.G,Zhou J,Zhang C.S.A novel algorithm for rotated human face detection.In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Hilton Head Island,South Carolina,USA,2000,760-764
[33]Dai Y,Nakano Y.Face-texture model based on SGLD and its application in face detection in a color scene.Pattern Recognition,1996,29(6):1007-1017.
[34]Kouzani A Z,He F,Sammut K.Commonsense knowledge-based face detection.In: Proc. Conf. on Intelligent Engineering Systems, Budapast, Hungary, 1997, 215-220
[35] Sung K. and Poggio T. Example-based learning for view based human face detection. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1): 39-51
[36] 梁路宏、艾海舟、徐光档、张钹,人脸检测研究综述,计算机学报, 2002 Vol．25 No．5
[37] Yoo T.W, Oh I. S. A fast algorithm for tracking human faces based on chromatic histograms. Pattern Recognition Letters .1999, 20(10): 967-978
[38] Cai J, Goshtasby A. Detecting human faces in color images. Image and Vision Computing, 1999(1), 18: 63-75
[39] Garcia C, Tziritas G. Face detection using quantized skin color regions merging and wavelet packet analysis. IEEE Trans, on Multimedia, 1999, 1(3): 264-277
[40] Yang M H, Ahuja N. Detecting human faces in color images. In Proc. IEEE Conf. on Image Processing, Chicago, 1998, 127-139.
[41] Abdel-Mottaleb M, Elgammal A. Face detection in complex environments from color images. In: Proc. IEEE Conf. on Image Processing, Kobe, Japan, 1999,Vol.3(11-13): 622-626
[42] Wei G, Sethi I K. Face detection for image annotation. Pattern Recognition Letters, 20(1999):1313-1321
[43] Karlekar 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
[44] Wu H Y, Chen Q, Yachida M. A fuzzy-theory-based face detector. In: Proc. Conf. on Pattern Recognition, Vienna, Austria, 1996, Vol.3: 406-410
[45] Wu H Y, Chen Q, Yachida M. Face detection from color images using a fuzzy pattern matching method. IEEE Trans. Pattern Analysis and Machine Intelligence, 1999, 21(6) 557-563.
[46] Govindaraju V, Srihari S N, Sher D B. A computational model for face location.In:Proc.IEEE Conf.on Computer Vision,Osaka,Japan,1990,718-721
[47]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,清华大学学报(自然科学版),1999,39(1):101-105
[48]Miao J.,Yin B.C.,Wang K.Q.,et al.A hierachical multiscale and multiangle system for human face detection in a complex background using gravity-center template.Pattern Recognition,1999,32(10):1237-1248
[49]Moghaddam B,Pentland A.Probabilistic visual learning for object representation.IEEE Trans.Pattern Analysis and Machine Intelligence,1997,19(7),696-710
[50]Rowley H A,Baluja S,Kanade T.Rotation invariant neural network-based face detection,CMU-CS-97-201,1997.
[51]Rowley H A,Baluja S,Kanade T.Neural network-based face detection.IEEE Trans.Pattern Analysis and Machine Intelligence,.1998,20(1):23-38
[52]Rowley HA.Neural network-based face detection.Ph.D.thesis,CMU-CS-99-117,1999
[53]Rowley H A.Neural network-based face detection.Ph.D.thesis,CMU-CS-99-117,1999
[54]Schneiderman H,Kanade T.Probabilistic modeling of local appearance and spatial relationships for object recognition.In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Santa Barbara,California,1998,45-51
[55]Schneiderman H.A statistical approach to 3D object detection applied to faces and cars.PhD Thesis,CMU-RI-TR-00-06,2000
[56]Meng L,Nguyen T Q,Castanon D A.An image-based bayesian framework for face detection.In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Hilton Head Island,South Carolina,USA,2000,302-307
[57]B.E.Boser,I.M.Guyon,and V.N.Vapnik.A training algorithm for optimalmargin classifier.In:Proc.5th ACM Workshop on Computational Learning Theory,Pittsburgh,1992,144-152.
[58]S.R.Gunn.Support vector machines for classification and regression.Technical Report,Image Speech and Intelligent Systems Research group, University of Southampton, 1997.
