人脸及其特征点的定位与应用
|
摘要
随着科技技术的不断进步和人们安全意识的逐步提高,人们对基于人脸应用的需求日益剧增。人脸相比于其他人体生物特征更容易观察,更直接,因此基于人脸及其特征点的定位与应用成为当今图像处理领域的研究热点,具有非常广泛的应用前景。人脸识别系统和疲劳检测系统是现在人脸应用方面最具有实际意义的应用,它们关心的都是人类的安全问题,因此具有很重要的研究意义。人脸识别系统关注的是输入图像是否与人脸库的中的图像匹配;疲劳检测系统研究的则是通过一定的准则,根据驾驶员的实时情况对其的疲劳状态进行检测,并在必要时进行预警。它们都需要对人脸进行检测,并对关键特征进行准确定位,从而为后续的工作奠定基础。因此,特征点精确定位是人脸应用的关键,是研究的重点。
本论文对于人脸应用中的人脸定位框的矫正、人脸特征点定位、以及疲劳检测进行了深入研究,并在此基础上对相关算法进行了创新性的改进。论文的主要工作如下:
1)系统地综述了人脸特征点定位和疲劳检测系统的发展历史和研究现状。详细总结了基于灰度信息、基于先验规则、基于几何形状、基于统计等人脸特征点定位方法,并分析和比较各种方法的优缺点。同时介绍了几种疲劳检测方法,并对它们进行了比较和分析。
2)对人脸特殊器官的定位进行了研究,并在此基础上对初始人脸定位框进行了矫正。首先介绍了基于模板的眼睛虹膜定位方法,然后介绍了基于FCM聚类的嘴巴定位方法。最后根据人脸的黄金分割比与实验经验对Adaboost人脸定位框进行了矫正,并比较矫正前后对人脸识别准确度的影响。
3)介绍了基于模型的两种经典的特征点定位算法:主动形状模型(ASM)和主动外观模型(AAM),并且对这两种模型分别进行了实验,通过理论地分析和实验对ASM和AAM算法进行比较,讨论了这两种传统方法的优缺点。
4)基于传统的主动形状模型(ASM)思想,提出了模板匹配搜索(TMS)算法,进一步提高了定位精度,达到鲁棒精确地定位特征点的目的。同时弥补了ASM只能对完全正面人脸进行定位的不足。
5)模拟驾驶场景,对眼睛和嘴巴进行定位,并计算眼睛与嘴巴的面积,从而得到眨眼次数,并且根据不同情况进行分析和判定,在必要时系统会发出警告。
With the fast development of technology and gradual improvement of people awareness of safety, the demand for application on human face is increasingly urgent. Comparing with other human biological characteristics, face characteristics are prone to observe and direct, therefore detection of human face and its features and relevant application become the research focus of the field of image processing and has extensive application future. Face recognition system and fatigue detection system are the most important face applications which care about the safety problems related with human and have done great help to human safety, accordingly the research on them is of great importance. The face recognition system pays much attention to whether an input image is matched with the training images. The fatigue detection system works to detect and analyze whether a driver is tired or not based on real-time situation and sends out the warning if necessary. Both of the two systems need to detect the face firstly and then detect the critical features on human face, which is the basis of consequent work. So, how to detect the features accurately is the key to the face application and the emphasis of our research.
In this dissertation, refinement of detection of human face, algorithms of facial features extraction, fatigue detection and relevant application were profoundly researched, based on which the classical algorithms, novel and creative improvement was proposed. The main discussion of the dissertation is listed as follows:
1) The history and status of research on facial features extraction and fatigue detection system are systematically summarized. Detailed kinds of feature points extraction approaches, including grey-level-based algorithm, knowledge-based algorithm, Geometry-base algorithm, statistic-based algorithm, wavelet-base algorithm, and then analyze the different algorithm. Also, some methods to detect the fatigued status of human are introduced and analyzed.
2) The algorithms of locating rough position of special facial organs are researched, based on which the detection of face is improved. Firstly, eyes locating methods using templates is introduced, and Clustering-based mouth locating method is advanced. According to the golden selection and experiences, correction of the frame of the face is made and the results before and after the correction are compared.
3) Two classical algorithms of facial features detection are introduced: Active Shape Model (ASM) and Active Appearance Model (AAM). Experiments are made with comparing the two algorithms not only in theory but also in real use, and then we conclude the merits and weakness of them and propose the improving solution.
