基于K-L变换与模板匹配的彩色图像人脸定位
|
摘要
人脸自动识别技术有广阔的应用前景和迫切的现实要求，是当前模式识别领域最热门的研究方向之一。人脸是一种复杂的模式，从背景中定位人脸是一件非常困难的事，其难度不小于人脸识别本身。研究人员对人脸识别作了大量的研究，但对复杂图像人脸定位的研究却不多。本文首先对人脸定位和人脸识别的意义、人脸定位和人脸识别的发展作了概括性的介绍；然后对一些基本理论作了简单的介绍，紧接着对人脸定位的方法做了全面的论述。
本文第四章提出了一种基于简单背景的人眼定位算法，用小波变换对人脸图像进行边缘检测，对得到的结果进行行列统计，得到人脸的大致位置，再用模板匹配进行最后的精确定位。
在本文最后提出了一种在静态图像中定位出人脸的方法，此方法对图像没有任何限制，对人脸的个数、大小、位置、方向也没有任何限制。具体就是利用K-L变换将肤色样本和非肤色样本的RGB三种颜色分量重新构造了一个颜色空间，肤色空间和非肤色空间在该空间的距离得到拉伸，因此，两类样本具有良好的可分性，从而实现了肤色区域和非肤色区域的分割。最后，利用自定义的模板来实现人脸的定位。通过实验仿真证明，此方法能够较好的实现了人脸定位。
Automatic human face recognition is attractive in pattern recognition and image procession. The human face is a complex pattern. It is very diffcult that locate face in complex background. It is even harder than face recognition. Many researches have been done upon face recognition, more effort need to be directed in face location problem. In this paper , first , a survey of human face location and recognition is given. Then, it introduces the developments of the human location and recognition. Afterword, it discussed the basis theory and method.
In chapter IV , a new method of eyes location is provided. It detects the edg of human face image with wavelet transform in the first. Then it begins to statistic the gray value of the row and list. So we can get approximate position. At last we can get accurate position with template maching.
At last, a method of location face in the static image is provided without any limitation upon images , or any condition about number, size, position and orientation of faces. A new color space is drived from RGB color format of the skin colors and other background colors with K~L transforms. The distance between the skin color and the background colors is increased in this color space. So we can segment the skin regions from one image. Then we match with templates that was difined by myself. At last we can get the position of the human face. The experiment result shows that this method finishes the human faces location.
本文第四章提出了一种基于简单背景的人眼定位算法，用小波变换对人脸图像进行边缘检测，对得到的结果进行行列统计，得到人脸的大致位置，再用模板匹配进行最后的精确定位。
在本文最后提出了一种在静态图像中定位出人脸的方法，此方法对图像没有任何限制，对人脸的个数、大小、位置、方向也没有任何限制。具体就是利用K-L变换将肤色样本和非肤色样本的RGB三种颜色分量重新构造了一个颜色空间，肤色空间和非肤色空间在该空间的距离得到拉伸，因此，两类样本具有良好的可分性，从而实现了肤色区域和非肤色区域的分割。最后，利用自定义的模板来实现人脸的定位。通过实验仿真证明，此方法能够较好的实现了人脸定位。
Automatic human face recognition is attractive in pattern recognition and image procession. The human face is a complex pattern. It is very diffcult that locate face in complex background. It is even harder than face recognition. Many researches have been done upon face recognition, more effort need to be directed in face location problem. In this paper , first , a survey of human face location and recognition is given. Then, it introduces the developments of the human location and recognition. Afterword, it discussed the basis theory and method.
In chapter IV , a new method of eyes location is provided. It detects the edg of human face image with wavelet transform in the first. Then it begins to statistic the gray value of the row and list. So we can get approximate position. At last we can get accurate position with template maching.
At last, a method of location face in the static image is provided without any limitation upon images , or any condition about number, size, position and orientation of faces. A new color space is drived from RGB color format of the skin colors and other background colors with K~L transforms. The distance between the skin color and the background colors is increased in this color space. So we can segment the skin regions from one image. Then we match with templates that was difined by myself. At last we can get the position of the human face. The experiment result shows that this method finishes the human faces location.
