基于Boosting算法的头部、脸部、眼睛和嘴检测技术研究
|
摘要
本论文主要研究基于Boosting算法的头部、脸部、眼睛和嘴检测。在目前的人机图像交互领域中,包含有人脸识别、姿态估计、表情识别等多个方向的研究。而头部、脸部、眼睛和嘴检测是它们的前端课题,越来越受到研究者的普遍重视。
本文系统地归纳、总结了当前常用的头部、脸部、眼睛和嘴检测方法,首次将头部、脸部、眼睛和嘴检测方法集中在一起,进行系统地研究,分析比较了这些方法各自的优缺点。扩展了基于AdaBoost算法的脸部检测方法。目前,已经有人提出了基于AdaBoost算法的脸部检测,并取得了较好的结果。本文在原方法的基础上,进行了扩展,实现了基于AdaBoost算法的头部、眼睛和嘴检测。本文设计了实验流程,通过大量的实验,训练产生了头部、眼睛和嘴检测的Boosting分类器,在实际检测中取得了较好的效果。实验证明了基于AdaBoost算法的头部、眼睛和嘴检测鲁棒性比较好,而且基本能满足实时性的需求。
In this thesis, we study the human head, face, eyes and mouth detection based on Boosting algorithm. Nowadays, in the field of the image interface between human and machine, research consists of face recognition, pose estimation and etc. The detection of human head, face, eyes and mouth is a hot topic and deserve the attention of researchers.
We study the methods of human head, face, eyes and mouth detection at state of arts, classify all the methods for the first time, and analyze the merits and deficiency of all these methods. We introduce the approaches of head, face, eyes and mouth detection based on the AdaBoost algorithm. There exists numbers of researchers who have performed face detection based on AdaBoost, we extend the approach to head, face, eyes and mouth detection. We perform experiments on real images and analyze the results. We design the flow chart of the experiments, train the Boosting classifiers of the head, face, eyes and mouth detection. Experimental results demonstrate the good performance of our methods. The experimental results show the robustness of the AdaBoost method, and it maintains the real-time requirement.
本文系统地归纳、总结了当前常用的头部、脸部、眼睛和嘴检测方法,首次将头部、脸部、眼睛和嘴检测方法集中在一起,进行系统地研究,分析比较了这些方法各自的优缺点。扩展了基于AdaBoost算法的脸部检测方法。目前,已经有人提出了基于AdaBoost算法的脸部检测,并取得了较好的结果。本文在原方法的基础上,进行了扩展,实现了基于AdaBoost算法的头部、眼睛和嘴检测。本文设计了实验流程,通过大量的实验,训练产生了头部、眼睛和嘴检测的Boosting分类器,在实际检测中取得了较好的效果。实验证明了基于AdaBoost算法的头部、眼睛和嘴检测鲁棒性比较好,而且基本能满足实时性的需求。
In this thesis, we study the human head, face, eyes and mouth detection based on Boosting algorithm. Nowadays, in the field of the image interface between human and machine, research consists of face recognition, pose estimation and etc. The detection of human head, face, eyes and mouth is a hot topic and deserve the attention of researchers.
We study the methods of human head, face, eyes and mouth detection at state of arts, classify all the methods for the first time, and analyze the merits and deficiency of all these methods. We introduce the approaches of head, face, eyes and mouth detection based on the AdaBoost algorithm. There exists numbers of researchers who have performed face detection based on AdaBoost, we extend the approach to head, face, eyes and mouth detection. We perform experiments on real images and analyze the results. We design the flow chart of the experiments, train the Boosting classifiers of the head, face, eyes and mouth detection. Experimental results demonstrate the good performance of our methods. The experimental results show the robustness of the AdaBoost method, and it maintains the real-time requirement.