4) A new method of facial features detection called Templates Matching Searching(TMS) based on some ideas of traditional Active Shape Model is presented. And it turned out that facial feature points can be located robustly and precisely using the method proposed. Experiments demonstrate that our algorithm for the facial feature extraction is precise and overcome the past defect that the features can be accurately extracted when searching the completely frontal face images.
5) Eyes and mouth are detected in each frame of a video in a driving situation, and then their areas are computed, from which we can get the frequency of eyes’blinking. Analysis and decisions are made for different conditions, and our system will send the warning when finding abnormity of a driver.
本论文对于人脸应用中的人脸定位框的矫正、人脸特征点定位、以及疲劳检测进行了深入研究,并在此基础上对相关算法进行了创新性的改进。论文的主要工作如下:
1)系统地综述了人脸特征点定位和疲劳检测系统的发展历史和研究现状。详细总结了基于灰度信息、基于先验规则、基于几何形状、基于统计等人脸特征点定位方法,并分析和比较各种方法的优缺点。同时介绍了几种疲劳检测方法,并对它们进行了比较和分析。
2)对人脸特殊器官的定位进行了研究,并在此基础上对初始人脸定位框进行了矫正。首先介绍了基于模板的眼睛虹膜定位方法,然后介绍了基于FCM聚类的嘴巴定位方法。最后根据人脸的黄金分割比与实验经验对Adaboost人脸定位框进行了矫正,并比较矫正前后对人脸识别准确度的影响。
3)介绍了基于模型的两种经典的特征点定位算法:主动形状模型(ASM)和主动外观模型(AAM),并且对这两种模型分别进行了实验,通过理论地分析和实验对ASM和AAM算法进行比较,讨论了这两种传统方法的优缺点。
4)基于传统的主动形状模型(ASM)思想,提出了模板匹配搜索(TMS)算法,进一步提高了定位精度,达到鲁棒精确地定位特征点的目的。同时弥补了ASM只能对完全正面人脸进行定位的不足。
5)模拟驾驶场景,对眼睛和嘴巴进行定位,并计算眼睛与嘴巴的面积,从而得到眨眼次数,并且根据不同情况进行分析和判定,在必要时系统会发出警告。
With the fast development of technology and gradual improvement of people awareness of safety, the demand for application on human face is increasingly urgent. Comparing with other human biological characteristics, face characteristics are prone to observe and direct, therefore detection of human face and its features and relevant application become the research focus of the field of image processing and has extensive application future. Face recognition system and fatigue detection system are the most important face applications which care about the safety problems related with human and have done great help to human safety, accordingly the research on them is of great importance. The face recognition system pays much attention to whether an input image is matched with the training images. The fatigue detection system works to detect and analyze whether a driver is tired or not based on real-time situation and sends out the warning if necessary. Both of the two systems need to detect the face firstly and then detect the critical features on human face, which is the basis of consequent work. So, how to detect the features accurately is the key to the face application and the emphasis of our research.
In this dissertation, refinement of detection of human face, algorithms of facial features extraction, fatigue detection and relevant application were profoundly researched, based on which the classical algorithms, novel and creative improvement was proposed. The main discussion of the dissertation is listed as follows:
1) The history and status of research on facial features extraction and fatigue detection system are systematically summarized. Detailed kinds of feature points extraction approaches, including grey-level-based algorithm, knowledge-based algorithm, Geometry-base algorithm, statistic-based algorithm, wavelet-base algorithm, and then analyze the different algorithm. Also, some methods to detect the fatigued status of human are introduced and analyzed.
2) The algorithms of locating rough position of special facial organs are researched, based on which the detection of face is improved. Firstly, eyes locating methods using templates is introduced, and Clustering-based mouth locating method is advanced. According to the golden selection and experiences, correction of the frame of the face is made and the results before and after the correction are compared.
3) Two classical algorithms of facial features detection are introduced: Active Shape Model (ASM) and Active Appearance Model (AAM). Experiments are made with comparing the two algorithms not only in theory but also in real use, and then we conclude the merits and weakness of them and propose the improving solution.
4) A new method of facial features detection called Templates Matching Searching(TMS) based on some ideas of traditional Active Shape Model is presented. And it turned out that facial feature points can be located robustly and precisely using the method proposed. Experiments demonstrate that our algorithm for the facial feature extraction is precise and overcome the past defect that the features can be accurately extracted when searching the completely frontal face images.
