基于图像分析的人脸比对技术研究
|
摘要
基于图像分析的人脸比对技术研究主要是面向ATM机环境的自动监控、报警和身份验证的问题提出来的,通过人脸异常的判断和人脸比对两个步骤实现以上的功能。
针对正面人脸特征比较多,而且容易提取,本文主要研究了如何对正面人脸进行比对研究。在研究和学习前人理论和方法的基础上,提出了一种基于加权分块区域的正面人脸比对方法。
本文的主要研究工作如下：
(1)利用Adaboost算法构建了人眼检测和嘴巴检测的分类器,并对训练过程中矩形特征的数量提出了一些优化的方法和改进的措施。通过检测人眼和嘴巴是否缺失来判断是否存在人脸异常的情况。
(2)对于前面分析留下的正常人脸图像存在的一些瑕疵,提出了一些校正的方法。并且规范化处理了所有的人脸图像,为人脸比对提供了较好的素材。
(3)提出了基于加权分块区域的正面人脸比对方法。该方法首先利用主动形状模型(ASM)的方法实现人脸特征点的自动标定。基于人脸面部的先验知识,面部几何位置特征存在稳定性。然后对特征点分成5块区域,构造人脸个性特征参数,分析各个区域的权重,在此基础上进行加权分块区域的人脸比对。最后实验论证了该方法对于正面人脸具有比较好的比对性能。
Face matching research based on image analysis issues to the ATM machine environment for automatic monitoring, alarm and authentication by two steps to achieve the above functions which are face abnormalities judgments and face matching.
As frontal face include more features, and easy to extract, this paper mainly studies how to match the frontal face. Based on researching and learning the previous theory and methods, a face matching algorithm with block based on the weighted region is presented.
What had been mainly done in this paper is as follows:
1. Adaboost algorithm have been used to build eye detection and mouth detection classifier, furthermore, some optimized methods and improved measures about the number of rectangular features in the training process are presented. We determine whether there is abnormal situation in the face image by detecting whether the absence of eye and mouth.
2. Some correction methods are presented for the remaining normal images which have some flaws. Moreover, all defective face images have been corrected, which provides good material for face matching.
3. A face matching algorithm with block based on the weighted region is presented. Firstly, facial feature points are labeled automatically by using Active Shape Models (ASM). According to facial prior knowledge, the features of the facial geometry information are stable. Then the feature points are divided into five regions, and facial personality features are constructed, and the weight of each region is analyzed, and face matching with block based on the weighted region have been carry on by these steps. At last, this method has better performance for frontal face matching demonstrated through experiments.
针对正面人脸特征比较多,而且容易提取,本文主要研究了如何对正面人脸进行比对研究。在研究和学习前人理论和方法的基础上,提出了一种基于加权分块区域的正面人脸比对方法。
本文的主要研究工作如下：
(1)利用Adaboost算法构建了人眼检测和嘴巴检测的分类器,并对训练过程中矩形特征的数量提出了一些优化的方法和改进的措施。通过检测人眼和嘴巴是否缺失来判断是否存在人脸异常的情况。
(2)对于前面分析留下的正常人脸图像存在的一些瑕疵,提出了一些校正的方法。并且规范化处理了所有的人脸图像,为人脸比对提供了较好的素材。
(3)提出了基于加权分块区域的正面人脸比对方法。该方法首先利用主动形状模型(ASM)的方法实现人脸特征点的自动标定。基于人脸面部的先验知识,面部几何位置特征存在稳定性。然后对特征点分成5块区域,构造人脸个性特征参数,分析各个区域的权重,在此基础上进行加权分块区域的人脸比对。最后实验论证了该方法对于正面人脸具有比较好的比对性能。
Face matching research based on image analysis issues to the ATM machine environment for automatic monitoring, alarm and authentication by two steps to achieve the above functions which are face abnormalities judgments and face matching.
As frontal face include more features, and easy to extract, this paper mainly studies how to match the frontal face. Based on researching and learning the previous theory and methods, a face matching algorithm with block based on the weighted region is presented.
What had been mainly done in this paper is as follows:
1. Adaboost algorithm have been used to build eye detection and mouth detection classifier, furthermore, some optimized methods and improved measures about the number of rectangular features in the training process are presented. We determine whether there is abnormal situation in the face image by detecting whether the absence of eye and mouth.
2. Some correction methods are presented for the remaining normal images which have some flaws. Moreover, all defective face images have been corrected, which provides good material for face matching.
