人脸识别系统中眼睛定位方法的研究
|
摘要
生物识别技术是利用人自身具备的生物特征进行身份鉴别的技术。与其他的生物认证技术相比,人脸识别具有更直接、友好、方便的优点。因此,人脸识别技术有着广泛的应用前景和迫切的现实需要,是当前模式识别领域最热门的研究方向之一。多年来,人们对人脸识别技术中的许多问题都进行了深入地研究,并且已经研制出了不少有效的算法。然而,由于不同人脸具有的内在相似性,而同一人脸的不同图像则常常因为一些因素的影响而表现出巨大的差异性,因此现有的人脸识别技术仍然无法满足实际应用的需要。
一般情况下,一个完整的人脸识别系统由人脸检测、特征提取、人脸识别等几部分组成。其中,特征提取的好坏将直接影响到识别的效果。而在脸部的所有特征点中,眼睛是最重要的器官,眼睛定位的准确与否将影响到特征提取的效果。因此人眼的快速准确定位被学者视为提高人脸识别准确率和人脸识别走向实用化的关键和瓶颈所在。
本文以实现眼睛的准确定位为目标,探讨了基于脸部的肤色、灰度和几何特性的眼睛定位方法。整个过程可以分为两个阶段,第一阶段研究了从图像中检测定位人脸的方法;第二阶段又研究了在脸部区域进行眼睛定位的方法。论文的研究工作主要包括以下内容:
第一,分别研究了适用于两种不同情况的脸部区域检测算法,算法根据其不同的应用特点进行了不同的处理。对于特定场合背景较简单的情况,采用投影法对图像进行了处理,然后通过分析其投影曲线的特征,进行脸部的粗定位。这种方法简单易实现,且计算复杂度小,非常适合处理一些实时的任务。而对于复杂背景的情况,则根据肤色对尺寸、姿态、表情不敏感的特性,采用基于肤色信息的方法来进行人脸检测。首先对不同的色彩空间进行分析比较,并选取YCbCr空间进行研究,然后通过大量肤色样本建立的高斯模型进行肤色分割,最后通过脸部的几何特性对分割出来的肤色区域进行优化处理。实验证明,文中针对两种不同情况采用的方法,在各自的应用场合中都取得了较好的效果。
第二,在检测到的脸部区域内进行眼睛定位阶段,本文提出了一种有效的眼睛精确定位方法。由于眼睛区域具有复杂的灰度变化特征,所以根据其灰度信息通常可以实现准确的定位。本文的方法是先对图像进行形态学处理从而粗定位到候选的眼睛点;而眼睛的精确定位过程采用的是一个复合的眼睛检测器,该检测器由两个不同的方差滤波器级联构成,通过构造的检测器和先验知识的验证,可以判定出眼睛的精确位置。实验证明,本文采用的眼睛定位方法容易实现,且具有较好的鲁棒性。
Biometric identification technology is a kind of technology using individual biometric characteristics to verify identity. Compared with other biometrics technology, face recognition is more direct, friend and convenient. So the technology of face recognition is one of the hottest research directions for its wide application and urgent demand. Face recognition has been intensively investigated by researchers and many useful algorithms have been developed. Since faces of different subjects are often similar, while face images from the same person often differ quite significantly due to the impact of certain factors, current face recognition systems cannot meet the requirements of many practical applications.
Usually a complete face recognition system includes face detection, feature extraction and face recognition. The quality of feature extraction will be affected by the recognition effects directly. The eye is the most important organ of face. As the accuracy of eye detection will affect the quality of feature extraction, rapid and precise eye detection is considered the most crucial work to be dealt with.
In this paper, in order to locate the eye exactly, the methods based on the facial color, grayness and geometric characteristics are studied. The whole process can be divided into two phases, that is, face detection and eye location in the face region. The main contributions are summarized as follows:
Firstly, in this paper two algorithms of face detection to different situations are studied, and they do corresponding treatments according to the different applications. For the specific occasions of simple background, gray projection is adopted to process the images. Face can be located roughly through analyzing the characteristics of the projection curve. This method is easy to implement and costs small complexity, so it can be adapted to deal with some real time tasks. For complex background, because the skin-color is not sensitive to size, pose and expression, the method based on skin-color is used to detect the face. By comparing the different color space, YCbCr color space is adopted. Then Gaussian model is established to segment the image and face region can be validated according to geometric characteristics. The result of experiment indicates that these two algorithms are all effective.