5) Eyes and mouth are detected in each frame of a video in a driving situation, and then their areas are computed, from which we can get the frequency of eyes’blinking. Analysis and decisions are made for different conditions, and our system will send the warning when finding abnormity of a driver.
引文
[1] Viola P, Jones M. Robust real time object detection Technical Report. CRL 2001/01, Compaq Cambridge Research Laboratory, February 2001.
[2] X.Xie, R.Sudhakar, and H.Zhuang, Corner Detection by a cost minimization approach[J]. Pattern Recognition, 1993, 26(8): 1235‐1243.
[3] Jiann‐shu Lee, Yung N. Sun, Chin‐Hsing Chen, Ching‐Tsomg Tsai, Wavelet Based Corner Detection[J]. Pattern Recognition, 1993, 26(6):853‐865.
[4] Yuille A.L., Hallinan P.W.&Cohen, Feature extraction from faces using deformable templates[J]. International Journal of Computer Vision, 8:99‐111
[5] A.R.Mirhosseini, H.Yan, and K.M.Lam, An adaptive deformable model for mouth boundary modeling, Opt.Eng.1998.3
[6] Craw.l, Tock.D, &Bennet.A , Finding face features[J]. In Proceedings 2nd European Conference on Computer Vision,1992,92‐96
[7] Huang, C.L.&Chen C.W. Human facial feature‐extraction for face interpretation and recognition[J]. Pattern Recognition,1992,25 (12):435‐444
[8] Chow, G.&Li, X.B. (1993). Towards a system for automatic facial feature detection[J]. Pattern Recognition, 1993, 26(12):1739‐1755
[9] Xie, X., Sudhakar, R.&Zhuang,H . Corner Detection By a Cost Minimization Approach[J]. Patern Recognition, 1993, 26(8):1235‐1243
[10] Xie, X., Sudhakar, R.&Zhuang, H. On improving eye feature‐extraction using deformable templates[J]. Pattern Recognition, 1994,27(6):791‐799
[11] Stephen J. Mckenna, Shaogang Gong, Tracking Facial Feature Points with Gabor Wavelets and shape Models[J]. Pro.1st Con. On Audio‐and Video‐based Bio‐metric Person Authentication, Le cture Notes in Computer Science, Springer Verlag,1997,1206:35‐42
[12] M.Kass,A .W itkin and D.Terzopdulos, Active Contour Models, 1st International Conference on Computer Vision, London, June, 1987,pp .25 9‐268
[13] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Haslam, Training Models of Shape from Sets of Examples, in Proc.British Machine Vision Conference.Sp ringer‐Verlag,1992,pp .9‐18.
[14] T.F. Cootes and C.J. Taylor, Active shape models "smart snakes", Proceeding of the British Vision Conference,Leeds, U K, 22‐24 September 1992, London, 1992, Springer‐ Verlag,pp .26 6‐275.
[15] T.F. Cootes, C.J. Taylor, and A. Lanitis, Multi‐Resolution Search with Active Shape Models[J]. Proc .ICPR 1994,1:610‐612
[16] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, Active Shape Models‐Their Training an d Application[J]. Computer Vision and Image Understanding, 1995, 6(1):38‐59
[17] T.F. Cootes, G.J. Edwards, and C.J. Taylor, Active Appearance Models[J]. Proceeding of the 5th European Conference on Computer Vision, 1998,2:484‐498
[18] Li, S.Z, Yan Shuicheng, Zhang Hongjiang, Cheng Qiansheng, Multi‐view face alignment using direct appearance models[J]. 5th IEEE International Conference on Automatic Face and Gesture Recognition, 2002: 309‐314.