引文
[1]颜丰,方晓彤.复杂环境下的头部检测方法研究[J].福建电脑,2006,1:46-48
[2]孙宁,邹采荣,赵力.人脸检测综述[J].电路与系统学报,2006,12,Vol.11,No.6:101-108
[3]Bledsoe.W,"Man-machine facial recognition",Panoranic Research Inc,Paloi A Ito,CA,1966,Rep PRI:22
[4]Berto.R,Poggio.T," Face recognition:Feature Versus templates" IEEE Trans on PAMI,1993,15(10):1024-1052
[5]Guodong Guo.Support Vector machines for face recognition.Image and Vision Computing,2001,19:631-638
[6]Theodore B.An Analytic Center Machine.Machine Learning
[7]李子青," Face Recognition:statistical leaming and subspace analysis methods",在教育部第一界生物特征识别高级研讨班上的报告,北京交通大学.2003年12月
[8]高文,在教育部“第一界生物特征识别高级研讨班”上的讲义“人脸识别概述”,北京,北京交通大学,2003.12
[9]Mckenna S J.Gong S.Raja Y."Modelling Facial Colour and identity with Gaussian Mistures"[J]Pattern Recogintion,1998
[10]M J Jones,J M Rehg.Statistical color models with application to skin detection[J].Int' Journal of Computer Vision archive,2002,46:81-96
[11]M J Jones J M Rehg "Statistical color models with application to skin detection"
[12]梁路宏,艾海舟,何克忠等.基于多关联模版匹配的人脸检测[J],软件学报2001:12(1):94-102
[13]M.Hu,S.Worrall,A.H.Sadka,A.M.Kondoz" Face feature detection and model design for 2-D scalable model-bassed video coding" Centre for Communication Systems Research,University of Surrey,Guildford,Surrey,GU2 7XH,U.K
[14]Jong-Gook Ko,Kyung-Nam Kim,and R.S.Ramakrishna" Facial Feature Tracking for Eye-Head Controlled Human Computer Interface" Department of Information and Communications
[15]J Yang,A Waibel.A real-time face tracker[A].IEEE Proc.of the 3~(rd)Workshop on Applications of Computer Vision[C].Florida,1996
[16]H P Graf,T Chen,E Petajan,et al.Locating Faces and Facial Parts[A].Proc.First Int'l Workshop Automatic Face and Gesture Recognition[C].1995.41-46
[17]T S Jebara,K Russell,A Pentland.Mixtures of Eigenfeatures for Real-Time Structure from Texture[A].Prec.Sixth IEEE Int'l Conf.Computer Vision[C].1998.128-135
[18]刘明宝,姚鸿勋,高文.彩色图像的实时人脸跟踪方法[[J].计算机学报,1998,21(6):527-532
[19]T W YOO,I S Oh.A fast algorithm for tracking human faces based on chromatic histograms[J].Pattern Recognition Letters,1999,20(10):967-978
[20]D Chai,K N Ngan.Locating Facial Region of a Head-and-Shoulders Color Image[A].Proc.Third Int'I Conf.Automatic Face and Gesture Recognition[C].1998.124-129
[21]M J Jones,J M Rehg.Statistical color models with application to skin detection[J].Int' Journal of Computer Vision archive,2002,46:81-96
[22]R L Hsu,M Abdel-Mottaleb,A K Jain.Face Detection in Color Images[J].IEEE Transactions on Pattern Analysis and Machine Inteligence,2002,24:696-706
[23]艾海舟,梁路宏,徐光佑,等.基于肤色和模板的人脸检测[J].软件学报,2001,12(12):1784-1792
[24]J Dowdall,I Pavlidis,G Bebis.Face Detection in the Near-IR Spectntm Image and Vision Computing[Z].2003,21:565-578
[25]C K Eveland,D A Socolinsky,L B Wolff.Tracking human faces in infrared video Image and Vision Computing[Z].2003,21:579-590
[26]G Yang,T S Huang.Human Face Detection in Complex Background Pattern Recognition[J].1994,27(1):53-63
[27]H P Graf,et al.locating Faces and Facial Parts[A].Proc.1" lnt'l Workshop Automatic Face and Gesture Recognition[C].1995.41-46
[28]T K Ieung,et al.Finding Faces in Cluttered Scenes Using Random Labeled Graph Vision[C].1995.637-644,Matching[A].Proc.5th IEEE Int'l Conf.Computer
[29]王延江,袁宗宝,唐晚芳.一种快速彩色图像中复杂背景下人脸检测方法[J]电子学报,2002,30(10):1566-1569
[30]I Craw,H Ellis,J Lishman.Automatic Extraction of Face Features[J].Pattern Recognition Letters,1987,5:183-187
[31]梁路宏,艾海舟,何克忠.基于多模板匹配的单人脸检测[J]中国图象图形学报,1999,4(10):825-830
