快速人脸检测与跟踪
|
摘要
人脸检测要走向实际应用,精度和速度是亟需解决的两个关键问题。经过十多年的发展,人脸检测的精度得到了大幅度的提高,但是速度却一直是阻挠人脸检测走向实用的绊脚石。因此,如何构建快速实用的人脸检测与跟踪算法是本文研究的主要问题。
本文在基于肤色分割的人脸检测系统中,将颜色恒常性算法引入到肤色分割中,较好解决了不同光照条件下的肤色分割问题。利用颜色恒常性算法估计环境光照,根据估计结果在YCbCr颜色空间中采用相应的高斯分布肤色模型,并利用动态阈值对人脸图像进行分割。实验结果表明,本文提出的算法对于非正常光照下,复杂背景的图像具有良好的分割效果。将本文算法加入到实验室基于肤色的人脸检测的程序中,比原系统的检测率提高了5.4%。
Viola提出的基于Adaboost的人脸检测算法包含三部分内容:利用积分图快速计算Harr-like特征;利用Adaboost算法将若干个弱分类器组合成一个强分类器;将训练出来的一系列强分类器串连起来,构成层叠分类器。本文在对该算法进行深入研究之后,根据人脸的边缘几何特征,在原有Adboost人脸检测算法中引入边缘方向特征(EDF),将扩展的Haar-like特征和EDF特征结合在一起,构成新的特征库,再利用Adaboost程序框架训练分类器。实验结果表明,加入边缘方向特征之后,该算法可以在比较小的训练样本上达到更高的检测率,最终训练的分类器比原分类器具有更高的检测率。
根据多媒体教学系统的应用需求,本文结合Adaboost人脸检测算法和Camshift跟踪算法,以Adaboost人脸检测算法作为人脸的初始定位,以Camshift作为后续帧的跟踪,构成在多媒体教学录制系统中实用的人脸跟踪算法。在模拟实验中,该算法取得了良好的跟踪效果。
If the face detection wants to be practical applications, accuracy and speed are the two key issues that need to be resolved. After 10 years of development, the accuracy of face detection has been significantly improved, but the speed is still a problem to cumber face detection system from being widely used. Therefore, how to build fast and practical face detection and face tracking algorithms becomes the major problem of this paper.
In this paper, we introduce color constancy algorithm into human skin segmentation to solve the problem of skin color segmentation under varying illumination. Firstly color constancy algorithm is adopted to estimate the illumination, then Gauss Skin Models and automatic-thresholding technique is used for skin-color segmentation in YCbCr color space. The experiment result shows that this method is good for skin segmentation in the image which is taken under deviant illumination and complex background. Applying this new method to our laboratory’s face detection system, the original system’s detection rate has increased by 5.4%.
The Adaboost face detection algorithm presented by Viola contains three parts: Rapid calculation of Harr-like features; Using Adaboost algorithm to combine several weak classifiers into a strong classifier; Serializing several strong classifiers to constitute the final cascade classifier. After studying this method deeply and analyzing the edge characteristics of face, we proposed an improved algorithm-adding Edge direction Feature. The EDF features and the extended Harr-like features are combined to construct new feature library, then Adaboost algorithm is used to train classifier. The experimental results show that the proposed algorithm could reach a higher detection rate on smaller training sample set, and the improved algorithm reaches higher detection rate.
Driven by application demand of Multimedia Teaching System, In this paper we combine Adaboost face detection algorithm and Camshift tracking algorithm, taking Adaboost algorithm as initial face location, and Camshift algorithm as follow-up frames tracking, to construct an effective and practical face tracking system which is very suitable for our Multimedia Teaching System. In simulation, the algorithm has achieved good results.