3. A face matching algorithm with block based on the weighted region is presented. Firstly, facial feature points are labeled automatically by using Active Shape Models (ASM). According to facial prior knowledge, the features of the facial geometry information are stable. Then the feature points are divided into five regions, and facial personality features are constructed, and the weight of each region is analyzed, and face matching with block based on the weighted region have been carry on by these steps. At last, this method has better performance for frontal face matching demonstrated through experiments.
引文
[1]宋加涛.基于二值边缘图像的眼睛定位和人脸识别[D].浙江大学博士学位论文.2004
[2]孙冬梅,裘正定.生物特征识别技术综述[J].电子学报,2001,29(12)：1744-1748
[3]International Biometric Group, The Biometrics Market and Industry Report 2009-2014.
[4]A.K.Jain, A Ross, and S.Prabhakar, "An introduction to biometric recognition", IEEE Transactions on Circuits and Systems for Video Technology,14 (1), pp.4-20,2004.
[5]闰红宾.标准正面人脸识别系统的研究[D].哈尔滨工程大学学位论文.2004.
[6]高涛.基于人脸特征的身份识别[D].西北工业大学学位论文.2006.
[7]山世光.人脸识别中的若干关键问题的研究[D],中国科学院博士学位论文,2004.
[8]邵叶秦.基于序列图像的人头定位.[D].南京理工大学,2004
[9]Yang M H, Kriegman D J, Ahuja N. Detecting Faces in Images:A Survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002, (1):34-58.
[10]Valiant L G A Theory of the Learnable. Communications of the ACM,1984,27 (11) 1134-1142.
[11]孙宁等.人脸检测综述[J].电路与系统学报,2006,11(6)：101-108
[12]G Yang, T S Huang. Human Face Detection in Complex Background. Pattern Recognition [J].1994,27 (1):53-63.
[13]卢春雨,张长水,闻方等.基于区域特征的快速人脸检测法[J].清华大学学报(自然科学版),1999,39(1)：101-105
[14]章品正,赵洪玉,梁晓云等.一种复杂背景中的人脸检测与验证方法[J].数据采集与处理,2004,19：10-15
[15]T F Cootes, et al. Active shape model-their training and application [J].Computer Vision and Image Understanding,1995,61 (1):38-59.
[16]T F Cootes, G J Edwards, C J Taylor. Active appearance models.European Conference on Computer Vision[C].1998,1407 (2):484-498.
[17]唐淑芬.基于肤色与Adaboost的人脸检测算法：[D],华南理工大学,2005.
[18]M J Jones, J M Rehg. Statistical color models with application to skin detection[J]. Int'l Journal of Computer Vision archive,2002,46:81-96
[19]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)：784-792
[20]H. A. Rowley, S. Baluja, T. Kanade. Neural network-based face detection[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1998,20 (1):23-38.
[21]H. A. Rowley, S. Baluja, T. Kanade. Rotation invariant neural network-based face detection[J]. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition,1998,38-44.
[22]B. Moghaddam, A. Pentland. Probabilistic visual learning for object representation[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1997,19(7):696-710.
[23]M. Turk, A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience[J],1991,3 (1):71-86.
[24]E. Osuna, R. Freund, F. Girosi. Training support vector machines:an application to face detection[J]. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition,1997,6:130-136.
[25]V. N. Vapnik. An overview of statistical learning theory[J]. IEEE Transaction on Neural Networks,1999,10 (5):988-999.
[26]J. C. Platt. Sequential minimal optimization:a fast algorithm for training support vector machines[J]. Technical Report MSR-TR-98-14, Microsoft Research,1998.
[27]Robert E Schapire. The strength of weak learnability[J]. Machine Learning,1990,5(2): 197-227
[28]Yoav Freund, Robert E Schapire. Detection using a Boosted cascade of simple feature[C]. In:Proc IEEE Conference on Computer Vision and Pattern Recognition, 2001:511-518
[29]Li S Z, Zhu L, Zhang Z Q, Zhang H J. Learning to detect multi-view faces in real-time[C]. In:Proceeding of the 2nd International Conference on Development and learning,2002:172-177
[30]Lienhart R, Kuranov A, V PIsarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection[C]. DAGM'03,25th Pattern Recognition Symposium,2003.
[31]Lienhart R, Kuranov A. A detector tree of boosted classifier for real time object detection and tracking[C]. IEEE International Conference on Multimedia & Expo,2003: 277-280
[32]Liu C, Shum H Y. Kullback-Leibler Boosting[C]. Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'03),1,2003:1587-1594
[33]Jianxin Wu, James M Rehg, Matthew D. Mullin. Learning a Rare Event Detection Cascade by Direct Feature Selection[C]. SCTV2003 & ICCV2003
[34]Jianxin Wu, Matthew D Mullin, James M Rehg. Linear Asymmetric Classifier for Cascade Detectors[C]. ICML 2005:993-1000
[35]X. W Hou, C. L Liu, T. Tan. Learning boosted asymmetric classifiers for object detection[J]. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition,2006,330-338.