[19] H.Rein‐Lien, M.Abdel‐Mottaleb, A.K.Jain. Face detection in color images[J]. IEEE Trans‐actions on Pattern Analysis and Machine Intelligence,2002,24(5):696‐706
[20] N.Friedman, D.Geiger, M.Goldszmidt. Bayesian Network Classifiers. Machine Learning. 1997,29(2):131‐163
[21] D.Edwards. Introduction to Graphical Modeling. Springer,2000
[22] D.Heckerman. A tutorial on learing with Bayesian networks. Learning in Graphical Models.1998:301‐354
[23] K.Murphy. The Bayes Net Toolbox for Matlab[J]. Computing Science and Statistics. 2001,33:331‐351
[24] L.Chengjun. A Bayesian discriminating features method for face detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(6):725‐740
[25] J.HongLiang, L.Qingshan, L.Hanqing, T.Xiaofeng. Face detection using improved LBP under Bayesian framework[J]. International Conference on Image and Graphics, 2004,306‐309
[26] P.Jae Hee, C.Hae Chul, K.Seong Dae. Bayesian face detection in an image sequence using face probability gradient ascent. IEEE International Conference on image Processing. 2005,vol.2,346‐9
[27] M.Lingmin, T.Q.Nguyen, D.A.Casanon. An image‐based Bayesian framework for face detection[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2000,1:302‐307
[28] T.V.Phan, M.Worring, A.W.M.Smeulders. Face detection by aggregated Bayesian network classifiers[J]. Pattern Recognition Letters, 2002,23(4):451‐461
[29] Z.Yi, Z.Wei, T.Xiaoou, S.Harry. A Bayesian miture model for multi‐view face alignment[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2005,2:741‐746
[30] N.Sebe, I.Cohen, T.S.Huang, T.Gevers. Semi‐Supervised Face Detection[J]. IEEE Conference on Computer Vision and Pattern Recognition,2005,3:51‐51
[31] S. Singh, and N.P. Papanikolopoulos, Monitoring driver fatigue usingfacial analysis techniques, in Proc. Int. Conf. Intelligent TransportationSystems, Tokyo, Japan, pp. 314‐318, 1999.
[32] Viola P, Jones M. Robust Real-Time Face Detection[J]. International Journal of ComputerVision, 2004,57(2):137-154.
[33] G. C. Feng, P. C. Yuen. Variance projection function and its application to eye detection for human face recognition[J]. Pattern Recognition Letters, 1998, 19(9):899–906
[34] T.Kawaguchi, M. Rizon. Iris detection using intensity and edge information[J]. Pattern Recognition, 2003,36(2):549‐562
[35] Daniel Reisfeld, Yehezkel Yeshurun, Preprocessing of Face Images:Detection of Features and Pose Normalization[J]. Computer Vision and Image Understanding, 1998,71(3):412‐430
[36] Reinders MJT, Koch RWC, Gerbrands JJ, Locating Facial Features in Images Sequences Using Netural Network, IEEE CS Press,1996,230‐235.
[37] Zhi‐Hua Zhou, Xin Geng, Projection Functions for Eye Detection[J]. Pattern Recognition, 2004,37:1049‐1056.
[38] L. Shu‐Hung, W. Shi‐Lin, L. Wing‐Hong. Lip image segmentation using fuzzy clustering incorporating an elliptic shape function[J]. IEEE Transactions on Image Processing,2004, 13(1):51–62
[39] Xinwen Hou, Stan Z.Li, Hongjiang Zhang, Qiansheng Cheng. Direct appearance models[J]. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001: 828‐833.
[40] Xinwen Hou, Stan Z.Li,Hongjiang Zhang,Qiansheng Cheng. Direct appearance models. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2001: 828‐833.
[41] Shuicheng Yan, Ce Liu, Stan Z.Li, Hongjiang Zhang, Heung‐Yeung Shum, Face alignment using texture‐constrained active shape models[J]. Image and Vision Computing,2003,21(1):69‐75.
[42] Yi Zhou, Lie Gu, Hongjiang Zhang, Bayesian tangent shape model: estimating shape and pose parameters via Bayesian inference[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2003:16‐22.
[43] Feng Jiao, Stan Li, Heung‐Yeung Shum, Dale Schuurmans, Face alignment using statistical models and wavelet feature[J]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2003: 321‐327.
[44] Fei Zuo, Peter H.N.de With, Fast facial feature extraction using a deformable shape model with Haar‐wavelet based local texture attributes[J]. Proceedings of IEEE Conference on Image Processing, 2004: 1425‐1428.
[45] J.C.Gower, Generalized Procrustes analysis, Psychometrika 40, 1975: 33‐51.
[46] T.F Cootes, C.J.Taylor, D.H. Cooper, and J.Graham*. Active Shape Models‐ Their Training and Application[J]. Computer Vision and Image Understanding, 1995, 61(1): 38‐59.
[47]吴证,周越,杜春华.彩色图像人脸特征点定位算法研究[J].上海交通大学学报,2008,36(2):309‐313.
[48] Cootes T F, Edwards G J, Taylor C J. Active appearance model[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2001: 23(6): 681‐685.
