彩色图像的人脸检测与跟踪方法研究
|
摘要
本文针对彩色图像的人脸检测跟踪问题，提出了一种比较新颖的方法。整个算法包括以下三个主要模块。
首先基于颜色和形状分割出人脸候选区域，其中，皮肤检测采用HSCC颜色空间方法，这种方法结合HSV，YCrCb两种颜色空间中的色度分量H，S，Cr，Cb，用模糊隶属度函数来决定像素点的可能程度，这种方法能有效地从彩色图像中检测出各种不同肤色的人脸，同时减少图像背景的影响。
接着通过从定位人脸相似区域中抽取眼睛，嘴巴，鼻子等脸部特征来证实人脸。对脸部特征抽取，我们应用脸部区域内的灰度信息。通过观察可知，眼睛和嘴巴等脸部特征相对其它的脸部区域较暗，我们可以通过积分投影和人脸分布特征初步定位眼睛、嘴巴、鼻子等的大致位置，然后根据眼睛特征，用方差投影精确定位人眼，最后再根据人脸分布特征依次定位人脸各器官。
在可靠地检测出人脸后，就可以进行人脸跟踪。跟踪过程通过主动轮廓来实现，轮廓用“蛇”(snake)来表示。蛇的外部能量由颜色信息决定，它推动蛇的元素snaxel内外移动。
本算法简单使用，实验表明了该算法的有效性和鲁棒性。
In this paper we present a novel approach for segmentation and tracking of faces in color images. The whole algorithm is composed of three main modules.
Segmentation of faces is performed by evaluating color and shape information. First, skin-like regions are determined based on Fuzzy HSCC by integrating the HS and CrCb spaces based on the concept of fuzzy membership function. Then regions with elliptical shape are selected as face hypotheses.The skin segmentation is robust against different lighting conditions and various types of skin color. They are verified by searching for facial features in their interior.
Our approach for facial feature extraction is based on the observation that facial features differ from the rest of the face because of their low brightness. Thus, we detect facial features candidates by evaluating the lopographic greylevel relief of the face region. After obtaining an eye window, the eye can be located by using variance projection functions. Based on vertical symmetry distances between facial features and the assessment of each facial feature, we choose the best face constellation.
After a face is reliably detected, it is tracked over time. Tracking is realized by using an active contour model. The exterior forces of the snake are defined based on color features. They push or pull snaxels perpendicular to the snake. Results demonstrate the efficiency and feasibility of this algorithm, which can be used in time critical system.
首先基于颜色和形状分割出人脸候选区域，其中，皮肤检测采用HSCC颜色空间方法，这种方法结合HSV，YCrCb两种颜色空间中的色度分量H，S，Cr，Cb，用模糊隶属度函数来决定像素点的可能程度，这种方法能有效地从彩色图像中检测出各种不同肤色的人脸，同时减少图像背景的影响。
接着通过从定位人脸相似区域中抽取眼睛，嘴巴，鼻子等脸部特征来证实人脸。对脸部特征抽取，我们应用脸部区域内的灰度信息。通过观察可知，眼睛和嘴巴等脸部特征相对其它的脸部区域较暗，我们可以通过积分投影和人脸分布特征初步定位眼睛、嘴巴、鼻子等的大致位置，然后根据眼睛特征，用方差投影精确定位人眼，最后再根据人脸分布特征依次定位人脸各器官。
在可靠地检测出人脸后，就可以进行人脸跟踪。跟踪过程通过主动轮廓来实现，轮廓用“蛇”(snake)来表示。蛇的外部能量由颜色信息决定，它推动蛇的元素snaxel内外移动。
本算法简单使用，实验表明了该算法的有效性和鲁棒性。
In this paper we present a novel approach for segmentation and tracking of faces in color images. The whole algorithm is composed of three main modules.
Segmentation of faces is performed by evaluating color and shape information. First, skin-like regions are determined based on Fuzzy HSCC by integrating the HS and CrCb spaces based on the concept of fuzzy membership function. Then regions with elliptical shape are selected as face hypotheses.The skin segmentation is robust against different lighting conditions and various types of skin color. They are verified by searching for facial features in their interior.
Our approach for facial feature extraction is based on the observation that facial features differ from the rest of the face because of their low brightness. Thus, we detect facial features candidates by evaluating the lopographic greylevel relief of the face region. After obtaining an eye window, the eye can be located by using variance projection functions. Based on vertical symmetry distances between facial features and the assessment of each facial feature, we choose the best face constellation.