[59] Osuna E, Freund R, Girosi F. Training support vector machines: an application to face detection. In: Proc. of Computer Vision and Pattern Recognition, Puerto Rico, 1997. 130-136
[60] Scholkopf B., et al. Fast approximation of support vector kernel expansions, and an Interpretation of Clustering as Approximation in Feature Spaces. In P. Levi, M. Schanz, R. -J. Ahlers, and F. May, Mustererkennung, Springer, Berlin, 1998, 124-132.
[61] J. C. Platt. Sequential minimal optimization: A fast algorithm for training support vector machines. Technical Report MSR-TR-98-14, 1998
[62] Viola Paul, Jones Michael. Rapid Object Detection using a Boosted Cascade of Simple Features. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Kauai, Hawaii, USA, 2001.
[63] A. Lanitis, C. J. Taylor, and T. F. Cootes, Automatic tracking, coding and reconstruction of human faces, using flexible appearance models, IEEE Electron. Lett. 30, 1994, 1578-1579.
[64] T, F. Cootes, G.J.Edwards, and C. J. Taylor, "Active Appearance Models, " Proc. 5th European Conference on Computer Vision , pp. 484-498,1998.
[65] X.W. Hou, S. Z. Li, H. J. Zhang, Q. S. Cheng. "Direct Appearance Models ". In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. Hawaii. December, 2001.
[66] PhungS. L., BouzerdoumA., ChaiD.. Skin segmentation using color pixel classification:Analysisandcomparison. IEEE Transactionson Pattern Analysisand Machine Intelligence, 2005, 27(1) :149-154
[67] Kearns M, Valiant L. G, Learning Boolean formulae for finite automata is as hard as factoring. TR-1488, Cambridge, Harvard University Aiken Computation Laboratory, 1998
[68] Schapire R. E. The Strength of weak learnability. Machine Learning, 1990(5):197-227
[69] Freund Y. Boosting a weak learning algorithm by majority. Information and Computation, 1995(121)
[70] Freund Y., Schapire R. E. A decision-theoretic generalization of online learning and an application to boosting. In Proc. Second European Conference on Computational Learning Theory, 1995.
[71] Dietterich T. G., An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting and randomization. AI Magazine, 1997(18):97-136
[72] Freund Y. An adaptive version of boosting by majority algorithm. Machine Learning. 2001(43, 3):293-318.
[73] Hansen L. K Salamon P. Neural Network Ensembles. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1990, 12(10):993-1001
[74] Krogh A, Vedelsby J, Neural Network Ensembles Cross Validation And Active Learning. In Tesauro. Touretzky D. Leen T eds. Advances in Neural Information Processing Systems, 1995(7):231-238
[75] Schapire R. E. Freund Y. Bartlett Y, Lee W. S. Boosting the margin: A New Explanation for the effectiveness of Voting Methods. The Annuals of statistics, 1998, 26(5):1651-1686.
[76] Cootes T.F., Taylor C. J., Locating Faces Using Statistical Feature Detectors [A], In: Proc. Automatic Face and Gesture Recognition[C], 1996: 204-209.
[77] Wiskott L., Fellous J.-M. Kruger N., von der Malsburg C., Face recognition by elastic bunch graph matching [J], IEEE Trans, on Pattern Analysis and Machine Intelligence, 1997, 19(7): 775-779.
[78] Kin C. Y., Cipolla R., A probabilistic framework for perceptual grouping of features for human face detection [A], In: Proc. Automatic Face and Gesture Recognition [C], 1996: 16-21.
[79] Son Lam Phung, Douglas Chai, Bouzerdoum, Skin Color Based Face Detection [A]. In: Proc. Intelligent Information Systems Conference[C], 2001: 171-176.
[80] Heisele B., Ho P., Poggio T., Face recognition with support vector machines: global versus component-based approach [A], In: Proc. Intl. Conf. On Computer Vision[C],2001(2):688-694.
[81]Kotropoulos C.,Pitas I.,Rule-based face detection in frontal views[A],In:Proc.Intl.Conf.on Acoustics,Speech and Signal Processing[C],1997(4):2537-2540.