Then an effective eye location algorithm in the face region is brought forward. Because of the complex gray of the eye region, these characteristics can be used to locate the eyes exactly. Eye candidates can be found through morphology operation; Eye detector is designed, and it is structured with two different variance filters. The eyes are accurately located with the detector and prior knowledge. The experimental results prove that the algorithm is easy, efficient and robust.
一般情况下,一个完整的人脸识别系统由人脸检测、特征提取、人脸识别等几部分组成。其中,特征提取的好坏将直接影响到识别的效果。而在脸部的所有特征点中,眼睛是最重要的器官,眼睛定位的准确与否将影响到特征提取的效果。因此人眼的快速准确定位被学者视为提高人脸识别准确率和人脸识别走向实用化的关键和瓶颈所在。
本文以实现眼睛的准确定位为目标,探讨了基于脸部的肤色、灰度和几何特性的眼睛定位方法。整个过程可以分为两个阶段,第一阶段研究了从图像中检测定位人脸的方法;第二阶段又研究了在脸部区域进行眼睛定位的方法。论文的研究工作主要包括以下内容:
第一,分别研究了适用于两种不同情况的脸部区域检测算法,算法根据其不同的应用特点进行了不同的处理。对于特定场合背景较简单的情况,采用投影法对图像进行了处理,然后通过分析其投影曲线的特征,进行脸部的粗定位。这种方法简单易实现,且计算复杂度小,非常适合处理一些实时的任务。而对于复杂背景的情况,则根据肤色对尺寸、姿态、表情不敏感的特性,采用基于肤色信息的方法来进行人脸检测。首先对不同的色彩空间进行分析比较,并选取YCbCr空间进行研究,然后通过大量肤色样本建立的高斯模型进行肤色分割,最后通过脸部的几何特性对分割出来的肤色区域进行优化处理。实验证明,文中针对两种不同情况采用的方法,在各自的应用场合中都取得了较好的效果。
第二,在检测到的脸部区域内进行眼睛定位阶段,本文提出了一种有效的眼睛精确定位方法。由于眼睛区域具有复杂的灰度变化特征,所以根据其灰度信息通常可以实现准确的定位。本文的方法是先对图像进行形态学处理从而粗定位到候选的眼睛点;而眼睛的精确定位过程采用的是一个复合的眼睛检测器,该检测器由两个不同的方差滤波器级联构成,通过构造的检测器和先验知识的验证,可以判定出眼睛的精确位置。实验证明,本文采用的眼睛定位方法容易实现,且具有较好的鲁棒性。
Biometric identification technology is a kind of technology using individual biometric characteristics to verify identity. Compared with other biometrics technology, face recognition is more direct, friend and convenient. So the technology of face recognition is one of the hottest research directions for its wide application and urgent demand. Face recognition has been intensively investigated by researchers and many useful algorithms have been developed. Since faces of different subjects are often similar, while face images from the same person often differ quite significantly due to the impact of certain factors, current face recognition systems cannot meet the requirements of many practical applications.
Usually a complete face recognition system includes face detection, feature extraction and face recognition. The quality of feature extraction will be affected by the recognition effects directly. The eye is the most important organ of face. As the accuracy of eye detection will affect the quality of feature extraction, rapid and precise eye detection is considered the most crucial work to be dealt with.
In this paper, in order to locate the eye exactly, the methods based on the facial color, grayness and geometric characteristics are studied. The whole process can be divided into two phases, that is, face detection and eye location in the face region. The main contributions are summarized as follows:
Firstly, in this paper two algorithms of face detection to different situations are studied, and they do corresponding treatments according to the different applications. For the specific occasions of simple background, gray projection is adopted to process the images. Face can be located roughly through analyzing the characteristics of the projection curve. This method is easy to implement and costs small complexity, so it can be adapted to deal with some real time tasks. For complex background, because the skin-color is not sensitive to size, pose and expression, the method based on skin-color is used to detect the face. By comparing the different color space, YCbCr color space is adopted. Then Gaussian model is established to segment the image and face region can be validated according to geometric characteristics. The result of experiment indicates that these two algorithms are all effective.