本文在基于肤色分割的人脸检测系统中,将颜色恒常性算法引入到肤色分割中,较好解决了不同光照条件下的肤色分割问题。利用颜色恒常性算法估计环境光照,根据估计结果在YCbCr颜色空间中采用相应的高斯分布肤色模型,并利用动态阈值对人脸图像进行分割。实验结果表明,本文提出的算法对于非正常光照下,复杂背景的图像具有良好的分割效果。将本文算法加入到实验室基于肤色的人脸检测的程序中,比原系统的检测率提高了5.4%。
Viola提出的基于Adaboost的人脸检测算法包含三部分内容:利用积分图快速计算Harr-like特征;利用Adaboost算法将若干个弱分类器组合成一个强分类器;将训练出来的一系列强分类器串连起来,构成层叠分类器。本文在对该算法进行深入研究之后,根据人脸的边缘几何特征,在原有Adboost人脸检测算法中引入边缘方向特征(EDF),将扩展的Haar-like特征和EDF特征结合在一起,构成新的特征库,再利用Adaboost程序框架训练分类器。实验结果表明,加入边缘方向特征之后,该算法可以在比较小的训练样本上达到更高的检测率,最终训练的分类器比原分类器具有更高的检测率。
根据多媒体教学系统的应用需求,本文结合Adaboost人脸检测算法和Camshift跟踪算法,以Adaboost人脸检测算法作为人脸的初始定位,以Camshift作为后续帧的跟踪,构成在多媒体教学录制系统中实用的人脸跟踪算法。在模拟实验中,该算法取得了良好的跟踪效果。
If the face detection wants to be practical applications, accuracy and speed are the two key issues that need to be resolved. After 10 years of development, the accuracy of face detection has been significantly improved, but the speed is still a problem to cumber face detection system from being widely used. Therefore, how to build fast and practical face detection and face tracking algorithms becomes the major problem of this paper.
In this paper, we introduce color constancy algorithm into human skin segmentation to solve the problem of skin color segmentation under varying illumination. Firstly color constancy algorithm is adopted to estimate the illumination, then Gauss Skin Models and automatic-thresholding technique is used for skin-color segmentation in YCbCr color space. The experiment result shows that this method is good for skin segmentation in the image which is taken under deviant illumination and complex background. Applying this new method to our laboratory’s face detection system, the original system’s detection rate has increased by 5.4%.
The Adaboost face detection algorithm presented by Viola contains three parts: Rapid calculation of Harr-like features; Using Adaboost algorithm to combine several weak classifiers into a strong classifier; Serializing several strong classifiers to constitute the final cascade classifier. After studying this method deeply and analyzing the edge characteristics of face, we proposed an improved algorithm-adding Edge direction Feature. The EDF features and the extended Harr-like features are combined to construct new feature library, then Adaboost algorithm is used to train classifier. The experimental results show that the proposed algorithm could reach a higher detection rate on smaller training sample set, and the improved algorithm reaches higher detection rate.
Driven by application demand of Multimedia Teaching System, In this paper we combine Adaboost face detection algorithm and Camshift tracking algorithm, taking Adaboost algorithm as initial face location, and Camshift algorithm as follow-up frames tracking, to construct an effective and practical face tracking system which is very suitable for our Multimedia Teaching System. In simulation, the algorithm has achieved good results.
引文
[1] M. H. Yang, D. Kriegman, N. Ahuja. Detecting faces in images a survey. IEEE Trans. PAMI. 2002,24(1):34-58
[2] Erik Hjelmas, Boon Kee Low. Face Detection: A Survey. Computer Vision and Image Understanding. 2001, 83(3):236-274
[3] 刘党辉,沈兰荪,Kin-Man Lam,人脸检测研究进展,计算机工程与应用. 2003, 39(28):5-9
[4] 梁路宏,艾海舟,徐光枯等,人脸检测研究综述.计算机学报,2002, 25(5):449-458
[5] Center for Biometrics and Security Research, the Institute of Automation, Chinese Academy of Sciences. The emerging gait recognition[J].China Public Security,2003,(6):43
[6] 沈兰荪,卓力等,视频编码与低速率传输,电子工业出版社
[7] M. Flickner et al. Query by Image and Video Content: The QBIC System. IEEE Computer. 1995, 28:23-32
[8] MPEG-7 Applications Document V8.ISOIIEC JTCIISC29fWGII N2728[S]. Seoul, Korea, 1999.3
[9] Craw I, Ellis H, Lishman J R, Automatic extraction of face feature, Pattern Recognition Letters, 1987, 5(2): 183-187
[10] Wang J, Tan T, A new face detection method based on shape information, Pattern Recognition Letters, 2000, 21(6-7): 463-471.
[11] 杨光正,黄煦涛,镶嵌图在人面定位中的应用,模式识别与人工智能,1996,9 ( 3): 213-220
[12] Lu X, Zhou J, Zhang C, A novel algorithm for rotated human face detection, In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, South Carolina, USA, 2000, pp.760-764.
[13] 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.