[36]Q. J Li, Y. B Mao, Z. Q Wang, et al. Cost-sensitive boosting:fitting an additive asymmetric logistic regression model. In Proceeding of the 1st Asian Conference on Machine Learning[J]:Advances in Machine Learning.2009,234-247.
[37]P.Viola, M.Jones. Robust Real-Time Face Detection. International Journal of Computer Vision[J].2004,57 (2):137-154.
[38]P.Viola, M.Jones. Rapid Object Detection using a Boosted Cascade of Simple Features[J]. In proceedings IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, USA,2001:511-518.
[39]P.Viola, M.Jones. Robust Real-time Object Detection. Cambridge Research Laboratory [J], Technical Report Series. CRL 2001/01.
[40]Rowley, Baluja S, Kanade T. Neural transactions on Pattern Analysis and Machine network-based face detection[J]. IEEE Intelligence,1998,20 (1):23-38
[41]黄金凤.人脸检测系统的设计与实现[D].华侨大学硕士学位论文,2007：20-22
[42]袁凤刚,刘建成.不同插值方法实现数字图像旋转研究[J].软件导刊,2010,9(4)
[43]唐娅琴.几种图像平滑去噪方法的比较[J].西南大学学报,2009,11,11(31)
[44]T.F. Cootes, C.J. Taylor et al. Active Shape Models-Their Training and Application[J].Computer Vision and Image Understanding,1995,61 (1):38-59
[45]Hu J, Yan H, Sakalli M. Locating head and face boundaries for headshoulder images[J]. Pattern Recognition,1999,32:1317-1333
[46]Tang X S, Ou Z Y, Su T M. Robust Precise Eye Location by Adaboost and SVM Techniques [C].In:Wang J, Liao X F, Yi Zh,eds. Advances in Neural Networks-ISNN 2005. Berlin:Springer-Verlag,2005,3497:93-98.
[47]张春美.特征点提取及其在图像匹配中的应用研究[D].解放军信息工程大学,2008
[48]王燕群,童卫青,张昌明.基于边缘统计和特征定位的人脸姿态估计方法[J].计算机系统应用,2011,20(4)
[49]陈平.应用数理统计[M].北京：机械工业出版社.2008
[50]http://www.milbo.users.sonic.net/stasm/index.html
[2]孙冬梅,裘正定.生物特征识别技术综述[J].电子学报,2001,29(12)：1744-1748
[3]International Biometric Group, The Biometrics Market and Industry Report 2009-2014.
[4]A.K.Jain, A Ross, and S.Prabhakar, "An introduction to biometric recognition", IEEE Transactions on Circuits and Systems for Video Technology,14 (1), pp.4-20,2004.
[5]闰红宾.标准正面人脸识别系统的研究[D].哈尔滨工程大学学位论文.2004.
[6]高涛.基于人脸特征的身份识别[D].西北工业大学学位论文.2006.
[7]山世光.人脸识别中的若干关键问题的研究[D],中国科学院博士学位论文,2004.
[8]邵叶秦.基于序列图像的人头定位.[D].南京理工大学,2004
[9]Yang M H, Kriegman D J, Ahuja N. Detecting Faces in Images:A Survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002, (1):34-58.
[10]Valiant L G A Theory of the Learnable. Communications of the ACM,1984,27 (11) 1134-1142.
[11]孙宁等.人脸检测综述[J].电路与系统学报,2006,11(6)：101-108
[12]G Yang, T S Huang. Human Face Detection in Complex Background. Pattern Recognition [J].1994,27 (1):53-63.
[13]卢春雨,张长水,闻方等.基于区域特征的快速人脸检测法[J].清华大学学报(自然科学版),1999,39(1)：101-105
[14]章品正,赵洪玉,梁晓云等.一种复杂背景中的人脸检测与验证方法[J].数据采集与处理,2004,19：10-15
[15]T F Cootes, et al. Active shape model-their training and application [J].Computer Vision and Image Understanding,1995,61 (1):38-59.
[16]T F Cootes, G J Edwards, C J Taylor. Active appearance models.European Conference on Computer Vision[C].1998,1407 (2):484-498.
[17]唐淑芬.基于肤色与Adaboost的人脸检测算法：[D],华南理工大学,2005.
[18]M J Jones, J M Rehg. Statistical color models with application to skin detection[J]. Int'l Journal of Computer Vision archive,2002,46:81-96
[19]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)：784-792
[20]H. A. Rowley, S. Baluja, T. Kanade. Neural network-based face detection[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1998,20 (1):23-38.
