复杂背景下人脸检测方法研究
|
摘要
人脸检测是人脸识别之前的重要和必不可少的步骤,用于确定人脸在视频图像中的位置和大小。随着科学技术的迅猛发展,以及人们对模式识别和计算机交互需求的发展,人脸检测技术也越来越受到人们的重视。
本文是对复杂背景下人脸检测进行研究,在现有技术的基础上,提出了肤色模型与AdaBoost方法相结合的检测方法,肤色模型方面主要是提出了模糊自适应光照补偿方法,结合了不同方法改进了肤色分割和唇色检测的效果;之后采用增加矩形特征的AdaBoost方法训练了新分类器用于人脸检测。
本文的主要工作包括:
肤色是人脸很重要的特征,为了避免光照的影响,首先对图片进行了模糊自适应光照补偿,改进了原有的自适应补偿方法,使补偿之后的效果更易于二值化。之后基于YCbCr模型的基础上进行肤色分割,根据最大类间方差法和阈值调整法进行了肤色块的查找。为了增加肤色检测的正确度,在肤色检测的基础上增加了唇色检测,在唇色检测时,在原有唇色检测理论的基础上,结合了两种方法,并提出自己的唇色检测标准,使唇色检测更加准确。
AdaBoost方法进行人脸检测是十分迅速的,本文在原有方法的基础上,增加了三种新的矩形特征,利用新的矩形特征和原矩形特征共同训练了新的分类器。之后将分类器加载到自己的程序当中,进行人脸检测。
最后在分析了肤色检测方法和AdaBoost方法的优缺点之后,本文将两种方法有机的结合起来,形成一种混合型的人脸检测方法。
实验结果表明,本文的方法有效,具有较高的检测性能。
Face detection is a very important step before the face recognition. The size and the location of the face are detected in the process. With the rapid development of science and technology, as well as people's demand for pattern recognition and computer-based interactive development, human face detection technology has also developed so quickly.
The methods of face detection in complicated condition based on the current methods have been done some research in the paper. A new illumination compensation method which be called fuzzy adaptive light compensation has proposed and the effect of the segmentation and lip detection has improved in the paper. And new rectangle features have added to train a new classifier here.
The main contributions are as followed:
Complexion is an important character of face. Avoiding the effect of the light, a new light compensation method which uses the fuzzy adaptive light compensation has proposed to enhance the quality of the image, so it is easier to do the binarization.Then segmentation has been done by Gauss model in YCbCr space. Then the image has been binarized based on the OUST and threshold adjustment. When detecting the lip, a new detection standard has proposed based on the combination of two current methods.
AdaBoost is a very popular method to do the face detection. New three rectangle features has been added and a classifier has been trained by both the old and new rectangle features. Then put the new classifier into the program and detect the human face.
At last, a new method based on the current two methods was proposed, through analyzing the advantages and disadvantages of the current methods.
The experiment proves that the method is effective and has a good performance.
本文是对复杂背景下人脸检测进行研究,在现有技术的基础上,提出了肤色模型与AdaBoost方法相结合的检测方法,肤色模型方面主要是提出了模糊自适应光照补偿方法,结合了不同方法改进了肤色分割和唇色检测的效果;之后采用增加矩形特征的AdaBoost方法训练了新分类器用于人脸检测。
本文的主要工作包括:
肤色是人脸很重要的特征,为了避免光照的影响,首先对图片进行了模糊自适应光照补偿,改进了原有的自适应补偿方法,使补偿之后的效果更易于二值化。之后基于YCbCr模型的基础上进行肤色分割,根据最大类间方差法和阈值调整法进行了肤色块的查找。为了增加肤色检测的正确度,在肤色检测的基础上增加了唇色检测,在唇色检测时,在原有唇色检测理论的基础上,结合了两种方法,并提出自己的唇色检测标准,使唇色检测更加准确。
AdaBoost方法进行人脸检测是十分迅速的,本文在原有方法的基础上,增加了三种新的矩形特征,利用新的矩形特征和原矩形特征共同训练了新的分类器。之后将分类器加载到自己的程序当中,进行人脸检测。
最后在分析了肤色检测方法和AdaBoost方法的优缺点之后,本文将两种方法有机的结合起来,形成一种混合型的人脸检测方法。
实验结果表明,本文的方法有效,具有较高的检测性能。
Face detection is a very important step before the face recognition. The size and the location of the face are detected in the process. With the rapid development of science and technology, as well as people's demand for pattern recognition and computer-based interactive development, human face detection technology has also developed so quickly.