引文
(1) 李在铭等，数字图像处理、压缩与识别技术，电子科技大学出版社；
(2) 康学雷等，一种基于肤色和模板的人脸定位方法，红外与毫米波学报，2000年6月vol19，209-214；
(3) 周宗恒等，基于KL肤色的人脸初定位，计算机工程，2001年4月vol 27，109-111；
(4) 艾海舟等，基于肤色和模板的人脸定位，软件学报，2001年12月vol 12 1784-1791；
(5) 周长发，精通Visual C++图像编程，电子工业出版社
(6) 章毓，图像处理与分析，晋清华大学出版社，1996
(7) 邢藏菊，人脸自动方法研究，硕士学位论文，2001
(8) 王宇光，应用小波变换和K-L变换的人脸识别方法研究，上海交通大学硕士学位论文，2001
(9) John E．Swanke，Visual C++ MFC编程实例，机械工业出版社 2000
(10) 刘长明等，Visual C++实践与提高(多媒体篇)，中国铁道出版社，2001
(11) 何斌等，Visual C++数字图像处理，人民邮电出版社，2002
(12) 李世雄，小波变换及其应用，高等教育出版社，1997
(13) 杨福生，小波变换的工程分析与应用，科学出版社，1999
(14) 胡昌平，基于MATLAB的系统分析与设计——小波分析，西安电子科技大学出版社，1999
(15) 吕凤军，数字图像处理编程入门，清华大学出版社 1999
(16) 崔屹，图像处理与分析——数学形态学方法及应用，科学出版社，2000
(17) 周杰等，人脸自动识别方法综述电子学报，2000．4 vol 28，No．4
(18) 边肇祺，模式识别，清华大学出版社 2000
(19) 彭辉，人脸自动定位与识别方法研究清华大学博士学位论文，1998
(20) 吕凤军，基于肤色和特征脸的人脸定位，清华大学硕士学位论文。2000
(21) 彭玉华，小波变换与工程应用，科学出版社 2000
(22) 杨光正，黄熙涛，镶嵌图在人脸定位中的应用，模式识别与人工智能，Vol9 No3，1996
(23) Dario Maio, Davide Maltoni, Real-time face location on gray-scal static image, Pattern Recognition 33(2000) 1525-1539
(24) A. Jacquin; A. Eleftheriadis. Automatic location tracking of faces and facial features in video sequences. Proc. Int. Workshop on Automatic Face and Gesture-Recognition, M. Bichsel(ed.),Zurich, 1995, p142-147.
(25) Antonio J. Colmenarez;Thomas S. Huang. Frontal view face dection. http://www.ifp. uiuc. edu/~antonio/vcip95. ps
(26) Antonio J. Colmenarez;Thomas S. Huang. Face Dection and Recognition. http://www.ifp.uiuc.edu/~antonio/nato.ps
(27) A. Pentland;B. Moghaddam;T.Starner;M. Turk. View-based and modular eigenspaces for face recognition. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 1994, p84~91．
(28) http://www.csdn. net.
(29) A. Samal ;P.Iyengar. Automatic recognition and analysis of human faces and facial expressions: A survey. Pattern Recognition, vo125, 1992, p65~77．
(30) Dai, Y;Y. Nakano;H. Miyao. Extraction of Facial Image from a Complex Background Using SGLD Matrices.Proceedings of the 12th International Conference on Pattern Recognition, 1994, p137~141．
(31) D. Valentin;H. Abdi. Categorization and identification of human face images by neural netwoks: a review of the linear autoassociative and principal component approaches,Journal of Biological Systems 2, 1994, p413-429．
(32) Ferdinando Silvestro Samaria. Face Recognition Using Hidden Markov Models. Doctor Dissertion, at University of Cambridge.
(33) F. Smeraldi;A. Makarov; J. Bigun. Saccadic Search with Gabor features applied to Eye detection.