Then an effective eye location algorithm in the face region is brought forward. Because of the complex gray of the eye region, these characteristics can be used to locate the eyes exactly. Eye candidates can be found through morphology operation; Eye detector is designed, and it is structured with two different variance filters. The eyes are accurately located with the detector and prior knowledge. The experimental results prove that the algorithm is easy, efficient and robust.
引文
[1] Zhang Mingui, Zhou Delong, Pan Quan, et al. Biometrics identification techniques. Proceedings of the 4th World Cogress on Intelligent Control and Automation, 2002, 2: 1133-1137
[2] 高文.人脸识别研究概述.生物特征识别技术高级研讨班.北京,2003,12
[3] 张燕昆,刘重庆.基于核方法的人脸识别技术的研究.上海交通大学博士论文,2003,10
[4] Burel G, Carel D. Detection and localization of face on digital images. Pattern Recognion Letters, 1994, 15(7): 963-967
[5] Chellappa R, Wilson C L and Sirohey S. Human and Machine Recognition of Face: A Survey, Proc IEEE, 1995, 83(5): 705-740
[6] Allen A.L. Personal Descriptions. London Butterworth,1950:91-104
[7] Parke F.L. Computer geberated animation of faces. In Proceedings ACMann Conference, 1972, l: 451-457
[8] Goldstion R.J, Harmon L.D, LeskA.B. Man-machine interaction in human face identication Bell Syst. Tech.Journal, 2001, 51: 399-427
[9] KayaY, Kobayashi K. A basic study on human recognition. In Frontiers of Pattern Recognition, New York: Academic, 2004: 265-289
[10] Kanada T. Picture Processing system by computer and recognition of human faces. Ph.D Dissertation.Kyoto:KyotoUniversity,2003:27-46
[11] Baron R.J. Mechanisms of human facial recognition. In T.J Man Machine Studies, 1981, 15: 137-178
[12] M.Turk, A.Pentland. Eigenfaces for Recognition. Journal of Cognitive Neurosicence, 1991, 3(1): 71-86
[13] D.Valentin, H.Abdi, B.Edelman, A.J.OToole. Principal Component and Neural Network Analyses of Face Images: What Can Be Generalized in Gender Classification. Journal of Mathematical Psychology, 1997, 41: 398-412
[14] 周激流,张晔.人脸识别理论研究进展.计算机辅助设计与图形学学报,1999,11(2):180-184
[15] R.Chellappa, C.L.Wilson, S.Sirohey. Human and Machine Recognition of Faces: A Servey, Proc.IEEE, 1995, 83(5): 705-740
[16] 孙大瑞,吴乐南.基于 Gabor 变换的人眼定位.电路与系统学报,2001,6(4):29-32
[17] 蔡国松,卢广山,王合龙.眼跟踪技术.电光与控制,2004,11(1):71-73
[18] 周玉彬,俞梦孙.用红外图像实时跟踪的和监测眼睛的方法.北京生物医学工程,2003,22(2):104-108
[19] 吴林托,李芳,栩步军等.基于红外 LED 的人眼快速定位与跟踪的研究.光学仪器,2006,28(1):85-88
[20] 杨彬,黄耀志.基于 PERCL0S 的汽车司机疲劳监控方法的研究.微计算机信息.2005,21(3):119-122
[21] Brunelli R, Poggio T. Feature recognition: Features versus templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(10): 1042-1052
[22] A.L.Yuille, P.W.Hallinan, D.S.Cohen. Feature extraction from faces using deformable templaet. International journal of Computer Vision, 1992, 8(2): 99-111
[23] Reisfeld D. Yesburun Y. PreProcessing of face images detection of features and pose normalization. IEEE Trans Computer Vision and Image Understanding, 1998, 3(71): 413-420
[24] ZhouJie, LuChun Yu, ZhangChang Shui. Human face locations based on directional symmetry transform. Acta Electronica Sinica, 1999, 27(8): 12-15
[25] 刘文予,潘峰.离散对称变换在人脸图像眼睛定位中的应用.红外与毫米波学报,2001,20(5):375-380