The methods of face detection in complicated condition based on the current methods have been done some research in the paper. A new illumination compensation method which be called fuzzy adaptive light compensation has proposed and the effect of the segmentation and lip detection has improved in the paper. And new rectangle features have added to train a new classifier here.
The main contributions are as followed:
Complexion is an important character of face. Avoiding the effect of the light, a new light compensation method which uses the fuzzy adaptive light compensation has proposed to enhance the quality of the image, so it is easier to do the binarization.Then segmentation has been done by Gauss model in YCbCr space. Then the image has been binarized based on the OUST and threshold adjustment. When detecting the lip, a new detection standard has proposed based on the combination of two current methods.
AdaBoost is a very popular method to do the face detection. New three rectangle features has been added and a classifier has been trained by both the old and new rectangle features. Then put the new classifier into the program and detect the human face.
At last, a new method based on the current two methods was proposed, through analyzing the advantages and disadvantages of the current methods.
The experiment proves that the method is effective and has a good performance.
引文
[1]梁路宏,艾海舟,徐光等.人脸检测研究综述[J].计算机学报,2002,25(5):449-458.
[2]潘翔,王万森,黄远鸣.彩色静态图像的人脸检测研究[J].计算机工程与设计,2009,30(11):2785-2787
[3]Alton S F.Personal identification and description[J].Nature,1888,38(973):173-177.
[4]黄福珍,苏剑波.人脸检测[M].武汉:上海交通大学出版社,2006.
[5]杨光正.复杂景物中人面的定位[J].自动化学报,1995,4(3):499-503.
[6]CHIUNHSIUN L.Face detection in complicated backgrounds and different illumination conditions by using YCbCr color space and neural network[J].Pattern Recognition,2007,28(16):2190-2200.
[7]CHELLAPA R,WILSON C L,SIROHEY S.Human and machine recognition of faces:A survey [J].Proceedings of the IEEE,1995,83(5):705-740.
[8]HJELMAS E,LOW B K.Face detection:A survey[J].Computer Vision and Image Understanding,2001,83:236-274.
[9]S A Sirohey.Human Face Segmentation and Identification Technical Report[R].CS-TR-3176.Univ.of Maryland,1993.
[10]H P Graf,et al.Locating Faces and Facial Parts[C].Proc.1st Int' l Workshop Automatic Face and Gesture Recognition.1995:441-461.
[11]JAIN A-K,ZHONG Y.Dubuission-Jolly M-P.Deformable template models[J].A review Signal Processing.1998,71(2):109-129.
[12]A.Yuille,P.Hallinan,and D.Cohen.Feature Extraction from Faces Using Deformable Templates[J].Computer Vision,1992,2(8):99-111.
[13]赵海涛,於东军,杨健等.基于特征融合的人脸自动识别[C].第三届中国生物识别学术会议学术报告,2002.
[14]M.H.Yang,N.Ahuja.Face Detection and Gesturer Recognition for Human Computer Interaction[M].Kluwer Academic Publishers GrouP,2001.
[15]F.Samaria and S.Young.HMM based architecture for face identification[J].Image and Vision Computing,1994.1(12):537-543
[16]T.G.Dietterich.Machine learning research:Four current directions[J].AI Magazine.1997.18(4):97-136
[17]L.Breiman.Bagging Predictors[J].Machine Learning.1996.24(2):123-140
[18]Rowley,Baluja,Kanade.Neural Network-Based Face Detection[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1998,20(1):23-38.