[14] Yang J, Stiefelhagen R, Meier U, et al. Visual tracking for multimodal human computer interaction, In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 1998, pp.140-147
[15] Chen Q, Wu H and Yachida M. Face detection by fuzzy pattern matching. Proc. 5th International Conference on Computer Vision, Cambridge, Massachusetts, USA, 591-596
[16] Dai. Y and Nakano. Y. Extraction for facial images from complex background using color information and SGLD matrices, Proc. 1st International Workshop on Automatic Face and Gesture Recognition, Zurich, Switzerland, 238-242
[17] M.Kapfer and J.Benois-Pineau, Detection of human faces in color image sequences with arbitrary motions for very low bit-rate videophone coding, Pattern Recog. Lett. 18,1997
[18] M. Yang and N. Ahuja. Detecting human faces in color images. In International Conference on Automatic Face and Gesture Recognition, 446-453
[19] C.Garcia and G. Tziritas, Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis, IEEE transactions on multimedia, 1999,1(3):264-277
[20] Zabrodsky H, Peleg S, Avnir D, Symmetry as a continuous feature, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(12): 1154 1166.
[21] Reisfeld D, Yeshurun Y, Robust detection of facial features by generalized symmetry, In Proceedings of the International Conference on Pattern Recognition, Hague, Netherlands, 1992, pp.117-120.
[22] Yow K-C, Cipolla R. Feature-based human face detection. Image and Vision Computing.1997, 15(9): 713-735
[23] Han C-C, Liao H-Y, Yu G-J, Chen L-H, Fast face detection via morphology-based pre-processing, Pattern Recognition, 2000, 33(10):1701-1712
[24] Bruneli R, Poggio T. Face recognition: Features versus templates, IEEE Transactions on pattern analysis and machine intelligence, 1993, 15(10): 1042-1052
[25] Yullie A, Hallinan P, Cohen D. Feature exaction from faces using deformable templates. International Journal of Computing Vision, 1992, 8(2):99-111
[26] Moghaddam B, Pentland A, Probabilistic visual learning for object representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 696-710.
[27] Martinez A, Kak A, PCA versus LDA, IEEE Transactions on Pattern Analysisand Machine Intelligence, 2001, 23 (2): 228-233.
[28] M. H. Yang, D. Kriegman, and N. Ahuja. Face Detection Using Multimodal Density Models, Computer Vision Understanding, 2001(84):264-284
[29] Samson C, Blanc-Feraud L, Aubert G, et al. Level set model for image classification, International Journal of Computer Vision, 2000, 40(3): 187-197.
[30] Juell P, Marsh R, A hierarchical neural network for human face detection, Pattern Recognition, 1996, 29(5): 781-187.
[31] Sung K K, Poggio T, Example-based learning for view-based human face detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1): 39-50.
[32] Roth D, Yang M-H, Ahuja N, A Snow-based face detector, In Advances in Neural Information Processing Systems 12, MIT Press, Cambridge, MA, 2000, pp.855-861.
[33] Nefian Ara V, Hayes Monson H III, Face detection and recognition using hidden Markov models, In Proceedings of the International Conference on Image Processing, Chicago, Illinois, USA, 1998, pp.141-145.
[34] Osuna E, Freund R, Gorosi F, Training support vector machines: An application to face detection, In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, 1997, pp.130-136.
[35] Schneiderman H, Kanade T, A statistical model for 3D object detection applied to faces and cars, In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, South Carolina, USA, 2000, pp.746-751.
[36] 艾海舟,王栓,何克忠,基于差分图像的人脸检测,中国图象图形学报,1998,3(12):987-992
[37] Decarlo D, Metaxas D, Optical flow constraints on deformable models with applications to face tracking, International Journal of Computer Vision, 2000, 38(2): 99-127
[38] Birchfield S, An elliptical head tracker, In 31st Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, 1997, pp.1710-1714.
[39] 刘万春,贾云得,徐一华等,基于肤色的人脸实时跟踪方法,北京理工大学学报,2000,20(4): 461-465
[40] 邢昕,汪孔桥,沈兰荪,基于器官跟踪的人脸实时跟踪方法,电子学报,2000,28(6):29-31
[41] Yang J, Waibel A, Real-time face tracker, In IEEE Workshop on Applications of Computer Vision, Sarasota, Florida, USA, 1996, pp.142-147.
[42] M-H Yang, D. Kriegman and N. Ahuja, "Detecting Face in Images: A Survey", IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 34-58, January, 2002.
[43] 游亚平,李明,袁保宗,可变光照下的人脸检测,信号处理,2004, 20(2): 101-107.