[82]Kanade T.,Picture processing by computer complex and recognition of human faces[R],Kyoto Univ.,Dept.Inform.Sci.,1978.
[83]Brunelli R.,Poggio T.,Face recognition:features versus templates[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1993,15(10):1042-1052.
[84]Feng G.C.,Yuen P.C.,Variance projection function and its application to eye detection for human face recognition[J],Pattern Recognition Letters,1998,19:899-906.
[85]Verjak M.,Stephancic M.,An ahthropological model for automatic recognition of the male human face[J],Ann.Human Biology,1994(21):363-380.
[86]姜军,张桂林,一种基于知识的快速人脸检测方法[J],中国图象图形学报,2002,7(1):6-10。
[87]Zhang L.M.,Lenders P.,Knowledge-based eye detection for human face recognition[A],In:Proc.Knowledge-Based Intelligent Engineering Systems and Allied Technologies[C],2000(1):117-120.
[88]范宏深,倪国强,申会堂,利用几何特性及神经网络进行人脸探测技术的研究[J],光学技术,2002,28(2):105-107。
[89]Reisfeld D.,Yeshurun Y.,Robust detection of facial features by generalized symmetry[A].In:Proc.Int.Conf.on Pattern.Recognition[C],1992:117-120.
[90]Reisfeld D.,Wolfson H.,Yeshurun Y.,Context-free attentional operators:the generalized symmetry transform[J].Int.Journals of Computer Vision,1995,14:119-130.
[91]周杰,卢春雨,张长水,李衍达,基于方向对称变换的人脸定位方法[J],电子学报,1999,27(8):12-15。
[92]刘文予,潘峰,离散对称变换在人脸图像眼睛定位中的应用[J],红外与毫米波 学报, 2001, 20(5):375-380。
[93] von der Malsburg C., The correlation theory of brain function[R], Postfach: Max-Planck-Institut fur Biophysikalische Chemie, 1981.
[94] 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 link architecture [J], Computers, 1993, 42(3):300-311.
[95] Liao R., Stan Z. Li, Face recognition based on multiple facial features [A], In: Proc. Automatic Face and Gesture Recognition[C], 2000: 239-244.
[96] Zhang Q., Benveniste A., Wavelet networks [J], Neural Networks, 1992(3): 889-898.
[97] Kruger V., Sommer. G., Wavelet networks for face processing [J]. J. Opt. Soc. Am. 2002, accepted for publication.
[98] Feris R.S., Gemmell J., Toyama K., Kruger V., Hierarchical Wavelet Networks for Facial Feature Localization [A]. In: Proc. Automatic Face and Gesture Recognition[C], 2002: 118-123.
[99] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chern and Yao Tsorng Liu. Facial feature detection using geometrical face model[J]. An efficient approach, Pattern Recognition, 1998, 31(3): 273-282.
[100]Toshiaki Kondo and Hong Yan. Automatic human face detection and recognition under non-uniform illumination[J]. Pattern Recognition, 1999,32:1707-1718.
[101] Jun Miao, Baocai Yin, Kongqiao Wang, Lansun Shen and Xuecun Chen. A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template[J]. Pattern Recognition, 1999,32(7): 1237-1248.
[2]潘志庚,邹鹏程,梁荣华.基于特征人脸和肤色统计的人脸检测[J].系统仿真学报,2002,16(6).
[3]刘党辉,沈兰荪,LAM K-M,等.人脸检测研究进展[J].计算机工程与应用,2003,23(3).
[4]YANG G,HUANG TS.Human Face Detection in Complex Back-ground[J].Pattern Recongnition,1994,27(1):53-63.
[5]MIAO J,YIN BC,WANG KQ,etal.AHierarchicalMultiscale and Multiangle System forHuman Face Detection in a Complex Back-ground Using Gravity-Center Template[J].Pattern Recongnition,1999,32(7):1237-1248.
[6]WU LF,SHEN LS,JIA KB,et al.ISO/IEC JTC1 /SC29 /WG11 MPEG2000 /m6536,ImprovementofAutomaticHuman FaceDetec-tion[Sl,2000.