[19]叶艳芳,黄席樾,沈志熙.一种基于肤色和模板匹配的人脸检测方法[J].重庆工学院学报,2007,21(12):102-106
[20]张洪明,赵德斌,高文.基于肤色模型、神经网络和人脸结构模型的平面旋转人脸检测[J].计算机学报,2002,25(11):1250-1256.
[21]齐永锋,张家树,火元莲.一种基于肤色与改进的LBP的人脸检测方法[J].光电子·激光,2009,12(6):816-821
[22]韩燕丽,杨慧宇,苏伟.基于分形和肤色模型的自然态人脸检测方法[J].计算机工程与设计,2009,30(1):251-254
[23]MAYBANK S,TAN T.Introduction to special section on visual surveillance [J].International Journal of Computer Vision,2000,37(2):173-173.
[24]章毓晋.图像工程[M].北京:清华大学出版社,2006
[25]孙即祥.图像分析[M].北京:科学出版社,2005
[26]JIE Y,WEIBEL.A real-time face tracker[C].Proceedings of WACV' 96,Sarasota Floreda,1996:142-147.
[27]张宏林.精通Visual C++数字图像模式识别技术及工程实践(第2版)[M]北京:人民邮电出版社,2008
[28]Joachim M.BUHMANN,Martin LADES,Frank EECKMAN.A Silicon Retina Object Recognition[R].Universidad Bonn:Technical Report No.8596-CS,1993.
[29]TSENG Y C,CHEN Y Y,PAN H K.A secure data hiding scheme for binary images[J].IEEE Transactions on Communications,2002,50(8):1227-1231.
[30]卿来云,山世光,陈熙霖,等.基于球面谐波基图像的任意光照下的人脸识别[J].计算机学报,2006,29(5):760-768
[31]梁晓辉,游志胜.自适应光照补偿[J].光电工程,2006,33(2):94-97
[32]肖明坤,王厚大.一种基于肤色分割的彩色图像人脸检测算法[J].电子工程师,2007,33(3):1-2
[33]彭波,崔永普,黄丹霞,吕小晴.基于肤色和唇色的人脸检测方法的研究[J].计算机工程与设计,2005,26(6):1500-1502.
[34]Valiant L.G.A Theory of the Learnable[J].Communications of the ACM,1984,11(127):1134-1142.
[35]Rearns M.The Computational Complexity of Machine Learning[M].Cambridge:MIT Press,1990.
[36]Kearns M.,Valiant L.G.Cryptographic Limitations on Learning Boolean Formulae and Finite Automata[J].Journal of the ACM,1994,41(1):67-95.
[37]Schapire R.E.The Strength of Weak Learnability[J].Machine Learning,1990,5(2):197-227
[38]Freund Y.Boosting a Weak Learning Algorithm by Majority[J].Information and Computation,1995,121(2):256-285
[39]Drucker H.,Schapire R.E.,Simard P.Boosting Performance in Neural Networks[C].International Journal of Pattern Recognition and Artificial Intelligence,1993,7(4):705-719
[40]Freund Y.,Schapire R.E.A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139
[41]Viola P.,Jones M.J.Robust Real-Time Face Detection[C]International Journal of Computer Vision 2004,57(2):137-154.
[42]U.S.Microprocessor Research Lab,Intel Labs Intel Corporation.Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection[R].MRL Technical Report,May 2002.
[43]Viola P.,Jones M.J.Rapid Object Detection using a Boosted Cascade of Simple Features[C].Computer Vision and Pattern Recognition,2001,1:8-14
[44]Viola P.,Jones M.J.Robust Real-time Object Detection[R].Cambridge Research Laboratory,Technical Report Series,CRL 2001/01.
[45]A.Mohan,C.Papageorgiou,T.Poggio.Example-based object detection in images by components[C].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(4):349-361.