[44] Hsu RL, Abdel-Mottaleb M,A K Jain. Face detection in color images. IEEE Trans.Pattern Analysis and Machine Intelligence, vol24, o.5, pp.696~706,May 2002
[45] Quan Huynh-Thu, Mitsuhiko Meguro, Masahide Kaneko, "Skin-Color Extraction in Images with Complex Background and Varying Illumination", in Proceedings of IEEE Workshop on Applications of Computer-Vision, pp 280-285, USA, Dec 2002.
[46] Martinkauppi B. Face colour under varying illumination-analysis and applications. PhD thesis , University of Oulu, 2002.
[47] D.A.Forsyth, “A Novel Algorithm for Colour Constancy ” Computer Vision, vol.5, no.1, pp.5-36,1990
[48] Finlayson G, Hordley S. Improving gamut mapping color constancy. IEEE Transactions On Image Processing, 2000, 9(10):1774～1783
[49] Klinker GJ, Shafer SA, Kanade T. A physical approach to color image understanding. International Journal of Computer Vision,1990,4(1):7~38
[50] G. Finlayson, S. Hordley, P. M. Hubel "Color by Correlation: A Simple, Unifying Framework for Color Constancy", IEEE Trans. on Pattern Analysis And Machine Intelligence, Vol. 23, No. 11, pp. 1209-1221, 2001
[51] J.Cai and A Goshtasby. Detecting Human Faces in Color Images. Image and Vision Computing, 18:63-75,Feb 1999.
[52] P.Viola and M.Jones. “Rapid object detection using a boosted cascade of simple features”. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, December 12-14,2001.
[53] P.Viola and M.Jones. “Robust real time object detection”. In IEEE ICCVWorkshop on Statistical and Computational Theories of Vision, Vancouver, Canada,July 13,2001.
[54] Constantine P. Papageorgiou, Michael Oren, Tomaso Poggio. A General Framework for Object Detection. Proceedings of International Conference on Computer Vision. January 1998.
[55] Mohan,C.Papageorgiou, T.Poggio. Example-based object detection in images by components. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.23, No.4, pp.349-361, April 2001.
[56] Rainer Lienhart and Jochen Maydt, A Extended Set of Harr-like Features for Rapid Object Detection, IEEE ICIP 2002, Vol.1, pp 900-903, 2002.
[57] Freund Y, Schapire R E, A Decision-Theoretic Generalization of On Line Learning and An Application to Boosting. Journal of Computer and System Science, 1997, 55(1):119-139.
[58] W. Freeman and M. Roth. Orientation histogram for hand gesture recognition. In Int’l Workshop on Automatic Face and Gesture Recognition, 1995
[59] D. G. Lowe. Object recognition from local scaleinvariant features. In Proceedings of the International Conference on Computer Vision-Volume 2, page 1150.IEEE Computer Society, 1999.
[60] M. Bichsel. Strategies of robust object recogni-tion for the automatic identi_cation of human faces. PhD thesis, ETH Zurich, 1991
[61] T.Jebara, K.Russel and A.Pentland. “Mixture of Eigenfeatures for Real-Time Structure for Texture”. Tech Report-440, MIT Media Lab, 1998
[62] Garcia, Zikos, Tziritas. Wavelet packet analysis for face recognition, Image and Vision Computing, Volume:18, Issue:4, March 1,2000, pp.289-297
[63] Horn B.K.P, Schunck B.G Determining optical flow. Artificial Intelligence,1981, 17:185-204.
[64] Bradski G R. Computer Video Face Tracking for use in a Perceptual User Interface. Proceedings of IEEE Workshop Application of Computer Vision. Princeton, NJ: IEEE, 1998: 241-219
[2] Erik Hjelmas, Boon Kee Low. Face Detection: A Survey. Computer Vision and Image Understanding. 2001, 83(3):236-274
[3] 刘党辉,沈兰荪,Kin-Man Lam,人脸检测研究进展,计算机工程与应用. 2003, 39(28):5-9
[4] 梁路宏,艾海舟,徐光枯等,人脸检测研究综述.计算机学报,2002, 25(5):449-458
[5] Center for Biometrics and Security Research, the Institute of Automation, Chinese Academy of Sciences. The emerging gait recognition[J].China Public Security,2003,(6):43
[6] 沈兰荪,卓力等,视频编码与低速率传输,电子工业出版社
[7] M. Flickner et al. Query by Image and Video Content: The QBIC System. IEEE Computer. 1995, 28:23-32
[8] MPEG-7 Applications Document V8.ISOIIEC JTCIISC29fWGII N2728[S]. Seoul, Korea, 1999.3
[9] Craw I, Ellis H, Lishman J R, Automatic extraction of face feature, Pattern Recognition Letters, 1987, 5(2): 183-187
[10] Wang J, Tan T, A new face detection method based on shape information, Pattern Recognition Letters, 2000, 21(6-7): 463-471.