[32]Rowley H A,Baluja S,Kanade T.Rotation invariant neural network-based face detection.Carnegie Mellon University,Pittsburgh PA:Technical Report CMU-CS-97-201,1997
[33]Rowley H A,Baluja S,Kanade T.Neural network-based face detection.IEEE Trans Pattern Analysis and Machine Intelligence,1998,20(1):23-38
[34]Rowley H A.Neural network-based face detection.Carnegie Mellon University,Pittsburgh PA:Technical Report CMUCS-99-117,1999
[35]H M EI-Bakry,H Stoyan.Fast neural networks for sub-matrix(object/face)detection,Circuits and Systems
[36]M Turk,A Pentland.Eigenfaces for Recognition[J].J.cognitive Neuroscience,1991,3(1):71-86
[37]B Moghaddam,A Pentland.Probabilistic visual learning for object representation[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1997,19(7):696-710
[38]K K Sung,T Poggio.Example-Based Learning for View-Based Human Face Detection[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1998,20(1):39-51
[39]M H Yang,N Ahuja,D Kriegman.Mixtures of Linear Subspaces for Face Detection[A].Proc.Fourth Int'I Conf.Automatic Face and Gesture Recognition[C].2000.70-76
[40]V Vapnik.The Nature of Statistical Learning Theory[M].New York,Springer-Verlag,1995
[41]E Osuna,R Freund,F Girosi.Training support vector machines:An 即placation to face detection[A].Proc.Computer Vision and Pattern Recognition[C].1997.130-136
[42]J C Platt.Sequential minimal optimization:A fast algorithm for training support vector machines[R].MSR:Technical Report MSR-TR-98-14,1998
[43]梁路宏,艾海舟,肖习攀,等.基于模板匹配与支持向量机的人脸检测[J].计算机学报,2002,25(1):22-29
[44]祝海龙,屈梁生,张海军.基于小波变换和支持向量机的人脸检测系统[J].西安交通大学学报,2002,36(9):947-950
[45]A V Nefian,M H Hayes.Face detection and recognition using hidden Markov models[A].Proc IEEE Conference on Image Processing[C].Chicago,1998.141-145
[46]A V Nefian,M H Hayes.An embeddcn HMM based approach for face detection and recognition[A].Proc IEEE Conference nn Acoustics Speech,and Signal Processing[C].Phoenix,1999.3553-3556
[47]陈茂林,戚飞虎.自组织隐马尔可夫模型的人脸检测研究[J].计算机学报,2002,25(11):1165-1169
[48]P Viola,M Jones.Robust real time object detection[A].8~(th) IEEE International Conference on Computer Vision(ICCV)[C].Vancouver,British Columbia,2001
[49]S Z Li,Z Q Zhang.FloatBoost learning and statistical face detection[J].IEEE Trans.Pattern Analysis and Machine Intelligence,2004,28(9):1112-1123
[50]R Xiao,M J Li,H J Zhang.Robust multipose face detection in images[J].IEEE Trans.Circuits and Systems for Video Technology,2004,14(1):31-41
[51]王湘平,张星明.基于Gabor小波的眼睛和嘴巴检测算法[A].计算机工程, 2005,22:169-171
[52]万里红,董兰芳,陈意云。一种快速鲁棒的唇部建模方法研究与实现[A],2006,23:207-210
[53]Duda,R.O.;李宏东等译.模式分类[M].北京:机械工业出版社,2003.9
[54]Yoav Freund and Robert E.Schapire.A decision-theoretic generalization of on-line learning and an application to boosting Journal of Computer and System Sciences,55(1):119-139,August 1997
[55]Schapire R.E.Singer Y.Boost Texer:A system for multiclass multi-table text categorization.Machine Ixaming.1998
[56]Friedman J,Hastie T,Tibshirani R.Additive logistic regression:a statistical view of boosting:[Technical Report],1998
[57]Schapire R.E.Singer Y.Using output codes to boost multiclass teaming problems.In:machine Teaming:Proc.Of the fourteenth international conference.313-321,1997
[58]Robert E.Schapire and Singer Y.Improved boosting algorithms using confidence-rated predictions.ln Proceedings of the Eleventh Annual Conference on Computational Learning Theory,To appear,Machine Learning.pages 80-91,1998
[59]LIENHART R,MAYDT J.An extended set of haar-like features for rapid object detection[J].IEEE ICP 2002,1:900-903