[49] G.J Edwards*, A. Lanitis, C.J.Taylor, T.F.Cootes. Statistical models of face images‐improving specificity[J], Image and Vision Computing, 1998,16(3):203‐211.
[50] T.F. Cootes, G.J.Edwards, and C.J.Taylor. Active appearance models[J]. 5th European Conference on Computer Vision. 1998,2: 484‐498.
[51] P.Felzenszwalb and D.Huttenlocher. Pictorial structures for objects recognition[J], International Journal of Computer Vision,2005,61(1):55‐79.
[52] Paul Viola and Michael Jones. Rapid object detection using a boosted cascade of simple features[J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001,1:511–518.
[53] E.Loutas, N.Nikolaidis and I.Pitas. EVALUTION OF TRACKING RELIABILITY METRICS BASED ON INFORMATION THEORY AND NORMALIZED CORRELATION[J]. IEEE Proceedings of the 17th International Conference on Pattern Recognition. 2004,4: 653‐656
[54] J.A Nelder and R.Mead. A simplex method for function minimization[J]. Computer Journal, 1965, 7(4):308‐313.
[55] Yuguang Huang and W F McColl. An improved simplex method for function minimization[J]. IEEE International Conference on Systems,Man,and Cybernetics. 1996,3: 1702‐1705.
[56] D.Cristinacce, T.Cootes. A comparision of shape constrained facial feature detectors[C]// 6th International Conference on Automatic Face and Gesture Recognition. Piscataway,NJ:IEEE Press, 2004:375‐380.
[57] L.M. Bergasa, J.Nuevo, M.A. Sotalo, and M. Vazquez, Real‐time system for monitoring driver vigilance, IEEE Transactions on Intelligent Transportation System,IEEE Press,2006,7(1)
[58] J. Healey, and R. Picard, SmartCar: detecting driver stress[J], in Proc.15th Int. Conf. Pattern Recognition, 2000,4:218‐221
[59] A. Kircher, M.Uddman, and J.Sandin, Vehicle Control and drowsiness,Swedish National Road and Transport Research Institute, 2002.
[60] Anon, Perclos and eyetracking: Challenge and Opportunity, TechnicalReport, Applied Science Laboratories, Bedford, MA, 1999.
[61] H. Ueno, M. Kaneda, and M.Tsukino, Development of drowsinessdetection system, in Proc. Vehicle Navigation and Information Systems Conf., pp.15‐20, 1994
[62] M. Eriksson, and N.P. Papanikotopoulos, Eye‐tracking for detection ofdriver fatigue, in Proc .Int. Conf. Intelligent Transportation Systems,Boston, pp. 314‐319, 1997.
[63] S. Singh, and N.P. Papanikolopoulos, Monitoring driver fatigue usingfacial analysis techniques, in Proc. Int. Conf. Intelligent TransportationSystems, Tokyo, Japan, pp. 314‐318,1999.
[64] E. Wahlstrom, O. Masoud, and N.P. Papanikotopoulos, Vision‐based methods for driver monitoring[J], in Proc. Int. Conf. Intelligent Transportation Systems, 2003,2:903‐908.
[65] P. Smith, M. Shah, and N. da Vitoria Lobo, Monitoring head/eye motion for driver alertness with one camera, in Proc. 15th Int. Conf. Pattern Recognition, Barcelona, Spain, vol. 4, pp. 636‐642, 2000.
[66] P. Smith, M. Shah, and N. da Vitoria Lobo, Determine driver visual attention with one camera, Intelligent Transportation Systems, vol. 4, pp. 205‐218, December 2003.
[67] R. Grace, Drowsy driver monitor and warning system, in Proc. Int. Driving Symp. Human Factors in Driver Assessment, Training and Vehicle Design, 2001.
[68] D.F. Dinges, and R. Grace, PERCLOS: A valid physiological measure of alertness as assessed by psychomotor vigilance, US Department of Transportation, Federal highway Administration. Publication Number FHWA‐MCRT‐98‐006.
[69] R. Grace et al., A drowsy driver detection system for heavy vehicle, in Proc. 17th Digital Avionics Systems Conference, Bellevue, USA, vol. 2, pp. I36/1‐I36/8, 1998.
[70] X. Liu, F.L. Xu, and K. Fujimura, Real‐time eye detection and tracking for driver observation under various light conditions, in Proc. Intelligent Vehicle Symp., Versailles, France, pp. 344‐351, 2002.
