人脸分割和特征提取技术研究
|
摘要
本文主要介绍了彩色图像中的人脸区域定位和面部特征提取技术。人脸定位就是从复杂的图像中找出人脸区域，它是进行特征提取的前提。特征提取是指从人脸区域中分割出特征点所在区域，并进一步找到特征点的坐标。这里所指的特征点是指瞳孔、眼角、鼻角和嘴角。
本文首先详细介绍了人脸定位的原理：根据人的肤色在色度空间的聚类特性，选择合适的色彩空间建立肤色模型，利用相似度将人脸区域分割出来，再结合人脸的结构特点进行人脸定位。接着分别阐述了各个特征点的提取方案：瞳孔的定位采用了灰度投影与边缘检测相结合的方法。先找出眼睛区域的外切矩形，再取该矩形的中心，得到瞳孔的位置，并在此基础上找到眼角的坐标。嘴角的定位则利用了嘴唇的颜色特征。先根据人脸的结构特点，定位出大致的嘴巴区域，然后利用唇色将嘴唇区域分割出来，再进一步找出嘴角的坐标。鼻角的定位利用了鼻孔的亮度值较低的特点，先通过阈值分割找出两个鼻孔区域，再根据鼻孔的形状特征寻找到鼻角。
Technology of human face area location and feature extraction in color image is introduced in this paper. Human face location which is the premise of feature extraction means finding the position of human face in the complicated image. Feature extraction means locating the area where the feature belongs and finding the coordinates of these feature. Feature we point out here refers to pupil, canthus, corners of the mouth and corners of the nose.
In the first part of this paper, the principle of human face location is introduced: Because human skin color clusters in the color space, we select a appropriate space to construct the skin color model, then skin color area of face is separated. Finally, we use the construction feature of face to locate the face. In the second part of this paper, different algorithm is introduced to locate different feature points. First, grey level projection and edge detection are used to find the coordinates of the pupil. After finding the rectangle area of the eye position, we calculate the center of the rectangle to get the coordinates, then the canthus can be found. Second, to extract the corner of the mouth, the color of the lip is used. After locating the proximate area of the mouth based on the construction feature of face, we separate the area of lip using its color, then the corner of the mouth can be easily found. To locate the position of the corner of the nose, we separate the nose area on the basis that its i
ntensity of luminance is smaller than other parts of its vicinity, then the coordinates can be found based on the feature of the nostril.
本文首先详细介绍了人脸定位的原理：根据人的肤色在色度空间的聚类特性，选择合适的色彩空间建立肤色模型，利用相似度将人脸区域分割出来，再结合人脸的结构特点进行人脸定位。接着分别阐述了各个特征点的提取方案：瞳孔的定位采用了灰度投影与边缘检测相结合的方法。先找出眼睛区域的外切矩形，再取该矩形的中心，得到瞳孔的位置，并在此基础上找到眼角的坐标。嘴角的定位则利用了嘴唇的颜色特征。先根据人脸的结构特点，定位出大致的嘴巴区域，然后利用唇色将嘴唇区域分割出来，再进一步找出嘴角的坐标。鼻角的定位利用了鼻孔的亮度值较低的特点，先通过阈值分割找出两个鼻孔区域，再根据鼻孔的形状特征寻找到鼻角。
Technology of human face area location and feature extraction in color image is introduced in this paper. Human face location which is the premise of feature extraction means finding the position of human face in the complicated image. Feature extraction means locating the area where the feature belongs and finding the coordinates of these feature. Feature we point out here refers to pupil, canthus, corners of the mouth and corners of the nose.
In the first part of this paper, the principle of human face location is introduced: Because human skin color clusters in the color space, we select a appropriate space to construct the skin color model, then skin color area of face is separated. Finally, we use the construction feature of face to locate the face. In the second part of this paper, different algorithm is introduced to locate different feature points. First, grey level projection and edge detection are used to find the coordinates of the pupil. After finding the rectangle area of the eye position, we calculate the center of the rectangle to get the coordinates, then the canthus can be found. Second, to extract the corner of the mouth, the color of the lip is used. After locating the proximate area of the mouth based on the construction feature of face, we separate the area of lip using its color, then the corner of the mouth can be easily found. To locate the position of the corner of the nose, we separate the nose area on the basis that its i
ntensity of luminance is smaller than other parts of its vicinity, then the coordinates can be found based on the feature of the nostril.