[26] Shi Hong Jeng, Hong Yuan Mark Yang Chern, Yao Tsorng Liu.Liao, Chin Chuan Han. Ming Facial Feature Detection Sing Geometrical Face Recognition, p MODEL: An Efficient Approach.Pattern, 1998, 31(3): 273-282
[27] Yang G, Huang T.S. Human face detection in a complex background. Pattern Recognition, 1994, 27: 53-63
[28] Waite J, Vincent J. A probabilistic framework for neural network facial feature location. British Telecom Technology Journal, 1992, 10(3): 20-29
[29] Reinders M.J.T, Koch R.W.C, Gerbrands J.J. Locating facial features in image sequences using neural networks. In: Proc. Automatic Face and Gesture Recognition, 1996: 230-235
[30] Bichsel M. Strategies of robust object recognition for the automatic identification of human faces. Zurich: ETH Zurich, 1991
[31] Hayit Greenspan, Jacob Goldberger, Itay Eshet. Mixture model for face-color modeling and segmentation. Pattern Recognition Letters, 2001, 22(14): 1525-1536
[32] Son Lam Phung, Douglas Chai, Bouzerdoum. Skin Color Based Face Detection. Intelligent Information Systems Conference, 2001: 171-176
[33] Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces. Opt.Soc, 1987, 4: 519-524
[34] Cootes T.F, Taylor C.J. Locating Faces Using Statistical Feature Detectors. Automatic Face and Gesture Recognition, 1996: 204-209
[35] Vapnik V.N. Statistical Learning Theory. New York:John Wiley & Sons, 1998
[36] Pan G, Lin W.X, Wu Z.H, Yang Y.C. An eye detection system based on SVM filter. Electronic Imaging and Multimedia Technology III, Proceedings of SPIE, 2002, 4925: 326-331
[37] Dihua Li, Podolak I.T, Lee S.W. Facial Component Extraction and Face Recognition with Support Vector Machines. Automatic Face and Gesture Recognition, 2002: 76-81
[38] Heisele B, Serre T, Pontil M, Poggio T. Component based face detection. Computer Vision and Pattern Recognition, 2001(1): 657-662
[39] Samaria F.S. Face Recognition Using Hidden Markov Models. Univ.of Cambridge, 1994
[40] Feng G C, Yuen P C. Variance projection function and its application to eye detection for human face recognition. Pattern Recognition Letters, 1998, 19(9): 899-906
[41] 耿新,周志华,陈世福.基于混合投影函数的眼睛定位.软件学报,2003,14(08):1394-1400
[42] Jones M. J, Rehg J.M. Statistical color models with application to skin detection. IEEE Computer Vision and Pattern Recognition,Fort Collins, Colorado,1999:274-280
[43] Martinkauppi B. Face color under varying illumination analysis and applications.PhD thesis, University of Oulu,2002
[44] Rafael C. Gonzalez Richad E.Woods.数字图像处理(第二版).阮秋琦,阮宇智译.北京.电子工业出版社.2003
[45] 陶霖密,彭振云,徐光祐.人体的肤色特征.软件学报.2001,5
[46] Hsu R L, Abdel mottaleb M, A K Jain. Face detection in color images. IEEE Trans.Pattern Analysis and Machine Intelligence, 2002, 24(5): 696-706
[47] 陈锻生,刘政凯.肤色检测技术综述.计算机学报,2006,29(2):194-207
[48] Hsu R L. Face detection and modeling for recognition. Ph.D.CSE.MSU, 2002
[49] A.Bishnu, B.B.Bhattachaya, M.K.Kundu, C.A.Murthy, T.Acharya. One chipcomputation of Euler number of a binary image for efficient database search. proc.Int.Conf.on Image Processing (ICIP-2001), 2001, 111: 310-313
[50] 张宏林,蔡锐.Visual C++数字图像模式识别技术与工程实践.北京:人民邮电出版社,2003
[51] 张毓晋.图像处理与分析.北京:清华大学出版社,1999:123-124
[52] 李介谷..图像处理技术.上海:上海交通大学出版社,1988:42-45
[53] D.Marr, E.Hildreth. Theory of edge detection.Computer Vision, 1991: 77 -107