[7]TURKM,PENTLAND A.Eigenfaces forRecognition[J].Cognitive Neuro-science,1991,3(1):71-86.
[8]SUNG KK,POGGIO Z.Example-BasedLearing forView-Based Human Face Detection[J].IEEE Transactions on Pattern Analysis andMachine Intelligence,1998,20(1):39-51.
[9]SCHNEIDERMANH,KANADE T.ProbabilisticModeling of Local Appearance and Spatial Relationships for Object Recognition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],1998.45-51.
[10]YOO T-W,OH Ⅱ-S.A fast algorithm for tracking human faces based chromatic histograms[J].Pattern ReCognition Letters,1999,20(10):967-968.
[11]HSU R-L,ABDEL-MOTTALEBM,JAIN A-K.Face detection in color images[J].IEEE Transactions on Pattern Analysis andMa-chine Intelligence,2002,24(5):696-706.
[12]TERRILLON J-C,SHIRAZIM-N,FUKAMACHIH,et al.Com-parative Performance of Different Skin Chrominance Models and Chrominance Spaces for theAutomaticDetection of Human Faces in Color Images[A].Proceedings of the Fourth IEEE International Conference onAutomatic Face and Gesture Recognition[el,2000.54-60.
[13]Coots T.F,Taylor C.J.Locating Faces using Statistical Feature Detectors in:Proc.Automatic Face an Gesture Recognition,1996;204-209
[14]Wiskott L.,Fellous J.-M Kuger N.Von derMalsburg C.Face Recognition by elastic bunch graph matching.IEEE Trans.On Pattern Analysis and Machine Intelligence,1997,19(7);775-779
[15]kin C.Y.Cipollar R.A Probablistic Framework for perceptual grouping of features for human facedetection.In Proc.Automatic Face and Gesture Recognition,1996,16-21;
[16]艾海舟、肖习攀、徐光祜,人脸检测与检索,计算机学报,2003 Vol.26 No.07[17]王良民、张建明、詹永照、宋顺林人脸检测研究现状和发展江苏大学学报(自然科学版),2003 Vol.24 No.3
[17]Amaryllis Raouzaiou,Nicolas Tsapatsoulis,Stefanos Kollias Parameterized Facial Expression Synthesis For Videoconferencing Applications
[18]Dan Witzner Hansen,John Paulin Hansen,Mads Nielsen,Anders Sewerin Johansen and Mikkel B.Stegmann "Eye Typing using Markov and Active Appearance Models" "IEEE Workshop on Applications on Computer Vision",2002,pp.132-136.
[19]John Paulin Hansen,Dan Witzner Hansen and Anders Sewerin Johansen " Bringing Gaze-based Interaction Back to Basics" in " Universal Access In HCI",C.Stephanidis(ed.),Lawrence Erlbaum Associates.2001,pp.325-328
[20]陶亮、庄镇泉,一种基于个人身份认证的正下面人脸识别算法,中国图象图形学报A,2003 Vol.8 No.08
[21]高文金辉面部表情图像的分析与识别计算机学报.1997,20(9).-782-789
[22]Terrillon J C,Shirazi M N,Fukamachi H,et al.Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images.In:Proc.Conf.on Automatic Face and Gesture Recognition,Grenoble,France,2000,54-61.
[23]Jones M J,Rehg J M.Statistical color models with application to skin detection.In Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Fort Collins,Colorado,1999,274-280
[24]YANG J,LUW,WAIBELA.Skin-colormodeling and adaptation[A].LectureNotes in ComputerScience[C],1998.1352.
[25]陈忠林,刘智明,周激流.复杂背景图像中彩色人脸的检测[J].成都理工大学学报(自然科学版),2004,31(1):86-90.
[26]LI SZ,JAINAK.Handbook ofFaceRecognition "FacialSkin Col-orModeling"[A].Springer Pattern Recognition Book[C],2004.109-131.