[2]孙宁,邹采荣,赵力.人脸检测综述[J].电路与系统学报,2006,12,Vol.11,No.6:101-108
[3]Bledsoe.W,"Man-machine facial recognition",Panoranic Research Inc,Paloi A Ito,CA,1966,Rep PRI:22
[4]Berto.R,Poggio.T," Face recognition:Feature Versus templates" IEEE Trans on PAMI,1993,15(10):1024-1052
[5]Guodong Guo.Support Vector machines for face recognition.Image and Vision Computing,2001,19:631-638
[6]Theodore B.An Analytic Center Machine.Machine Learning
[7]李子青," Face Recognition:statistical leaming and subspace analysis methods",在教育部第一界生物特征识别高级研讨班上的报告,北京交通大学.2003年12月
[8]高文,在教育部“第一界生物特征识别高级研讨班”上的讲义“人脸识别概述”,北京,北京交通大学,2003.12
[9]Mckenna S J.Gong S.Raja Y."Modelling Facial Colour and identity with Gaussian Mistures"[J]Pattern Recogintion,1998
[10]M J Jones,J M Rehg.Statistical color models with application to skin detection[J].Int' Journal of Computer Vision archive,2002,46:81-96
[11]M J Jones J M Rehg "Statistical color models with application to skin detection"
[12]梁路宏,艾海舟,何克忠等.基于多关联模版匹配的人脸检测[J],软件学报2001:12(1):94-102
[13]M.Hu,S.Worrall,A.H.Sadka,A.M.Kondoz" Face feature detection and model design for 2-D scalable model-bassed video coding" Centre for Communication Systems Research,University of Surrey,Guildford,Surrey,GU2 7XH,U.K
[14]Jong-Gook Ko,Kyung-Nam Kim,and R.S.Ramakrishna" Facial Feature Tracking for Eye-Head Controlled Human Computer Interface" Department of Information and Communications
[15]J Yang,A Waibel.A real-time face tracker[A].IEEE Proc.of the 3~(rd)Workshop on Applications of Computer Vision[C].Florida,1996
[16]H P Graf,T Chen,E Petajan,et al.Locating Faces and Facial Parts[A].Proc.First Int'l Workshop Automatic Face and Gesture Recognition[C].1995.41-46
[17]T S Jebara,K Russell,A Pentland.Mixtures of Eigenfeatures for Real-Time Structure from Texture[A].Prec.Sixth IEEE Int'l Conf.Computer Vision[C].1998.128-135
[18]刘明宝,姚鸿勋,高文.彩色图像的实时人脸跟踪方法[[J].计算机学报,1998,21(6):527-532
[19]T W YOO,I S Oh.A fast algorithm for tracking human faces based on chromatic histograms[J].Pattern Recognition Letters,1999,20(10):967-978
[20]D Chai,K N Ngan.Locating Facial Region of a Head-and-Shoulders Color Image[A].Proc.Third Int'I Conf.Automatic Face and Gesture Recognition[C].1998.124-129
[21]M J Jones,J M Rehg.Statistical color models with application to skin detection[J].Int' Journal of Computer Vision archive,2002,46:81-96
[22]R L Hsu,M Abdel-Mottaleb,A K Jain.Face Detection in Color Images[J].IEEE Transactions on Pattern Analysis and Machine Inteligence,2002,24:696-706
[23]艾海舟,梁路宏,徐光佑,等.基于肤色和模板的人脸检测[J].软件学报,2001,12(12):1784-1792
[24]J Dowdall,I Pavlidis,G Bebis.Face Detection in the Near-IR Spectntm Image and Vision Computing[Z].2003,21:565-578
[25]C K Eveland,D A Socolinsky,L B Wolff.Tracking human faces in infrared video Image and Vision Computing[Z].2003,21:579-590
[26]G Yang,T S Huang.Human Face Detection in Complex Background Pattern Recognition[J].1994,27(1):53-63
[27]H P Graf,et al.locating Faces and Facial Parts[A].Proc.1" lnt'l Workshop Automatic Face and Gesture Recognition[C].1995.41-46
[28]T K Ieung,et al.Finding Faces in Cluttered Scenes Using Random Labeled Graph Vision[C].1995.637-644,Matching[A].Proc.5th IEEE Int'l Conf.Computer
[29]王延江,袁宗宝,唐晚芳.一种快速彩色图像中复杂背景下人脸检测方法[J]电子学报,2002,30(10):1566-1569
[30]I Craw,H Ellis,J Lishman.Automatic Extraction of Face Features[J].Pattern Recognition Letters,1987,5:183-187
[31]梁路宏,艾海舟,何克忠.基于多模板匹配的单人脸检测[J]中国图象图形学报,1999,4(10):825-830