[21]H. A. Rowley, S. Baluja, T. Kanade. Rotation invariant neural network-based face detection[J]. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition,1998,38-44.
[22]B. Moghaddam, A. Pentland. Probabilistic visual learning for object representation[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1997,19(7):696-710.
[23]M. Turk, A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience[J],1991,3 (1):71-86.
[24]E. Osuna, R. Freund, F. Girosi. Training support vector machines:an application to face detection[J]. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition,1997,6:130-136.
[25]V. N. Vapnik. An overview of statistical learning theory[J]. IEEE Transaction on Neural Networks,1999,10 (5):988-999.
[26]J. C. Platt. Sequential minimal optimization:a fast algorithm for training support vector machines[J]. Technical Report MSR-TR-98-14, Microsoft Research,1998.
[27]Robert E Schapire. The strength of weak learnability[J]. Machine Learning,1990,5(2): 197-227
[28]Yoav Freund, Robert E Schapire. Detection using a Boosted cascade of simple feature[C]. In:Proc IEEE Conference on Computer Vision and Pattern Recognition, 2001:511-518
[29]Li S Z, Zhu L, Zhang Z Q, Zhang H J. Learning to detect multi-view faces in real-time[C]. In:Proceeding of the 2nd International Conference on Development and learning,2002:172-177
[30]Lienhart R, Kuranov A, V PIsarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection[C]. DAGM'03,25th Pattern Recognition Symposium,2003.
[31]Lienhart R, Kuranov A. A detector tree of boosted classifier for real time object detection and tracking[C]. IEEE International Conference on Multimedia & Expo,2003: 277-280
[32]Liu C, Shum H Y. Kullback-Leibler Boosting[C]. Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'03),1,2003:1587-1594
[33]Jianxin Wu, James M Rehg, Matthew D. Mullin. Learning a Rare Event Detection Cascade by Direct Feature Selection[C]. SCTV2003 & ICCV2003
[34]Jianxin Wu, Matthew D Mullin, James M Rehg. Linear Asymmetric Classifier for Cascade Detectors[C]. ICML 2005:993-1000
[35]X. W Hou, C. L Liu, T. Tan. Learning boosted asymmetric classifiers for object detection[J]. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition,2006,330-338.
[36]Q. J Li, Y. B Mao, Z. Q Wang, et al. Cost-sensitive boosting:fitting an additive asymmetric logistic regression model. In Proceeding of the 1st Asian Conference on Machine Learning[J]:Advances in Machine Learning.2009,234-247.
[37]P.Viola, M.Jones. Robust Real-Time Face Detection. International Journal of Computer Vision[J].2004,57 (2):137-154.
[38]P.Viola, M.Jones. Rapid Object Detection using a Boosted Cascade of Simple Features[J]. In proceedings IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, USA,2001:511-518.
[39]P.Viola, M.Jones. Robust Real-time Object Detection. Cambridge Research Laboratory [J], Technical Report Series. CRL 2001/01.
[40]Rowley, Baluja S, Kanade T. Neural transactions on Pattern Analysis and Machine network-based face detection[J]. IEEE Intelligence,1998,20 (1):23-38
[41]黄金凤.人脸检测系统的设计与实现[D].华侨大学硕士学位论文,2007：20-22
[42]袁凤刚,刘建成.不同插值方法实现数字图像旋转研究[J].软件导刊,2010,9(4)
[43]唐娅琴.几种图像平滑去噪方法的比较[J].西南大学学报,2009,11,11(31)
[44]T.F. Cootes, C.J. Taylor et al. Active Shape Models-Their Training and Application[J].Computer Vision and Image Understanding,1995,61 (1):38-59
[45]Hu J, Yan H, Sakalli M. Locating head and face boundaries for headshoulder images[J]. Pattern Recognition,1999,32:1317-1333
[46]Tang X S, Ou Z Y, Su T M. Robust Precise Eye Location by Adaboost and SVM Techniques [C].In:Wang J, Liao X F, Yi Zh,eds. Advances in Neural Networks-ISNN 2005. Berlin:Springer-Verlag,2005,3497:93-98.
[47]张春美.特征点提取及其在图像匹配中的应用研究[D].解放军信息工程大学,2008
[48]王燕群,童卫青,张昌明.基于边缘统计和特征定位的人脸姿态估计方法[J].计算机系统应用,2011,20(4)
[49]陈平.应用数理统计[M].北京：机械工业出版社.2008
[50]http://www.milbo.users.sonic.net/stasm/index.html