[46]C.Papageorgiou,M.Oren,and T.Poggio.A general framework for Object Detection[C].In International Conference on Computer Vision,1998.
[47]于仕琪 刘瑞祯.OpenCV教程:基础篇[M].北京:北京航空航天大学出版社,2007
[48]陈兵旗 孙明.Visual C++实用图像处理专业教程[M].北京:清华大学出版社,2004
[49]王长军,朱善安等.基于统计模型和GVF-Snake的彩色目标检测与跟踪[J].中国图像图形学报学报,2006,11(1):13-18
[50]姚建,赵勋杰等.结合肤色模型和Adaboost算法的人脸检测[J].苏州大学学报,2009,25(3):63-67
[51]杨勇,徐春,潘伟民等.基于区域GAC模型的二值化水平集图像分割算法[J].计算机应用,2009,29(9):2414-2417
[2]潘翔,王万森,黄远鸣.彩色静态图像的人脸检测研究[J].计算机工程与设计,2009,30(11):2785-2787
[3]Alton S F.Personal identification and description[J].Nature,1888,38(973):173-177.
[4]黄福珍,苏剑波.人脸检测[M].武汉:上海交通大学出版社,2006.
[5]杨光正.复杂景物中人面的定位[J].自动化学报,1995,4(3):499-503.
[6]CHIUNHSIUN L.Face detection in complicated backgrounds and different illumination conditions by using YCbCr color space and neural network[J].Pattern Recognition,2007,28(16):2190-2200.
[7]CHELLAPA R,WILSON C L,SIROHEY S.Human and machine recognition of faces:A survey [J].Proceedings of the IEEE,1995,83(5):705-740.
[8]HJELMAS E,LOW B K.Face detection:A survey[J].Computer Vision and Image Understanding,2001,83:236-274.
[9]S A Sirohey.Human Face Segmentation and Identification Technical Report[R].CS-TR-3176.Univ.of Maryland,1993.
[10]H P Graf,et al.Locating Faces and Facial Parts[C].Proc.1st Int' l Workshop Automatic Face and Gesture Recognition.1995:441-461.
[11]JAIN A-K,ZHONG Y.Dubuission-Jolly M-P.Deformable template models[J].A review Signal Processing.1998,71(2):109-129.
[12]A.Yuille,P.Hallinan,and D.Cohen.Feature Extraction from Faces Using Deformable Templates[J].Computer Vision,1992,2(8):99-111.
[13]赵海涛,於东军,杨健等.基于特征融合的人脸自动识别[C].第三届中国生物识别学术会议学术报告,2002.
[14]M.H.Yang,N.Ahuja.Face Detection and Gesturer Recognition for Human Computer Interaction[M].Kluwer Academic Publishers GrouP,2001.
[15]F.Samaria and S.Young.HMM based architecture for face identification[J].Image and Vision Computing,1994.1(12):537-543
[16]T.G.Dietterich.Machine learning research:Four current directions[J].AI Magazine.1997.18(4):97-136
[17]L.Breiman.Bagging Predictors[J].Machine Learning.1996.24(2):123-140
[18]Rowley,Baluja,Kanade.Neural Network-Based Face Detection[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1998,20(1):23-38.
[19]叶艳芳,黄席樾,沈志熙.一种基于肤色和模板匹配的人脸检测方法[J].重庆工学院学报,2007,21(12):102-106
[20]张洪明,赵德斌,高文.基于肤色模型、神经网络和人脸结构模型的平面旋转人脸检测[J].计算机学报,2002,25(11):1250-1256.
[21]齐永锋,张家树,火元莲.一种基于肤色与改进的LBP的人脸检测方法[J].光电子·激光,2009,12(6):816-821
[22]韩燕丽,杨慧宇,苏伟.基于分形和肤色模型的自然态人脸检测方法[J].计算机工程与设计,2009,30(1):251-254
[23]MAYBANK S,TAN T.Introduction to special section on visual surveillance [J].International Journal of Computer Vision,2000,37(2):173-173.