引文
1．张翠平，苏光大，人脸识别技术综述，中国图形图像学报 2000年Vol．5(A)，No．11，885-894
2. Berto R, Poggio T, Face recognition: Feature versus templates. IEEE Trans. on PAMI, 1993,15(10), 1042-1052
3. Ziquan Hong. Algebraic feature extraction of image for recognition. Pattern Recognition, 1991,24(3), 211-219
4. Nakamura O, Mathur S, Minami T. Identification of human faces based on isodensity maps. Pattern Recognition, 1991,24(3), 263-272
5. Lades M, Vorbuggen J, Buhmann J et al. Distortion invariant object recognition in the dynamic link architecture. IEEE Tans. on Computers, 1991,42(3), 300-311
6. Samaria F, Young S. HMM-based architecture for face identification. Image and Vision Computing, 1994,12(8), 537-543
7．苏建波，徐波，应用模式识别技术导论，上海，上海交通大学出版社，2001年，9-10
8．Lockwood P．and Boundy J．，Experiments with a Nor-linear Spectral Substractor(NSS)，Hidden Markov Models and Projection，for Robust Speech Recognition in Cars，Speech Communication, 1992,11(2-3)，215-228
9．Li L. and Richard R., A Frequency Warping Approach to Speaker Normalization. IEEE Transactions on Speech and Audio Processing,1998, 6(1), 49-60
10．Lv X. G, Zhou J, Zhang C. S. A novel algorithm for rotated human face detection, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA,2000,760-764
11．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
12．梁路宏，艾海舟，何克忠，基于多模板匹配的单人脸检测，中国图像图形学报，1999，4A(10)，823-830
13. Wang J G, Tan T N, A new face detection method based on shape information, Pattern Recognition, 2000, 21(6-7), 463-471
14. Yang M H, Ahuja N, Kriegman D. A survey on face detection methods,1999, http://vision.aiuiuc,edu/mhyang/papers/survey.ps.gz
15．梁路宏，艾海舟，徐光佑等，人脸检测研究综述，计算机学报，2002，25(5)，449-458
16. S. Gutta et. al. Face recognition using ensembles of networks. In Proc. of Int. Conf. on Pattern Recognition. Vienna, Austria, Aug. 1996, 606-610
17. H.A. Rowley, S. Baluja and T. Kanade. Human face detection in visual scenes. Technical Report CMU-CS-95-158, Dept of Computer Science, Carnegie Mellon University, July, 1995, 875-881
18. S.-H. Lin, S.-Y. Kung and L.-J. Lin. Face recognition/detection by probabilistic decision-based neural network. IEEE Trans. on Neural Networks, 1997,8(1): 114-132.
19. K. C. Yow and R. Cipolla. Feature-based human face detection. Image and Vision Computing, 1997,vol 15,713-735
20. Q. Chen, H. Wu and M. Yachida. Face detection by fuzzy pattern matching. In Proc. of 5th Int confon Computer Vision, MIT, Boston, 1995, 591-596
21．鸿勋，刘明宝，高文等，基于彩色图像的色系坐标变换的面部定位与跟踪法，计算机学报2000，Vol．23，No．2，158-165
22. Growing Gaussian Mixture Models for Pose Invariant Face Recognition Ralph Gross, Jie Yang, Alex Waibel International Conference on Pattern Recognition-ICPR 2000, 5088-5091,
23. R.-L. Hsu, M. Abdel-Mottaleb, and A. K. Jain, "Face detection in color images," IEEE Trans. Pattern Analysis and Machine Intelligence, May 2002, vol. 24, no.5,696-706
24. Jennifer Wortman, Skin Detection, January, 2002(http://cs.people.bu.edu/ruel/cs585/HWl/jwortman/hwl/hwl.html)
25. G. Yang, T. Huang, Human face detection in a complex background, Pattern Recognition 27(1) 1994, 53-63
26. J. Bala et. al. Visual routine for eye detection using hybrid genetic architectures. In Proc. of Int. Conf. on Pattern Recognition. Vienna, Austria, Aug. 1996, 50-54
27. A. Yuille, D. Cohen and P. Hallinan. Feature extraction from faces using deformable templates. In IEEE Computer Soc. Conf on Computer Vision and Pattern Recognition,1989, 104-109
28．Rafael C．Gonzalez，Richard E．Woods箸，阮秋琦，阮宇智等译，Digital Image Processing(second edition)，北京，电子工业出版社，2003年3月，460—480
29．王华，李介古，人脸斜视图像的特征提取与恢复，计算机应用1997 vol．3l No．1，101．104