[27]Ishii H,Fukumi M,Akamatsu N.Face detection based on skin color information in visual scenes by neural networks.In Proc.Systems,Man,and Cybernetics,Tokyo,Japan,1999 Vol.5:350-355
[28]Zarit B D,Super B J,Quek F K H.Comparison of five color models in skin pixel classification.In:Proc.Workshop on Recognition,Analysis,and Tracking of Faces and Gestures in Real-Time systems,Corfu,Greece,1999,58-63
[29]I.Craw,H.Ellis and J.Lishman.Automatic extraction of face features.Pattern Recognition Letters,1987,5(2):183-187
[30]Wang J G;Tan T N.A new face detection method based on shape information.Pattern Recognition Letters,2000,21(6-7):463-471.
[31]Yang G Z,Huang T S.Human face detection in a complex background.PatternRecognition,1994,27(1):53-63
[32]Lv X.G,Zhou J,Zhang C.S.A novel algorithm for rotated human face detection.In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Hilton Head Island,South Carolina,USA,2000,760-764
[33]Dai Y,Nakano Y.Face-texture model based on SGLD and its application in face detection in a color scene.Pattern Recognition,1996,29(6):1007-1017.
[34]Kouzani A Z,He F,Sammut K.Commonsense knowledge-based face detection.In: Proc. Conf. on Intelligent Engineering Systems, Budapast, Hungary, 1997, 215-220
[35] Sung K. and Poggio T. Example-based learning for view based human face detection. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1): 39-51
[36] 梁路宏、艾海舟、徐光档、张钹,人脸检测研究综述,计算机学报, 2002 Vol．25 No．5
[37] Yoo T.W, Oh I. S. A fast algorithm for tracking human faces based on chromatic histograms. Pattern Recognition Letters .1999, 20(10): 967-978
[38] Cai J, Goshtasby A. Detecting human faces in color images. Image and Vision Computing, 1999(1), 18: 63-75
[39] Garcia C, Tziritas G. Face detection using quantized skin color regions merging and wavelet packet analysis. IEEE Trans, on Multimedia, 1999, 1(3): 264-277
[40] Yang M H, Ahuja N. Detecting human faces in color images. In Proc. IEEE Conf. on Image Processing, Chicago, 1998, 127-139.
[41] Abdel-Mottaleb M, Elgammal A. Face detection in complex environments from color images. In: Proc. IEEE Conf. on Image Processing, Kobe, Japan, 1999,Vol.3(11-13): 622-626
[42] Wei G, Sethi I K. Face detection for image annotation. Pattern Recognition Letters, 20(1999):1313-1321
[43] Karlekar 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
[44] Wu H Y, Chen Q, Yachida M. A fuzzy-theory-based face detector. In: Proc. Conf. on Pattern Recognition, Vienna, Austria, 1996, Vol.3: 406-410
[45] Wu H Y, Chen Q, Yachida M. Face detection from color images using a fuzzy pattern matching method. IEEE Trans. Pattern Analysis and Machine Intelligence, 1999, 21(6) 557-563.
[46] Govindaraju V, Srihari S N, Sher D B. A computational model for face location.In:Proc.IEEE Conf.on Computer Vision,Osaka,Japan,1990,718-721
[47]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,清华大学学报(自然科学版),1999,39(1):101-105
[48]Miao J.,Yin B.C.,Wang K.Q.,et al.A hierachical multiscale and multiangle system for human face detection in a complex background using gravity-center template.Pattern Recognition,1999,32(10):1237-1248
[49]Moghaddam B,Pentland A.Probabilistic visual learning for object representation.IEEE Trans.Pattern Analysis and Machine Intelligence,1997,19(7),696-710
[50]Rowley H A,Baluja S,Kanade T.Rotation invariant neural network-based face detection,CMU-CS-97-201,1997.