[24]章毓晋.图像工程[M].北京:清华大学出版社,2006
[25]孙即祥.图像分析[M].北京:科学出版社,2005
[26]JIE Y,WEIBEL.A real-time face tracker[C].Proceedings of WACV' 96,Sarasota Floreda,1996:142-147.
[27]张宏林.精通Visual C++数字图像模式识别技术及工程实践(第2版)[M]北京:人民邮电出版社,2008
[28]Joachim M.BUHMANN,Martin LADES,Frank EECKMAN.A Silicon Retina Object Recognition[R].Universidad Bonn:Technical Report No.8596-CS,1993.
[29]TSENG Y C,CHEN Y Y,PAN H K.A secure data hiding scheme for binary images[J].IEEE Transactions on Communications,2002,50(8):1227-1231.
[30]卿来云,山世光,陈熙霖,等.基于球面谐波基图像的任意光照下的人脸识别[J].计算机学报,2006,29(5):760-768
[31]梁晓辉,游志胜.自适应光照补偿[J].光电工程,2006,33(2):94-97
[32]肖明坤,王厚大.一种基于肤色分割的彩色图像人脸检测算法[J].电子工程师,2007,33(3):1-2
[33]彭波,崔永普,黄丹霞,吕小晴.基于肤色和唇色的人脸检测方法的研究[J].计算机工程与设计,2005,26(6):1500-1502.
[34]Valiant L.G.A Theory of the Learnable[J].Communications of the ACM,1984,11(127):1134-1142.
[35]Rearns M.The Computational Complexity of Machine Learning[M].Cambridge:MIT Press,1990.
[36]Kearns M.,Valiant L.G.Cryptographic Limitations on Learning Boolean Formulae and Finite Automata[J].Journal of the ACM,1994,41(1):67-95.
[37]Schapire R.E.The Strength of Weak Learnability[J].Machine Learning,1990,5(2):197-227
[38]Freund Y.Boosting a Weak Learning Algorithm by Majority[J].Information and Computation,1995,121(2):256-285
[39]Drucker H.,Schapire R.E.,Simard P.Boosting Performance in Neural Networks[C].International Journal of Pattern Recognition and Artificial Intelligence,1993,7(4):705-719
[40]Freund Y.,Schapire R.E.A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139
[41]Viola P.,Jones M.J.Robust Real-Time Face Detection[C]International Journal of Computer Vision 2004,57(2):137-154.
[42]U.S.Microprocessor Research Lab,Intel Labs Intel Corporation.Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection[R].MRL Technical Report,May 2002.
[43]Viola P.,Jones M.J.Rapid Object Detection using a Boosted Cascade of Simple Features[C].Computer Vision and Pattern Recognition,2001,1:8-14
[44]Viola P.,Jones M.J.Robust Real-time Object Detection[R].Cambridge Research Laboratory,Technical Report Series,CRL 2001/01.
[45]A.Mohan,C.Papageorgiou,T.Poggio.Example-based object detection in images by components[C].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(4):349-361.
[46]C.Papageorgiou,M.Oren,and T.Poggio.A general framework for Object Detection[C].In International Conference on Computer Vision,1998.
[47]于仕琪 刘瑞祯.OpenCV教程:基础篇[M].北京:北京航空航天大学出版社,2007
[48]陈兵旗 孙明.Visual C++实用图像处理专业教程[M].北京:清华大学出版社,2004
[49]王长军,朱善安等.基于统计模型和GVF-Snake的彩色目标检测与跟踪[J].中国图像图形学报学报,2006,11(1):13-18
[50]姚建,赵勋杰等.结合肤色模型和Adaboost算法的人脸检测[J].苏州大学学报,2009,25(3):63-67
[51]杨勇,徐春,潘伟民等.基于区域GAC模型的二值化水平集图像分割算法[J].计算机应用,2009,29(9):2414-2417