30. K.M. Lam and H. Yan, "Locating and extracting the eye in human face images", Pattern Recognition, vol. 29, no.5, 1996, 771-779
31. F.Smeraldi, O.Carmona, and J. Bigun, "Saccadic Search with Gabor Features Applied to Eye Detection and Real-time Head Tracking", Image and Vision Computing,vol.18, no.4, 2000, 323-329
32．林福严，刘巧静等，人脸特征的定位和提取，计算机应用，2000年第7期，17-21
33．张宏林Visual C++数字图像模式识别技术及工程实践人民邮电出版社 2003年，420-421
34. V Berzins. Accuracy of Laplacian edge detectors, Computer Vision, Graphics, Image Processing, 1984,27(2), 195-210
35．李于剑，Visual C++实践与提高—图形图像编程篇，北京，中国铁道出版社2001年2月
36．David J. Kruglinski, Scot Wingo, George Shepherd编著，希望图书创作室译，Visual C++6.0 技术内幕，北京：北京希望电子出版社，1999年5月
37．Richard C. Leinecker箸，陈冠民，王如亮，宋峥宁等译，Visual C++5.0开发技术内幕，北京，机械工业出版社，1999年1月
38．朗锐，数字图像处理学Visual C++实现，北京，北京希望电子出版社，2003年1月
39. T.S. Caetano, D.A.C. Barone, A Probabilistic Model for the Human Skin Color,2001, www.cs.ualberta.cw/～tcaetano/iciap2001.pdf
40. M.H. Yang, N. Ahuja, "Gaussian Mixture Model for Human Skin Color and Its Application in Image and Video Databases", Proc. of the SPIE, vol. 3656,1999,458-466
41. Wenmiao Lu, Shaohua Sun, Face Detection in Color Images, Stanford University, May 26,2003, http://ise.stanford.edu/2003projects/ee368/Project/reports/ee368group03.pdf
42. Tiberio S. Caetano, Silvia D. Olabarriaga, Dante A.C. Barone, Do mixture models in chromaticity space improve skin detection? Pattern Recognition,36(2003), 3019-3021
2. Berto R, Poggio T, Face recognition: Feature versus templates. IEEE Trans. on PAMI, 1993,15(10), 1042-1052
3. Ziquan Hong. Algebraic feature extraction of image for recognition. Pattern Recognition, 1991,24(3), 211-219
4. Nakamura O, Mathur S, Minami T. Identification of human faces based on isodensity maps. Pattern Recognition, 1991,24(3), 263-272
5. Lades M, Vorbuggen J, Buhmann J et al. Distortion invariant object recognition in the dynamic link architecture. IEEE Tans. on Computers, 1991,42(3), 300-311
6. Samaria F, Young S. HMM-based architecture for face identification. Image and Vision Computing, 1994,12(8), 537-543
7．苏建波，徐波，应用模式识别技术导论，上海，上海交通大学出版社，2001年，9-10
8．Lockwood P．and Boundy J．，Experiments with a Nor-linear Spectral Substractor(NSS)，Hidden Markov Models and Projection，for Robust Speech Recognition in Cars，Speech Communication, 1992,11(2-3)，215-228
9．Li L. and Richard R., A Frequency Warping Approach to Speaker Normalization. IEEE Transactions on Speech and Audio Processing,1998, 6(1), 49-60
10．Lv X. G, Zhou J, Zhang C. S. A novel algorithm for rotated human face detection, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA,2000,760-764
11．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
12．梁路宏，艾海舟，何克忠，基于多模板匹配的单人脸检测，中国图像图形学报，1999，4A(10)，823-830
13. Wang J G, Tan T N, A new face detection method based on shape information, Pattern Recognition, 2000, 21(6-7), 463-471
14. Yang M H, Ahuja N, Kriegman D. A survey on face detection methods,1999, http://vision.aiuiuc,edu/mhyang/papers/survey.ps.gz
15．梁路宏，艾海舟，徐光佑等，人脸检测研究综述，计算机学报，2002，25(5)，449-458
16. S. Gutta et. al. Face recognition using ensembles of networks. In Proc. of Int. Conf. on Pattern Recognition. Vienna, Austria, Aug. 1996, 606-610
17. H.A. Rowley, S. Baluja and T. Kanade. Human face detection in visual scenes. Technical Report CMU-CS-95-158, Dept of Computer Science, Carnegie Mellon University, July, 1995, 875-881
18. S.-H. Lin, S.-Y. Kung and L.-J. Lin. Face recognition/detection by probabilistic decision-based neural network. IEEE Trans. on Neural Networks, 1997,8(1): 114-132.