(34) Govindaraju,Venu.Location human faces in photographs.International Journal of Computer Vision vol 19, 1996,p129~146
(35) H. Abdi;D. Valentin;B. Edelman. More about the difference between men and women: evidence from linear networks and principal components approach, Perception, vol 24 ,1995, p539-562．
(37) Henry A. Rowley;Shumeet Baluja;Takeo Kanade. Human face detection in visual scenes.CMU-CS-95-158R,Carnegie Mellon University, November 1995．
(38) Jay P. Kapur. Face Detection in Color Images, weber. u. Washington. edu/~jaypk/face. html.
(39) Kin Choong Yow;Roberto Cipolla.Finding Initial Estimatres of Human Face Location.
(39) Kin Choong Yow;Roberto Cipolla. Scale and Orientation Invariance in Human Face Location.
(40) Kin Choong Yow;Roberto Cipolla.Towards an Automatic Human Face Location.
(41) Kin Choong Yow;Roberto Cipolla.A Probabilistic Framework for Perceptual Grouping of Features for Human Face Detection.
(42) M. C.Burr;T. K.Leung;P. Perona.Face localization via Shape Statistics.Proc. Int.Workshop on Automatic Face and Gesture-Recognition, M. Bichsel(ed.), Zurich, 1995,p154-159
(43) Michael S. Lew;Dr. Nies Hui jsmans; Roel Hoogenboom.Face Detection and Recognition
http://www. wi. leidenuniv. nl/home/lim/Leiden_face. htm
(44) Pal, N. ;K. Pal.A Review on Image Segmentation Technique .Pattern Recognition, vol. 26, 1993, p1277-1294
(45) Peter N. Belhumeur; Joao P. Hespanha;David J. Kriegman. Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection . 1996 European Conference on Computer Vision.
(46) P.JB. Hancock;A. M.Burton;V. Bruce. Face processing: human perception and principal component analysis.Memory and Cognition, 1996
(47) Shio, A. ;J. Sklansky. Segmentation of people in motion.Proceedings of the IEEE Workshop on Visual Motion, 1991,p325-332．
(48) Yang, Guangzheng;Huang, Thomas S. Human face detection in a complex background. Pttern Recognition, Vol.27 No.1,1994．
(2) 康学雷等，一种基于肤色和模板的人脸定位方法，红外与毫米波学报，2000年6月vol19，209-214；
(3) 周宗恒等，基于KL肤色的人脸初定位，计算机工程，2001年4月vol 27，109-111；
(4) 艾海舟等，基于肤色和模板的人脸定位，软件学报，2001年12月vol 12 1784-1791；
(5) 周长发，精通Visual C++图像编程，电子工业出版社
(6) 章毓，图像处理与分析，晋清华大学出版社，1996
(7) 邢藏菊，人脸自动方法研究，硕士学位论文，2001
(8) 王宇光，应用小波变换和K-L变换的人脸识别方法研究，上海交通大学硕士学位论文，2001
(9) John E．Swanke，Visual C++ MFC编程实例，机械工业出版社 2000
(10) 刘长明等，Visual C++实践与提高(多媒体篇)，中国铁道出版社，2001
(11) 何斌等，Visual C++数字图像处理，人民邮电出版社，2002
(12) 李世雄，小波变换及其应用，高等教育出版社，1997
(13) 杨福生，小波变换的工程分析与应用，科学出版社，1999
(14) 胡昌平，基于MATLAB的系统分析与设计——小波分析，西安电子科技大学出版社，1999
(15) 吕凤军，数字图像处理编程入门，清华大学出版社 1999
(16) 崔屹，图像处理与分析——数学形态学方法及应用，科学出版社，2000
(17) 周杰等，人脸自动识别方法综述电子学报，2000．4 vol 28，No．4
(18) 边肇祺，模式识别，清华大学出版社 2000
(19) 彭辉，人脸自动定位与识别方法研究清华大学博士学位论文，1998
(20) 吕凤军，基于肤色和特征脸的人脸定位，清华大学硕士学位论文。2000
(21) 彭玉华，小波变换与工程应用，科学出版社 2000
(22) 杨光正，黄熙涛，镶嵌图在人脸定位中的应用，模式识别与人工智能，Vol9 No3，1996
(23) Dario Maio, Davide Maltoni, Real-time face location on gray-scal static image, Pattern Recognition 33(2000) 1525-1539
(24) A. Jacquin; A. Eleftheriadis. Automatic location tracking of faces and facial features in video sequences. Proc. Int. Workshop on Automatic Face and Gesture-Recognition, M. Bichsel(ed.),Zurich, 1995, p142-147.