[51]Rowley H A,Baluja S,Kanade T.Neural network-based face detection.IEEE Trans.Pattern Analysis and Machine Intelligence,.1998,20(1):23-38
[52]Rowley HA.Neural network-based face detection.Ph.D.thesis,CMU-CS-99-117,1999
[53]Rowley H A.Neural network-based face detection.Ph.D.thesis,CMU-CS-99-117,1999
[54]Schneiderman H,Kanade T.Probabilistic modeling of local appearance and spatial relationships for object recognition.In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Santa Barbara,California,1998,45-51
[55]Schneiderman H.A statistical approach to 3D object detection applied to faces and cars.PhD Thesis,CMU-RI-TR-00-06,2000
[56]Meng L,Nguyen T Q,Castanon D A.An image-based bayesian framework for face detection.In:Proc.IEEE Conf.on Computer Vision and Pattern Recognition,Hilton Head Island,South Carolina,USA,2000,302-307
[57]B.E.Boser,I.M.Guyon,and V.N.Vapnik.A training algorithm for optimalmargin classifier.In:Proc.5th ACM Workshop on Computational Learning Theory,Pittsburgh,1992,144-152.
[58]S.R.Gunn.Support vector machines for classification and regression.Technical Report,Image Speech and Intelligent Systems Research group, University of Southampton, 1997.
[59] Osuna E, Freund R, Girosi F. Training support vector machines: an application to face detection. In: Proc. of Computer Vision and Pattern Recognition, Puerto Rico, 1997. 130-136
[60] Scholkopf B., et al. Fast approximation of support vector kernel expansions, and an Interpretation of Clustering as Approximation in Feature Spaces. In P. Levi, M. Schanz, R. -J. Ahlers, and F. May, Mustererkennung, Springer, Berlin, 1998, 124-132.
[61] J. C. Platt. Sequential minimal optimization: A fast algorithm for training support vector machines. Technical Report MSR-TR-98-14, 1998
[62] Viola Paul, Jones Michael. Rapid Object Detection using a Boosted Cascade of Simple Features. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Kauai, Hawaii, USA, 2001.
[63] A. Lanitis, C. J. Taylor, and T. F. Cootes, Automatic tracking, coding and reconstruction of human faces, using flexible appearance models, IEEE Electron. Lett. 30, 1994, 1578-1579.
[64] T, F. Cootes, G.J.Edwards, and C. J. Taylor, "Active Appearance Models, " Proc. 5th European Conference on Computer Vision , pp. 484-498,1998.
[65] X.W. Hou, S. Z. Li, H. J. Zhang, Q. S. Cheng. "Direct Appearance Models ". In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. Hawaii. December, 2001.
[66] PhungS. L., BouzerdoumA., ChaiD.. Skin segmentation using color pixel classification:Analysisandcomparison. IEEE Transactionson Pattern Analysisand Machine Intelligence, 2005, 27(1) :149-154
[67] Kearns M, Valiant L. G, Learning Boolean formulae for finite automata is as hard as factoring. TR-1488, Cambridge, Harvard University Aiken Computation Laboratory, 1998
[68] Schapire R. E. The Strength of weak learnability. Machine Learning, 1990(5):197-227
[69] Freund Y. Boosting a weak learning algorithm by majority. Information and Computation, 1995(121)
[70] Freund Y., Schapire R. E. A decision-theoretic generalization of online learning and an application to boosting. In Proc. Second European Conference on Computational Learning Theory, 1995.
[71] Dietterich T. G., An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting and randomization. AI Magazine, 1997(18):97-136
[72] Freund Y. An adaptive version of boosting by majority algorithm. Machine Learning. 2001(43, 3):293-318.
[73] Hansen L. K Salamon P. Neural Network Ensembles. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1990, 12(10):993-1001
[74] Krogh A, Vedelsby J, Neural Network Ensembles Cross Validation And Active Learning. In Tesauro. Touretzky D. Leen T eds. Advances in Neural Information Processing Systems, 1995(7):231-238
[75] Schapire R. E. Freund Y. Bartlett Y, Lee W. S. Boosting the margin: A New Explanation for the effectiveness of Voting Methods. The Annuals of statistics, 1998, 26(5):1651-1686.
[76] Cootes T.F., Taylor C. J., Locating Faces Using Statistical Feature Detectors [A], In: Proc. Automatic Face and Gesture Recognition[C], 1996: 204-209.