19. K. C. Yow and R. Cipolla. Feature-based human face detection. Image and Vision Computing, 1997,vol 15,713-735
20. Q. Chen, H. Wu and M. Yachida. Face detection by fuzzy pattern matching. In Proc. of 5th Int confon Computer Vision, MIT, Boston, 1995, 591-596
21．鸿勋，刘明宝，高文等，基于彩色图像的色系坐标变换的面部定位与跟踪法，计算机学报2000，Vol．23，No．2，158-165
22. Growing Gaussian Mixture Models for Pose Invariant Face Recognition Ralph Gross, Jie Yang, Alex Waibel International Conference on Pattern Recognition-ICPR 2000, 5088-5091,
23. R.-L. Hsu, M. Abdel-Mottaleb, and A. K. Jain, "Face detection in color images," IEEE Trans. Pattern Analysis and Machine Intelligence, May 2002, vol. 24, no.5,696-706
24. Jennifer Wortman, Skin Detection, January, 2002(http://cs.people.bu.edu/ruel/cs585/HWl/jwortman/hwl/hwl.html)
25. G. Yang, T. Huang, Human face detection in a complex background, Pattern Recognition 27(1) 1994, 53-63
26. J. Bala et. al. Visual routine for eye detection using hybrid genetic architectures. In Proc. of Int. Conf. on Pattern Recognition. Vienna, Austria, Aug. 1996, 50-54
27. A. Yuille, D. Cohen and P. Hallinan. Feature extraction from faces using deformable templates. In IEEE Computer Soc. Conf on Computer Vision and Pattern Recognition,1989, 104-109
28．Rafael C．Gonzalez，Richard E．Woods箸，阮秋琦，阮宇智等译，Digital Image Processing(second edition)，北京，电子工业出版社，2003年3月，460—480
29．王华，李介古，人脸斜视图像的特征提取与恢复，计算机应用1997 vol．3l No．1，101．104
30. K.M. Lam and H. Yan, "Locating and extracting the eye in human face images", Pattern Recognition, vol. 29, no.5, 1996, 771-779
31. F.Smeraldi, O.Carmona, and J. Bigun, "Saccadic Search with Gabor Features Applied to Eye Detection and Real-time Head Tracking", Image and Vision Computing,vol.18, no.4, 2000, 323-329
32．林福严，刘巧静等，人脸特征的定位和提取，计算机应用，2000年第7期，17-21
33．张宏林Visual C++数字图像模式识别技术及工程实践人民邮电出版社 2003年，420-421
34. V Berzins. Accuracy of Laplacian edge detectors, Computer Vision, Graphics, Image Processing, 1984,27(2), 195-210
35．李于剑，Visual C++实践与提高—图形图像编程篇，北京，中国铁道出版社2001年2月
36．David J. Kruglinski, Scot Wingo, George Shepherd编著，希望图书创作室译，Visual C++6.0 技术内幕，北京：北京希望电子出版社，1999年5月
37．Richard C. Leinecker箸，陈冠民，王如亮，宋峥宁等译，Visual C++5.0开发技术内幕，北京，机械工业出版社，1999年1月
38．朗锐，数字图像处理学Visual C++实现，北京，北京希望电子出版社，2003年1月
39. T.S. Caetano, D.A.C. Barone, A Probabilistic Model for the Human Skin Color,2001, www.cs.ualberta.cw/～tcaetano/iciap2001.pdf
40. M.H. Yang, N. Ahuja, "Gaussian Mixture Model for Human Skin Color and Its Application in Image and Video Databases", Proc. of the SPIE, vol. 3656,1999,458-466
41. Wenmiao Lu, Shaohua Sun, Face Detection in Color Images, Stanford University, May 26,2003, http://ise.stanford.edu/2003projects/ee368/Project/reports/ee368group03.pdf
42. Tiberio S. Caetano, Silvia D. Olabarriaga, Dante A.C. Barone, Do mixture models in chromaticity space improve skin detection? Pattern Recognition,36(2003), 3019-3021