[54] 杜干,杜延,管业鹏.基于对称性分析的眼睛定位方法.计算机工程与应用,2005,33:36-37
[55] Canfeng Guo, C.Yuen Pong. Multi-cues eye detection on gray intensity image. Pattern Recognition, 2001, 34: 1033-1046
[56] Abdolhossein Fathi , Mohammad T .Manzuri.Eye detection and tracking in video streams. International Symposium on Communications and Information Technologies, 2004: 1258-1261
[2] 高文.人脸识别研究概述.生物特征识别技术高级研讨班.北京,2003,12
[3] 张燕昆,刘重庆.基于核方法的人脸识别技术的研究.上海交通大学博士论文,2003,10
[4] Burel G, Carel D. Detection and localization of face on digital images. Pattern Recognion Letters, 1994, 15(7): 963-967
[5] Chellappa R, Wilson C L and Sirohey S. Human and Machine Recognition of Face: A Survey, Proc IEEE, 1995, 83(5): 705-740
[6] Allen A.L. Personal Descriptions. London Butterworth,1950:91-104
[7] Parke F.L. Computer geberated animation of faces. In Proceedings ACMann Conference, 1972, l: 451-457
[8] Goldstion R.J, Harmon L.D, LeskA.B. Man-machine interaction in human face identication Bell Syst. Tech.Journal, 2001, 51: 399-427
[9] KayaY, Kobayashi K. A basic study on human recognition. In Frontiers of Pattern Recognition, New York: Academic, 2004: 265-289
[10] Kanada T. Picture Processing system by computer and recognition of human faces. Ph.D Dissertation.Kyoto:KyotoUniversity,2003:27-46
[11] Baron R.J. Mechanisms of human facial recognition. In T.J Man Machine Studies, 1981, 15: 137-178
[12] M.Turk, A.Pentland. Eigenfaces for Recognition. Journal of Cognitive Neurosicence, 1991, 3(1): 71-86
[13] D.Valentin, H.Abdi, B.Edelman, A.J.OToole. Principal Component and Neural Network Analyses of Face Images: What Can Be Generalized in Gender Classification. Journal of Mathematical Psychology, 1997, 41: 398-412
[14] 周激流,张晔.人脸识别理论研究进展.计算机辅助设计与图形学学报,1999,11(2):180-184
[15] R.Chellappa, C.L.Wilson, S.Sirohey. Human and Machine Recognition of Faces: A Servey, Proc.IEEE, 1995, 83(5): 705-740
[16] 孙大瑞,吴乐南.基于 Gabor 变换的人眼定位.电路与系统学报,2001,6(4):29-32
[17] 蔡国松,卢广山,王合龙.眼跟踪技术.电光与控制,2004,11(1):71-73
[18] 周玉彬,俞梦孙.用红外图像实时跟踪的和监测眼睛的方法.北京生物医学工程,2003,22(2):104-108
[19] 吴林托,李芳,栩步军等.基于红外 LED 的人眼快速定位与跟踪的研究.光学仪器,2006,28(1):85-88
[20] 杨彬,黄耀志.基于 PERCL0S 的汽车司机疲劳监控方法的研究.微计算机信息.2005,21(3):119-122
[21] Brunelli R, Poggio T. Feature recognition: Features versus templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(10): 1042-1052
[22] A.L.Yuille, P.W.Hallinan, D.S.Cohen. Feature extraction from faces using deformable templaet. International journal of Computer Vision, 1992, 8(2): 99-111
[23] Reisfeld D. Yesburun Y. PreProcessing of face images detection of features and pose normalization. IEEE Trans Computer Vision and Image Understanding, 1998, 3(71): 413-420
[24] ZhouJie, LuChun Yu, ZhangChang Shui. Human face locations based on directional symmetry transform. Acta Electronica Sinica, 1999, 27(8): 12-15
[25] 刘文予,潘峰.离散对称变换在人脸图像眼睛定位中的应用.红外与毫米波学报,2001,20(5):375-380
[26] Shi Hong Jeng, Hong Yuan Mark Yang Chern, Yao Tsorng Liu.Liao, Chin Chuan Han. Ming Facial Feature Detection Sing Geometrical Face Recognition, p MODEL: An Efficient Approach.Pattern, 1998, 31(3): 273-282
[27] Yang G, Huang T.S. Human face detection in a complex background. Pattern Recognition, 1994, 27: 53-63
[28] Waite J, Vincent J. A probabilistic framework for neural network facial feature location. British Telecom Technology Journal, 1992, 10(3): 20-29