[11] 杨光正,黄煦涛,镶嵌图在人面定位中的应用,模式识别与人工智能,1996,9 ( 3): 213-220
[12] Lu X, Zhou J, Zhang C, A novel algorithm for rotated human face detection, In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, South Carolina, USA, 2000, pp.760-764.
[13] 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.
[14] Yang J, Stiefelhagen R, Meier U, et al. Visual tracking for multimodal human computer interaction, In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 1998, pp.140-147
[15] Chen Q, Wu H and Yachida M. Face detection by fuzzy pattern matching. Proc. 5th International Conference on Computer Vision, Cambridge, Massachusetts, USA, 591-596
[16] Dai. Y and Nakano. Y. Extraction for facial images from complex background using color information and SGLD matrices, Proc. 1st International Workshop on Automatic Face and Gesture Recognition, Zurich, Switzerland, 238-242
[17] M.Kapfer and J.Benois-Pineau, Detection of human faces in color image sequences with arbitrary motions for very low bit-rate videophone coding, Pattern Recog. Lett. 18,1997
[18] M. Yang and N. Ahuja. Detecting human faces in color images. In International Conference on Automatic Face and Gesture Recognition, 446-453
[19] C.Garcia and G. Tziritas, Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis, IEEE transactions on multimedia, 1999,1(3):264-277
[20] Zabrodsky H, Peleg S, Avnir D, Symmetry as a continuous feature, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(12): 1154 1166.
[21] Reisfeld D, Yeshurun Y, Robust detection of facial features by generalized symmetry, In Proceedings of the International Conference on Pattern Recognition, Hague, Netherlands, 1992, pp.117-120.
[22] Yow K-C, Cipolla R. Feature-based human face detection. Image and Vision Computing.1997, 15(9): 713-735
[23] Han C-C, Liao H-Y, Yu G-J, Chen L-H, Fast face detection via morphology-based pre-processing, Pattern Recognition, 2000, 33(10):1701-1712
[24] Bruneli R, Poggio T. Face recognition: Features versus templates, IEEE Transactions on pattern analysis and machine intelligence, 1993, 15(10): 1042-1052
[25] Yullie A, Hallinan P, Cohen D. Feature exaction from faces using deformable templates. International Journal of Computing Vision, 1992, 8(2):99-111
[26] Moghaddam B, Pentland A, Probabilistic visual learning for object representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 696-710.
[27] Martinez A, Kak A, PCA versus LDA, IEEE Transactions on Pattern Analysisand Machine Intelligence, 2001, 23 (2): 228-233.
[28] M. H. Yang, D. Kriegman, and N. Ahuja. Face Detection Using Multimodal Density Models, Computer Vision Understanding, 2001(84):264-284
[29] Samson C, Blanc-Feraud L, Aubert G, et al. Level set model for image classification, International Journal of Computer Vision, 2000, 40(3): 187-197.
[30] Juell P, Marsh R, A hierarchical neural network for human face detection, Pattern Recognition, 1996, 29(5): 781-187.
[31] Sung K K, Poggio T, Example-based learning for view-based human face detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1): 39-50.
[32] Roth D, Yang M-H, Ahuja N, A Snow-based face detector, In Advances in Neural Information Processing Systems 12, MIT Press, Cambridge, MA, 2000, pp.855-861.
[33] Nefian Ara V, Hayes Monson H III, Face detection and recognition using hidden Markov models, In Proceedings of the International Conference on Image Processing, Chicago, Illinois, USA, 1998, pp.141-145.
[34] Osuna E, Freund R, Gorosi F, Training support vector machines: An application to face detection, In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, 1997, pp.130-136.
[35] Schneiderman H, Kanade T, A statistical model for 3D object detection applied to faces and cars, In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, South Carolina, USA, 2000, pp.746-751.
[36] 艾海舟,王栓,何克忠,基于差分图像的人脸检测,中国图象图形学报,1998,3(12):987-992
[37] Decarlo D, Metaxas D, Optical flow constraints on deformable models with applications to face tracking, International Journal of Computer Vision, 2000, 38(2): 99-127
[38] Birchfield S, An elliptical head tracker, In 31st Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, 1997, pp.1710-1714.