After a face is reliably detected, it is tracked over time. Tracking is realized by using an active contour model. The exterior forces of the snake are defined based on color features. They push or pull snaxels perpendicular to the snake. Results demonstrate the efficiency and feasibility of this algorithm, which can be used in time critical system.
引文
[1] Chellappa R, WilsonC L, Sirohey S. Human and machine recognition of faces: Asurvey. Proceedings of the IEEE, 1995,83(5) :705-740
[2] 周杰，卢春雨，张长水等．人脸自动识别方法综述．电子学报，2000，28(4)：102-106
[3] Yoo T W, OhIS. A fast algorithm for tracking human faces based on chromatic histograms. Pattern Recognition Letters, 1999, 20(10): 967-978
[4] Cai J, Goshtasby A. Detecting human faces in color images. Image and Vision Computing, 1999,18(1):63-75
[5] Yang M H, AhujaN. Detecting human faces in color images. In: Proc IEEE Conferenceon Image Processing, Chicago, 1998.127-139
[6] Wei G, SethiIK. Face detection for image annotation. Pattern Recognition Letters, 1999, 20(11—13): 1313-1321
[7] Karlekar J, Desai U B. Finding faces in color images using wavelet transform. In: Proc IEEE Conferenceon Image Analysis and Processing, Venice, Italy, 1999.1085-1088
[8] Yang G Z, Huang T S. Human face detection in a complex background. Pattern Recognition, 1994, 27(1):53-63
[9] Y. Dai and Y. Nakano. Extraction of facial images from complex background using color information and SGLD matrices. In International Workshop on Automatic Face and Gesture Recognition, IEEE Computer Society. Swiss Informaticians Society. Swiss Computer Graphics Association et al, Zurich, Switzerl and June 26-28,1995. pp238-242.
[10] H. Wu.Q. Chen and M. Yachida. An application of fuzzy theory. Face detection, In International Workshop on Automatic Face and Gesture Recognition. IEEE Computer, Switzerland June 26-28,1995, pp, 314-319.
[11] S. Tominaga. Color image segmentation using three perceptual
attributes. In IEEE Conference on Computer Vision and Pattern Recognition 1986 pages 628-630.
[12] A. Eleftheriadis and A. Jacquin. Automatic face location, detection and tracking for model, assisted coding of video tele conferencing sequences at low bit-rates. Signal Processing. Image Communication, vol 7, no 3, July 1995, pp. 231-248.
[13] A.K. Jain. Fundamentals of Digital Image Processing. Prentice Hall, 1989.
[14] M.J.T. Reinders. P.J.L. van Beek. B. Sankur and J.C.A. van der Lubbe. Facial feature localization and adaption of a generic face model for model, based coding. Signal Processing. Image Communication. Vol 7 no 1 Jul 1995 pp. 57-74.
[15] A.N. Venetsanopoulos and I. Pitas. Nonlinear Digital Filters. Principles and Applications Kluwer Academic Publishers, 1990.
[16] H. Niemann. Pattern Analysis and Understanding. Springer Verlag, 1990.
[17] Anil K. Jain,Rein-Lien Hsu and Mohamed Abdel-Mottaleb Face Detection In Color Images
[18] F. Leymarie and M.D. Levine. Tracking deformable objects in the plane using an active contour model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):617-634, June 1993.
[19] L.D. Cohen and I. Cohen. Finite. element methods for active contour models and balloons for 2-D and 3-D images. IEEE Transactions on Pattern Analysis and Machine Intelligence 15(11):1131-1147, November 1993.
[20] A. Pentland and S. Sclaroff. Closed_form solutions for physically based shape modeling and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 13(7),715-729 July 1991.
[21] U. Pautz. Active contours for D. segmentation of magnetic resonance images (in German)Diploma Thesis. FORWISS. Erlangen Germany July 1995
[22] D. Williams and M. Schah. A fast algorithm for active contours and curvature estimation. CVGIP: Image Understanding. Bd. 55 (1) : 14-26, Jan 1991.