[71] H. Gu, Q. Ji, and Z.W. Zhu, Active facial tracking for fatigue detection, in Proc. Workshop on Application of Computer Vision, Orlando, pp. 137‐142, 2002.
[2] X.Xie, R.Sudhakar, and H.Zhuang, Corner Detection by a cost minimization approach[J]. Pattern Recognition, 1993, 26(8): 1235‐1243.
[3] Jiann‐shu Lee, Yung N. Sun, Chin‐Hsing Chen, Ching‐Tsomg Tsai, Wavelet Based Corner Detection[J]. Pattern Recognition, 1993, 26(6):853‐865.
[4] Yuille A.L., Hallinan P.W.&Cohen, Feature extraction from faces using deformable templates[J]. International Journal of Computer Vision, 8:99‐111
[5] A.R.Mirhosseini, H.Yan, and K.M.Lam, An adaptive deformable model for mouth boundary modeling, Opt.Eng.1998.3
[6] Craw.l, Tock.D, &Bennet.A , Finding face features[J]. In Proceedings 2nd European Conference on Computer Vision,1992,92‐96
[7] Huang, C.L.&Chen C.W. Human facial feature‐extraction for face interpretation and recognition[J]. Pattern Recognition,1992,25 (12):435‐444
[8] Chow, G.&Li, X.B. (1993). Towards a system for automatic facial feature detection[J]. Pattern Recognition, 1993, 26(12):1739‐1755
[9] Xie, X., Sudhakar, R.&Zhuang,H . Corner Detection By a Cost Minimization Approach[J]. Patern Recognition, 1993, 26(8):1235‐1243
[10] Xie, X., Sudhakar, R.&Zhuang, H. On improving eye feature‐extraction using deformable templates[J]. Pattern Recognition, 1994,27(6):791‐799
[11] Stephen J. Mckenna, Shaogang Gong, Tracking Facial Feature Points with Gabor Wavelets and shape Models[J]. Pro.1st Con. On Audio‐and Video‐based Bio‐metric Person Authentication, Le cture Notes in Computer Science, Springer Verlag,1997,1206:35‐42
[12] M.Kass,A .W itkin and D.Terzopdulos, Active Contour Models, 1st International Conference on Computer Vision, London, June, 1987,pp .25 9‐268
[13] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Haslam, Training Models of Shape from Sets of Examples, in Proc.British Machine Vision Conference.Sp ringer‐Verlag,1992,pp .9‐18.
[14] T.F. Cootes and C.J. Taylor, Active shape models "smart snakes", Proceeding of the British Vision Conference,Leeds, U K, 22‐24 September 1992, London, 1992, Springer‐ Verlag,pp .26 6‐275.
[15] T.F. Cootes, C.J. Taylor, and A. Lanitis, Multi‐Resolution Search with Active Shape Models[J]. Proc .ICPR 1994,1:610‐612
[16] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, Active Shape Models‐Their Training an d Application[J]. Computer Vision and Image Understanding, 1995, 6(1):38‐59
[17] T.F. Cootes, G.J. Edwards, and C.J. Taylor, Active Appearance Models[J]. Proceeding of the 5th European Conference on Computer Vision, 1998,2:484‐498
[18] Li, S.Z, Yan Shuicheng, Zhang Hongjiang, Cheng Qiansheng, Multi‐view face alignment using direct appearance models[J]. 5th IEEE International Conference on Automatic Face and Gesture Recognition, 2002: 309‐314.