[32]Rowley H A,Baluja S,Kanade T.Rotation invariant neural network-based face detection.Carnegie Mellon University,Pittsburgh PA:Technical Report CMU-CS-97-201,1997
[33]Rowley H A,Baluja S,Kanade T.Neural network-based face detection.IEEE Trans Pattern Analysis and Machine Intelligence,1998,20(1):23-38
[34]Rowley H A.Neural network-based face detection.Carnegie Mellon University,Pittsburgh PA:Technical Report CMUCS-99-117,1999
[35]H M EI-Bakry,H Stoyan.Fast neural networks for sub-matrix(object/face)detection,Circuits and Systems
[36]M Turk,A Pentland.Eigenfaces for Recognition[J].J.cognitive Neuroscience,1991,3(1):71-86
[37]B Moghaddam,A Pentland.Probabilistic visual learning for object representation[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1997,19(7):696-710
[38]K K Sung,T Poggio.Example-Based Learning for View-Based Human Face Detection[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1998,20(1):39-51
[39]M H Yang,N Ahuja,D Kriegman.Mixtures of Linear Subspaces for Face Detection[A].Proc.Fourth Int'I Conf.Automatic Face and Gesture Recognition[C].2000.70-76
[40]V Vapnik.The Nature of Statistical Learning Theory[M].New York,Springer-Verlag,1995
[41]E Osuna,R Freund,F Girosi.Training support vector machines:An 即placation to face detection[A].Proc.Computer Vision and Pattern Recognition[C].1997.130-136
[42]J C Platt.Sequential minimal optimization:A fast algorithm for training support vector machines[R].MSR:Technical Report MSR-TR-98-14,1998
[43]梁路宏,艾海舟,肖习攀,等.基于模板匹配与支持向量机的人脸检测[J].计算机学报,2002,25(1):22-29
[44]祝海龙,屈梁生,张海军.基于小波变换和支持向量机的人脸检测系统[J].西安交通大学学报,2002,36(9):947-950
[45]A V Nefian,M H Hayes.Face detection and recognition using hidden Markov models[A].Proc IEEE Conference on Image Processing[C].Chicago,1998.141-145
[46]A V Nefian,M H Hayes.An embeddcn HMM based approach for face detection and recognition[A].Proc IEEE Conference nn Acoustics Speech,and Signal Processing[C].Phoenix,1999.3553-3556
[47]陈茂林,戚飞虎.自组织隐马尔可夫模型的人脸检测研究[J].计算机学报,2002,25(11):1165-1169
[48]P Viola,M Jones.Robust real time object detection[A].8~(th) IEEE International Conference on Computer Vision(ICCV)[C].Vancouver,British Columbia,2001
[49]S Z Li,Z Q Zhang.FloatBoost learning and statistical face detection[J].IEEE Trans.Pattern Analysis and Machine Intelligence,2004,28(9):1112-1123
[50]R Xiao,M J Li,H J Zhang.Robust multipose face detection in images[J].IEEE Trans.Circuits and Systems for Video Technology,2004,14(1):31-41
[51]王湘平,张星明.基于Gabor小波的眼睛和嘴巴检测算法[A].计算机工程, 2005,22:169-171
[52]万里红,董兰芳,陈意云。一种快速鲁棒的唇部建模方法研究与实现[A],2006,23:207-210
[53]Duda,R.O.;李宏东等译.模式分类[M].北京:机械工业出版社,2003.9
[54]Yoav Freund and Robert E.Schapire.A decision-theoretic generalization of on-line learning and an application to boosting Journal of Computer and System Sciences,55(1):119-139,August 1997
[55]Schapire R.E.Singer Y.Boost Texer:A system for multiclass multi-table text categorization.Machine Ixaming.1998
[56]Friedman J,Hastie T,Tibshirani R.Additive logistic regression:a statistical view of boosting:[Technical Report],1998
[57]Schapire R.E.Singer Y.Using output codes to boost multiclass teaming problems.In:machine Teaming:Proc.Of the fourteenth international conference.313-321,1997
[58]Robert E.Schapire and Singer Y.Improved boosting algorithms using confidence-rated predictions.ln Proceedings of the Eleventh Annual Conference on Computational Learning Theory,To appear,Machine Learning.pages 80-91,1998
[59]LIENHART R,MAYDT J.An extended set of haar-like features for rapid object detection[J].IEEE ICP 2002,1:900-903