(25) Antonio J. Colmenarez;Thomas S. Huang. Frontal view face dection. http://www.ifp. uiuc. edu/~antonio/vcip95. ps
(26) Antonio J. Colmenarez;Thomas S. Huang. Face Dection and Recognition. http://www.ifp.uiuc.edu/~antonio/nato.ps
(27) A. Pentland;B. Moghaddam;T.Starner;M. Turk. View-based and modular eigenspaces for face recognition. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 1994, p84~91．
(28) http://www.csdn. net.
(29) A. Samal ;P.Iyengar. Automatic recognition and analysis of human faces and facial expressions: A survey. Pattern Recognition, vo125, 1992, p65~77．
(30) Dai, Y;Y. Nakano;H. Miyao. Extraction of Facial Image from a Complex Background Using SGLD Matrices.Proceedings of the 12th International Conference on Pattern Recognition, 1994, p137~141．
(31) D. Valentin;H. Abdi. Categorization and identification of human face images by neural netwoks: a review of the linear autoassociative and principal component approaches,Journal of Biological Systems 2, 1994, p413-429．
(32) Ferdinando Silvestro Samaria. Face Recognition Using Hidden Markov Models. Doctor Dissertion, at University of Cambridge.
(33) F. Smeraldi;A. Makarov; J. Bigun. Saccadic Search with Gabor features applied to Eye detection.
(34) Govindaraju,Venu.Location human faces in photographs.International Journal of Computer Vision vol 19, 1996,p129~146
(35) H. Abdi;D. Valentin;B. Edelman. More about the difference between men and women: evidence from linear networks and principal components approach, Perception, vol 24 ,1995, p539-562．
(37) Henry A. Rowley;Shumeet Baluja;Takeo Kanade. Human face detection in visual scenes.CMU-CS-95-158R,Carnegie Mellon University, November 1995．
(38) Jay P. Kapur. Face Detection in Color Images, weber. u. Washington. edu/~jaypk/face. html.
(39) Kin Choong Yow;Roberto Cipolla.Finding Initial Estimatres of Human Face Location.
(39) Kin Choong Yow;Roberto Cipolla. Scale and Orientation Invariance in Human Face Location.
(40) Kin Choong Yow;Roberto Cipolla.Towards an Automatic Human Face Location.
(41) Kin Choong Yow;Roberto Cipolla.A Probabilistic Framework for Perceptual Grouping of Features for Human Face Detection.
(42) M. C.Burr;T. K.Leung;P. Perona.Face localization via Shape Statistics.Proc. Int.Workshop on Automatic Face and Gesture-Recognition, M. Bichsel(ed.), Zurich, 1995,p154-159
(43) Michael S. Lew;Dr. Nies Hui jsmans; Roel Hoogenboom.Face Detection and Recognition
http://www. wi. leidenuniv. nl/home/lim/Leiden_face. htm
(44) Pal, N. ;K. Pal.A Review on Image Segmentation Technique .Pattern Recognition, vol. 26, 1993, p1277-1294
(45) Peter N. Belhumeur; Joao P. Hespanha;David J. Kriegman. Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection . 1996 European Conference on Computer Vision.
(46) P.JB. Hancock;A. M.Burton;V. Bruce. Face processing: human perception and principal component analysis.Memory and Cognition, 1996
(47) Shio, A. ;J. Sklansky. Segmentation of people in motion.Proceedings of the IEEE Workshop on Visual Motion, 1991,p325-332．
(48) Yang, Guangzheng;Huang, Thomas S. Human face detection in a complex background. Pttern Recognition, Vol.27 No.1,1994．