[23] Kouzani A Z, He F, Sammut K. Commonsense knowledge-based face detection. In: Proc Conference on Intelligent Engineering Systems, Budapast, Hungary, 1997. 215-220
[24] 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
[25] Moghaddam B, Pentland A. Probabilistic visual learning for object representation. IEEE Trans Pattern Analysis and Machine Intelligence,1997,19(7):696-710
[26] Sung K, PoggioT. Example-based learning for view based human face detection. IEEE Trans Pattern Analysis and Machine Intelligence, 1998,20(1):39-51
[27] RowleyHA,BalujaS,KanadeT.Rotationinvariantneuralnetwork-basedfacedetection.CarnegieMellonUniversity, PittsburghPA:TechnicalReportCMU-CS-97-201,1997
[28] Rowley H A, Baluja S, Kanade T. Neural network-based face detection. IEEE Trans Pattern Analysis and Machine Intelligence, 1998,20(1):23-38
[29] Rowley H A. Neural network-based face detection. Carnegie Mellon University, Pittsburgh PA: Technical Report CMU-CS-99-117,1999
[30] Schneiderman H, Kanade T. Probabilistic modeling of local appearance and spatial relationships for object recognition. In: Proc IEEE Conferenceon Computer Vision and Pattern Recognition, Santa Barbara, California, 1998.45-51
[31] Schneiderman H. Astatistical approach to 3D object detection applied to faces and cars. Carnegie Mellon University, Pittsburgh PA: Technical Report CMU-RI-TR-00-06, 2000
[32] Nefian A V, Hayes M H. Face detection and recognition using hidden Markov models. In: Proc IEEE Conference on Image Processing, Chicago, 1998.141-145
[33] Nefian A V, Hayes M H. An embedden H M M based approach for face detection and recognition. In: Proc IEEE Conference on Acoustics, Speech, and Signal Processing, Phoenix, Arizona,1999,6:3553-3556
[34] Boxer B E, Guyon I M, Vapnik v N. A training algorithm for optimalmal margin classifier. In:Proc of the 5th ACM Workshop on Computational Learning Theory, Pittsburgh, 1992.144-152
[35] Gunn S R. Support vector machines for classificati on and regression. Image Speech and Intelligent Systems Research group, University of Southapton: ISIS Technical Report, ISIS-1-98,1998
[36] Osuna E, FreundR, Girosi F. Training support vector machines: Anapplication to face detection. In: Proc Computer Vision and Pattern Recognition, Puerto Rico, 1997.130-136
[37] 卢春雨，张长水，闻方等．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
[38] 刘明宝，姚鸿勋，高文．彩色图像的实时人脸跟踪方法．计算机学报，1998，21(6)：527-532
[39] 梁路宏，艾海舟，徐光，张钹．人脸检测研究综述．计算机学报，2002，25(5)
[40] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chern and Yao Tsorng Liu, Facial feature detection using geometrical face model: an efficient approach, Pattern Recognition 31 (3), 273-282 (1998).
[41] C.Garicia,G.Zikos,G.Tziritas Face detection in color images using wavelet packet analysis
[2] 周杰，卢春雨，张长水等．人脸自动识别方法综述．电子学报，2000，28(4)：102-106
[3] Yoo T W, OhIS. A fast algorithm for tracking human faces based on chromatic histograms. Pattern Recognition Letters, 1999, 20(10): 967-978
[4] Cai J, Goshtasby A. Detecting human faces in color images. Image and Vision Computing, 1999,18(1):63-75
[5] Yang M H, AhujaN. Detecting human faces in color images. In: Proc IEEE Conferenceon Image Processing, Chicago, 1998.127-139
[6] Wei G, SethiIK. Face detection for image annotation. Pattern Recognition Letters, 1999, 20(11—13): 1313-1321
[7] Karlekar J, Desai U B. Finding faces in color images using wavelet transform. In: Proc IEEE Conferenceon Image Analysis and Processing, Venice, Italy, 1999.1085-1088
[8] Yang G Z, Huang T S. Human face detection in a complex background. Pattern Recognition, 1994, 27(1):53-63
[9] Y. Dai and Y. Nakano. Extraction of facial images from complex background using color information and SGLD matrices. In International Workshop on Automatic Face and Gesture Recognition, IEEE Computer Society. Swiss Informaticians Society. Swiss Computer Graphics Association et al, Zurich, Switzerl and June 26-28,1995. pp238-242.
[10] H. Wu.Q. Chen and M. Yachida. An application of fuzzy theory. Face detection, In International Workshop on Automatic Face and Gesture Recognition. IEEE Computer, Switzerland June 26-28,1995, pp, 314-319.
[11] S. Tominaga. Color image segmentation using three perceptual
attributes. In IEEE Conference on Computer Vision and Pattern Recognition 1986 pages 628-630.
[12] A. Eleftheriadis and A. Jacquin. Automatic face location, detection and tracking for model, assisted coding of video tele conferencing sequences at low bit-rates. Signal Processing. Image Communication, vol 7, no 3, July 1995, pp. 231-248.
[13] A.K. Jain. Fundamentals of Digital Image Processing. Prentice Hall, 1989.