[39] 刘万春,贾云得,徐一华等,基于肤色的人脸实时跟踪方法,北京理工大学学报,2000,20(4): 461-465
[40] 邢昕,汪孔桥,沈兰荪,基于器官跟踪的人脸实时跟踪方法,电子学报,2000,28(6):29-31
[41] Yang J, Waibel A, Real-time face tracker, In IEEE Workshop on Applications of Computer Vision, Sarasota, Florida, USA, 1996, pp.142-147.
[42] M-H Yang, D. Kriegman and N. Ahuja, "Detecting Face in Images: A Survey", IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 34-58, January, 2002.
[43] 游亚平,李明,袁保宗,可变光照下的人脸检测,信号处理,2004, 20(2): 101-107.
[44] Hsu RL, Abdel-Mottaleb M,A K Jain. Face detection in color images. IEEE Trans.Pattern Analysis and Machine Intelligence, vol24, o.5, pp.696~706,May 2002
[45] Quan Huynh-Thu, Mitsuhiko Meguro, Masahide Kaneko, "Skin-Color Extraction in Images with Complex Background and Varying Illumination", in Proceedings of IEEE Workshop on Applications of Computer-Vision, pp 280-285, USA, Dec 2002.
[46] Martinkauppi B. Face colour under varying illumination-analysis and applications. PhD thesis , University of Oulu, 2002.
[47] D.A.Forsyth, “A Novel Algorithm for Colour Constancy ” Computer Vision, vol.5, no.1, pp.5-36,1990
[48] Finlayson G, Hordley S. Improving gamut mapping color constancy. IEEE Transactions On Image Processing, 2000, 9(10):1774～1783
[49] Klinker GJ, Shafer SA, Kanade T. A physical approach to color image understanding. International Journal of Computer Vision,1990,4(1):7~38
[50] G. Finlayson, S. Hordley, P. M. Hubel "Color by Correlation: A Simple, Unifying Framework for Color Constancy", IEEE Trans. on Pattern Analysis And Machine Intelligence, Vol. 23, No. 11, pp. 1209-1221, 2001
[51] J.Cai and A Goshtasby. Detecting Human Faces in Color Images. Image and Vision Computing, 18:63-75,Feb 1999.
[52] P.Viola and M.Jones. “Rapid object detection using a boosted cascade of simple features”. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, December 12-14,2001.
[53] P.Viola and M.Jones. “Robust real time object detection”. In IEEE ICCVWorkshop on Statistical and Computational Theories of Vision, Vancouver, Canada,July 13,2001.
[54] Constantine P. Papageorgiou, Michael Oren, Tomaso Poggio. A General Framework for Object Detection. Proceedings of International Conference on Computer Vision. January 1998.
[55] Mohan,C.Papageorgiou, T.Poggio. Example-based object detection in images by components. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.23, No.4, pp.349-361, April 2001.
[56] Rainer Lienhart and Jochen Maydt, A Extended Set of Harr-like Features for Rapid Object Detection, IEEE ICIP 2002, Vol.1, pp 900-903, 2002.
[57] Freund Y, Schapire R E, A Decision-Theoretic Generalization of On Line Learning and An Application to Boosting. Journal of Computer and System Science, 1997, 55(1):119-139.
[58] W. Freeman and M. Roth. Orientation histogram for hand gesture recognition. In Int’l Workshop on Automatic Face and Gesture Recognition, 1995
[59] D. G. Lowe. Object recognition from local scaleinvariant features. In Proceedings of the International Conference on Computer Vision-Volume 2, page 1150.IEEE Computer Society, 1999.
[60] M. Bichsel. Strategies of robust object recogni-tion for the automatic identi_cation of human faces. PhD thesis, ETH Zurich, 1991
[61] T.Jebara, K.Russel and A.Pentland. “Mixture of Eigenfeatures for Real-Time Structure for Texture”. Tech Report-440, MIT Media Lab, 1998
[62] Garcia, Zikos, Tziritas. Wavelet packet analysis for face recognition, Image and Vision Computing, Volume:18, Issue:4, March 1,2000, pp.289-297
[63] Horn B.K.P, Schunck B.G Determining optical flow. Artificial Intelligence,1981, 17:185-204.
[64] Bradski G R. Computer Video Face Tracking for use in a Perceptual User Interface. Proceedings of IEEE Workshop Application of Computer Vision. Princeton, NJ: IEEE, 1998: 241-219