[29] Reinders M.J.T, Koch R.W.C, Gerbrands J.J. Locating facial features in image sequences using neural networks. In: Proc. Automatic Face and Gesture Recognition, 1996: 230-235
[30] Bichsel M. Strategies of robust object recognition for the automatic identification of human faces. Zurich: ETH Zurich, 1991
[31] Hayit Greenspan, Jacob Goldberger, Itay Eshet. Mixture model for face-color modeling and segmentation. Pattern Recognition Letters, 2001, 22(14): 1525-1536
[32] Son Lam Phung, Douglas Chai, Bouzerdoum. Skin Color Based Face Detection. Intelligent Information Systems Conference, 2001: 171-176
[33] Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces. Opt.Soc, 1987, 4: 519-524
[34] Cootes T.F, Taylor C.J. Locating Faces Using Statistical Feature Detectors. Automatic Face and Gesture Recognition, 1996: 204-209
[35] Vapnik V.N. Statistical Learning Theory. New York:John Wiley & Sons, 1998
[36] Pan G, Lin W.X, Wu Z.H, Yang Y.C. An eye detection system based on SVM filter. Electronic Imaging and Multimedia Technology III, Proceedings of SPIE, 2002, 4925: 326-331
[37] Dihua Li, Podolak I.T, Lee S.W. Facial Component Extraction and Face Recognition with Support Vector Machines. Automatic Face and Gesture Recognition, 2002: 76-81
[38] Heisele B, Serre T, Pontil M, Poggio T. Component based face detection. Computer Vision and Pattern Recognition, 2001(1): 657-662
[39] Samaria F.S. Face Recognition Using Hidden Markov Models. Univ.of Cambridge, 1994
[40] Feng G C, Yuen P C. Variance projection function and its application to eye detection for human face recognition. Pattern Recognition Letters, 1998, 19(9): 899-906
[41] 耿新,周志华,陈世福.基于混合投影函数的眼睛定位.软件学报,2003,14(08):1394-1400
[42] Jones M. J, Rehg J.M. Statistical color models with application to skin detection. IEEE Computer Vision and Pattern Recognition,Fort Collins, Colorado,1999:274-280
[43] Martinkauppi B. Face color under varying illumination analysis and applications.PhD thesis, University of Oulu,2002
[44] Rafael C. Gonzalez Richad E.Woods.数字图像处理(第二版).阮秋琦,阮宇智译.北京.电子工业出版社.2003
[45] 陶霖密,彭振云,徐光祐.人体的肤色特征.软件学报.2001,5
[46] Hsu R L, Abdel mottaleb M, A K Jain. Face detection in color images. IEEE Trans.Pattern Analysis and Machine Intelligence, 2002, 24(5): 696-706
[47] 陈锻生,刘政凯.肤色检测技术综述.计算机学报,2006,29(2):194-207
[48] Hsu R L. Face detection and modeling for recognition. Ph.D.CSE.MSU, 2002
[49] A.Bishnu, B.B.Bhattachaya, M.K.Kundu, C.A.Murthy, T.Acharya. One chipcomputation of Euler number of a binary image for efficient database search. proc.Int.Conf.on Image Processing (ICIP-2001), 2001, 111: 310-313
[50] 张宏林,蔡锐.Visual C++数字图像模式识别技术与工程实践.北京:人民邮电出版社,2003
[51] 张毓晋.图像处理与分析.北京:清华大学出版社,1999:123-124
[52] 李介谷..图像处理技术.上海:上海交通大学出版社,1988:42-45
[53] D.Marr, E.Hildreth. Theory of edge detection.Computer Vision, 1991: 77 -107
[54] 杜干,杜延,管业鹏.基于对称性分析的眼睛定位方法.计算机工程与应用,2005,33:36-37
[55] Canfeng Guo, C.Yuen Pong. Multi-cues eye detection on gray intensity image. Pattern Recognition, 2001, 34: 1033-1046
[56] Abdolhossein Fathi , Mohammad T .Manzuri.Eye detection and tracking in video streams. International Symposium on Communications and Information Technologies, 2004: 1258-1261