[14] M.J.T. Reinders. P.J.L. van Beek. B. Sankur and J.C.A. van der Lubbe. Facial feature localization and adaption of a generic face model for model, based coding. Signal Processing. Image Communication. Vol 7 no 1 Jul 1995 pp. 57-74.
[15] A.N. Venetsanopoulos and I. Pitas. Nonlinear Digital Filters. Principles and Applications Kluwer Academic Publishers, 1990.
[16] H. Niemann. Pattern Analysis and Understanding. Springer Verlag, 1990.
[17] Anil K. Jain,Rein-Lien Hsu and Mohamed Abdel-Mottaleb Face Detection In Color Images
[18] F. Leymarie and M.D. Levine. Tracking deformable objects in the plane using an active contour model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):617-634, June 1993.
[19] L.D. Cohen and I. Cohen. Finite. element methods for active contour models and balloons for 2-D and 3-D images. IEEE Transactions on Pattern Analysis and Machine Intelligence 15(11):1131-1147, November 1993.
[20] A. Pentland and S. Sclaroff. Closed_form solutions for physically based shape modeling and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 13(7),715-729 July 1991.
[21] U. Pautz. Active contours for D. segmentation of magnetic resonance images (in German)Diploma Thesis. FORWISS. Erlangen Germany July 1995
[22] D. Williams and M. Schah. A fast algorithm for active contours and curvature estimation. CVGIP: Image Understanding. Bd. 55 (1) : 14-26, Jan 1991.
[23] Kouzani A Z, He F, Sammut K. Commonsense knowledge-based face detection. In: Proc Conference on Intelligent Engineering Systems, Budapast, Hungary, 1997. 215-220
[24] 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
[25] Moghaddam B, Pentland A. Probabilistic visual learning for object representation. IEEE Trans Pattern Analysis and Machine Intelligence,1997,19(7):696-710
[26] Sung K, PoggioT. Example-based learning for view based human face detection. IEEE Trans Pattern Analysis and Machine Intelligence, 1998,20(1):39-51
[27] RowleyHA,BalujaS,KanadeT.Rotationinvariantneuralnetwork-basedfacedetection.CarnegieMellonUniversity, PittsburghPA:TechnicalReportCMU-CS-97-201,1997
[28] Rowley H A, Baluja S, Kanade T. Neural network-based face detection. IEEE Trans Pattern Analysis and Machine Intelligence, 1998,20(1):23-38
[29] Rowley H A. Neural network-based face detection. Carnegie Mellon University, Pittsburgh PA: Technical Report CMU-CS-99-117,1999
[30] Schneiderman H, Kanade T. Probabilistic modeling of local appearance and spatial relationships for object recognition. In: Proc IEEE Conferenceon Computer Vision and Pattern Recognition, Santa Barbara, California, 1998.45-51
[31] Schneiderman H. Astatistical approach to 3D object detection applied to faces and cars. Carnegie Mellon University, Pittsburgh PA: Technical Report CMU-RI-TR-00-06, 2000
[32] Nefian A V, Hayes M H. Face detection and recognition using hidden Markov models. In: Proc IEEE Conference on Image Processing, Chicago, 1998.141-145
[33] Nefian A V, Hayes M H. An embedden H M M based approach for face detection and recognition. In: Proc IEEE Conference on Acoustics, Speech, and Signal Processing, Phoenix, Arizona,1999,6:3553-3556
[34] Boxer B E, Guyon I M, Vapnik v N. A training algorithm for optimalmal margin classifier. In:Proc of the 5th ACM Workshop on Computational Learning Theory, Pittsburgh, 1992.144-152
[35] Gunn S R. Support vector machines for classificati on and regression. Image Speech and Intelligent Systems Research group, University of Southapton: ISIS Technical Report, ISIS-1-98,1998
[36] Osuna E, FreundR, Girosi F. Training support vector machines: Anapplication to face detection. In: Proc Computer Vision and Pattern Recognition, Puerto Rico, 1997.130-136
[37] 卢春雨，张长水，闻方等．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
[38] 刘明宝，姚鸿勋，高文．彩色图像的实时人脸跟踪方法．计算机学报，1998，21(6)：527-532
[39] 梁路宏，艾海舟，徐光，张钹．人脸检测研究综述．计算机学报，2002，25(5)
[40] Shi-Hong Jeng, Hong Yuan Mark Liao, Chin Chuan Han, Ming Yang Chern and Yao Tsorng Liu, Facial feature detection using geometrical face model: an efficient approach, Pattern Recognition 31 (3), 273-282 (1998).
[41] C.Garicia,G.Zikos,G.Tziritas Face detection in color images using wavelet packet analysis