[19] H.Rein‐Lien, M.Abdel‐Mottaleb, A.K.Jain. Face detection in color images[J]. IEEE Trans‐actions on Pattern Analysis and Machine Intelligence,2002,24(5):696‐706
[20] N.Friedman, D.Geiger, M.Goldszmidt. Bayesian Network Classifiers. Machine Learning. 1997,29(2):131‐163
[21] D.Edwards. Introduction to Graphical Modeling. Springer,2000
[22] D.Heckerman. A tutorial on learing with Bayesian networks. Learning in Graphical Models.1998:301‐354
[23] K.Murphy. The Bayes Net Toolbox for Matlab[J]. Computing Science and Statistics. 2001,33:331‐351
[24] L.Chengjun. A Bayesian discriminating features method for face detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(6):725‐740
[25] J.HongLiang, L.Qingshan, L.Hanqing, T.Xiaofeng. Face detection using improved LBP under Bayesian framework[J]. International Conference on Image and Graphics, 2004,306‐309
[26] P.Jae Hee, C.Hae Chul, K.Seong Dae. Bayesian face detection in an image sequence using face probability gradient ascent. IEEE International Conference on image Processing. 2005,vol.2,346‐9
[27] M.Lingmin, T.Q.Nguyen, D.A.Casanon. An image‐based Bayesian framework for face detection[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2000,1:302‐307
[28] T.V.Phan, M.Worring, A.W.M.Smeulders. Face detection by aggregated Bayesian network classifiers[J]. Pattern Recognition Letters, 2002,23(4):451‐461
[29] Z.Yi, Z.Wei, T.Xiaoou, S.Harry. A Bayesian miture model for multi‐view face alignment[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2005,2:741‐746
[30] N.Sebe, I.Cohen, T.S.Huang, T.Gevers. Semi‐Supervised Face Detection[J]. IEEE Conference on Computer Vision and Pattern Recognition,2005,3:51‐51
[31] S. Singh, and N.P. Papanikolopoulos, Monitoring driver fatigue usingfacial analysis techniques, in Proc. Int. Conf. Intelligent TransportationSystems, Tokyo, Japan, pp. 314‐318, 1999.
[32] Viola P, Jones M. Robust Real-Time Face Detection[J]. International Journal of ComputerVision, 2004,57(2):137-154.
[33] G. C. Feng, P. C. Yuen. Variance projection function and its application to eye detection for human face recognition[J]. Pattern Recognition Letters, 1998, 19(9):899–906
[34] T.Kawaguchi, M. Rizon. Iris detection using intensity and edge information[J]. Pattern Recognition, 2003,36(2):549‐562
[35] Daniel Reisfeld, Yehezkel Yeshurun, Preprocessing of Face Images:Detection of Features and Pose Normalization[J]. Computer Vision and Image Understanding, 1998,71(3):412‐430
[36] Reinders MJT, Koch RWC, Gerbrands JJ, Locating Facial Features in Images Sequences Using Netural Network, IEEE CS Press,1996,230‐235.
[37] Zhi‐Hua Zhou, Xin Geng, Projection Functions for Eye Detection[J]. Pattern Recognition, 2004,37:1049‐1056.
[38] L. Shu‐Hung, W. Shi‐Lin, L. Wing‐Hong. Lip image segmentation using fuzzy clustering incorporating an elliptic shape function[J]. IEEE Transactions on Image Processing,2004, 13(1):51–62
[39] Xinwen Hou, Stan Z.Li, Hongjiang Zhang, Qiansheng Cheng. Direct appearance models[J]. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001: 828‐833.
[40] Xinwen Hou, Stan Z.Li,Hongjiang Zhang,Qiansheng Cheng. Direct appearance models. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2001: 828‐833.
[41] Shuicheng Yan, Ce Liu, Stan Z.Li, Hongjiang Zhang, Heung‐Yeung Shum, Face alignment using texture‐constrained active shape models[J]. Image and Vision Computing,2003,21(1):69‐75.
[42] Yi Zhou, Lie Gu, Hongjiang Zhang, Bayesian tangent shape model: estimating shape and pose parameters via Bayesian inference[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2003:16‐22.
[43] Feng Jiao, Stan Li, Heung‐Yeung Shum, Dale Schuurmans, Face alignment using statistical models and wavelet feature[J]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2003: 321‐327.
[44] Fei Zuo, Peter H.N.de With, Fast facial feature extraction using a deformable shape model with Haar‐wavelet based local texture attributes[J]. Proceedings of IEEE Conference on Image Processing, 2004: 1425‐1428.
[45] J.C.Gower, Generalized Procrustes analysis, Psychometrika 40, 1975: 33‐51.
[46] T.F Cootes, C.J.Taylor, D.H. Cooper, and J.Graham*. Active Shape Models‐ Their Training and Application[J]. Computer Vision and Image Understanding, 1995, 61(1): 38‐59.
[47]吴证,周越,杜春华.彩色图像人脸特征点定位算法研究[J].上海交通大学学报,2008,36(2):309‐313.
[48] Cootes T F, Edwards G J, Taylor C J. Active appearance model[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2001: 23(6): 681‐685.
[49] G.J Edwards*, A. Lanitis, C.J.Taylor, T.F.Cootes. Statistical models of face images‐improving specificity[J], Image and Vision Computing, 1998,16(3):203‐211.