[77] Wiskott L., Fellous J.-M. Kruger N., von der Malsburg C., Face recognition by elastic bunch graph matching [J], IEEE Trans, on Pattern Analysis and Machine Intelligence, 1997, 19(7): 775-779.
[78] Kin C. Y., Cipolla R., A probabilistic framework for perceptual grouping of features for human face detection [A], In: Proc. Automatic Face and Gesture Recognition [C], 1996: 16-21.
[79] Son Lam Phung, Douglas Chai, Bouzerdoum, Skin Color Based Face Detection [A]. In: Proc. Intelligent Information Systems Conference[C], 2001: 171-176.
[80] Heisele B., Ho P., Poggio T., Face recognition with support vector machines: global versus component-based approach [A], In: Proc. Intl. Conf. On Computer Vision[C],2001(2):688-694.
[81]Kotropoulos C.,Pitas I.,Rule-based face detection in frontal views[A],In:Proc.Intl.Conf.on Acoustics,Speech and Signal Processing[C],1997(4):2537-2540.
[82]Kanade T.,Picture processing by computer complex and recognition of human faces[R],Kyoto Univ.,Dept.Inform.Sci.,1978.
[83]Brunelli R.,Poggio T.,Face recognition:features versus templates[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1993,15(10):1042-1052.
[84]Feng G.C.,Yuen P.C.,Variance projection function and its application to eye detection for human face recognition[J],Pattern Recognition Letters,1998,19:899-906.
[85]Verjak M.,Stephancic M.,An ahthropological model for automatic recognition of the male human face[J],Ann.Human Biology,1994(21):363-380.
[86]姜军,张桂林,一种基于知识的快速人脸检测方法[J],中国图象图形学报,2002,7(1):6-10。
[87]Zhang L.M.,Lenders P.,Knowledge-based eye detection for human face recognition[A],In:Proc.Knowledge-Based Intelligent Engineering Systems and Allied Technologies[C],2000(1):117-120.
[88]范宏深,倪国强,申会堂,利用几何特性及神经网络进行人脸探测技术的研究[J],光学技术,2002,28(2):105-107。
[89]Reisfeld D.,Yeshurun Y.,Robust detection of facial features by generalized symmetry[A].In:Proc.Int.Conf.on Pattern.Recognition[C],1992:117-120.
[90]Reisfeld D.,Wolfson H.,Yeshurun Y.,Context-free attentional operators:the generalized symmetry transform[J].Int.Journals of Computer Vision,1995,14:119-130.
[91]周杰,卢春雨,张长水,李衍达,基于方向对称变换的人脸定位方法[J],电子学报,1999,27(8):12-15。
[92]刘文予,潘峰,离散对称变换在人脸图像眼睛定位中的应用[J],红外与毫米波 学报, 2001, 20(5):375-380。
[93] von der Malsburg C., The correlation theory of brain function[R], Postfach: Max-Planck-Institut fur Biophysikalische Chemie, 1981.
[94] 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 link architecture [J], Computers, 1993, 42(3):300-311.
[95] Liao R., Stan Z. Li, Face recognition based on multiple facial features [A], In: Proc. Automatic Face and Gesture Recognition[C], 2000: 239-244.
[96] Zhang Q., Benveniste A., Wavelet networks [J], Neural Networks, 1992(3): 889-898.
[97] Kruger V., Sommer. G., Wavelet networks for face processing [J]. J. Opt. Soc. Am. 2002, accepted for publication.
[98] Feris R.S., Gemmell J., Toyama K., Kruger V., Hierarchical Wavelet Networks for Facial Feature Localization [A]. In: Proc. Automatic Face and Gesture Recognition[C], 2002: 118-123.
[99] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chern and Yao Tsorng Liu. Facial feature detection using geometrical face model[J]. An efficient approach, Pattern Recognition, 1998, 31(3): 273-282.
[100]Toshiaki Kondo and Hong Yan. Automatic human face detection and recognition under non-uniform illumination[J]. Pattern Recognition, 1999,32:1707-1718.
[101] Jun Miao, Baocai Yin, Kongqiao Wang, Lansun Shen and Xuecun Chen. A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template[J]. Pattern Recognition, 1999,32(7): 1237-1248.