[50] T.F. Cootes, G.J.Edwards, and C.J.Taylor. Active appearance models[J]. 5th European Conference on Computer Vision. 1998,2: 484‐498.
[51] P.Felzenszwalb and D.Huttenlocher. Pictorial structures for objects recognition[J], International Journal of Computer Vision,2005,61(1):55‐79.
[52] Paul Viola and Michael Jones. Rapid object detection using a boosted cascade of simple features[J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001,1:511–518.
[53] E.Loutas, N.Nikolaidis and I.Pitas. EVALUTION OF TRACKING RELIABILITY METRICS BASED ON INFORMATION THEORY AND NORMALIZED CORRELATION[J]. IEEE Proceedings of the 17th International Conference on Pattern Recognition. 2004,4: 653‐656
[54] J.A Nelder and R.Mead. A simplex method for function minimization[J]. Computer Journal, 1965, 7(4):308‐313.
[55] Yuguang Huang and W F McColl. An improved simplex method for function minimization[J]. IEEE International Conference on Systems,Man,and Cybernetics. 1996,3: 1702‐1705.
[56] D.Cristinacce, T.Cootes. A comparision of shape constrained facial feature detectors[C]// 6th International Conference on Automatic Face and Gesture Recognition. Piscataway,NJ:IEEE Press, 2004:375‐380.
[57] L.M. Bergasa, J.Nuevo, M.A. Sotalo, and M. Vazquez, Real‐time system for monitoring driver vigilance, IEEE Transactions on Intelligent Transportation System,IEEE Press,2006,7(1)
[58] J. Healey, and R. Picard, SmartCar: detecting driver stress[J], in Proc.15th Int. Conf. Pattern Recognition, 2000,4:218‐221
[59] A. Kircher, M.Uddman, and J.Sandin, Vehicle Control and drowsiness,Swedish National Road and Transport Research Institute, 2002.
[60] Anon, Perclos and eyetracking: Challenge and Opportunity, TechnicalReport, Applied Science Laboratories, Bedford, MA, 1999.
[61] H. Ueno, M. Kaneda, and M.Tsukino, Development of drowsinessdetection system, in Proc. Vehicle Navigation and Information Systems Conf., pp.15‐20, 1994
[62] M. Eriksson, and N.P. Papanikotopoulos, Eye‐tracking for detection ofdriver fatigue, in Proc .Int. Conf. Intelligent Transportation Systems,Boston, pp. 314‐319, 1997.
[63] S. Singh, and N.P. Papanikolopoulos, Monitoring driver fatigue usingfacial analysis techniques, in Proc. Int. Conf. Intelligent TransportationSystems, Tokyo, Japan, pp. 314‐318,1999.
[64] E. Wahlstrom, O. Masoud, and N.P. Papanikotopoulos, Vision‐based methods for driver monitoring[J], in Proc. Int. Conf. Intelligent Transportation Systems, 2003,2:903‐908.
[65] P. Smith, M. Shah, and N. da Vitoria Lobo, Monitoring head/eye motion for driver alertness with one camera, in Proc. 15th Int. Conf. Pattern Recognition, Barcelona, Spain, vol. 4, pp. 636‐642, 2000.
[66] P. Smith, M. Shah, and N. da Vitoria Lobo, Determine driver visual attention with one camera, Intelligent Transportation Systems, vol. 4, pp. 205‐218, December 2003.
[67] R. Grace, Drowsy driver monitor and warning system, in Proc. Int. Driving Symp. Human Factors in Driver Assessment, Training and Vehicle Design, 2001.
[68] D.F. Dinges, and R. Grace, PERCLOS: A valid physiological measure of alertness as assessed by psychomotor vigilance, US Department of Transportation, Federal highway Administration. Publication Number FHWA‐MCRT‐98‐006.
[69] R. Grace et al., A drowsy driver detection system for heavy vehicle, in Proc. 17th Digital Avionics Systems Conference, Bellevue, USA, vol. 2, pp. I36/1‐I36/8, 1998.
[70] X. Liu, F.L. Xu, and K. Fujimura, Real‐time eye detection and tracking for driver observation under various light conditions, in Proc. Intelligent Vehicle Symp., Versailles, France, pp. 344‐351, 2002.
[71] H. Gu, Q. Ji, and Z.W. Zhu, Active facial tracking for fatigue detection, in Proc. Workshop on Application of Computer Vision, Orlando, pp. 137‐142, 2002.