不良图像检测系统的设计与实现
|
摘要
伴随着信息时代的发展,网络已经成为人们最重要、最便捷的信息传播工具。而在网络带给我们巨大便利的同时,各种不良的信息也随之传播扩散,暴力、色情等不健康信息充斥在网络各个地方。据统计,互联网中色情网站数量要有50多万个,而深受其影响的网民,尤其青少年网民更是数之不尽。所以如何有效的阻止色情信息的传播一直是互联网健康发展的重要课题。因此,本文设计实现一种基于肤色的不良图像检测系统,用来检验图像是否为不良图像。
图像中大面积的裸露皮肤是判定该图像是否为色情图像的最重要的一个特征标志,肤色检测是色情图像判定的基础,所以本文主要对肤色检测技术进行研究,并实现一种在YCbCr空间的结合贝叶斯分类准则和阈值分割等技术的肤色提取方法。为了精确肤色提取结果,在此方法上再引入纹理分析等技术,进一步保证肤色提取的准确率。但是单纯的依靠对肤色的判定作为色情图像检测的唯一标准,不能保证色情图像检测的准确率。例如对穿着性感的明星写真或是头像证件照等图像的判定上,由于这类图片也存在大量的裸露皮肤,判定会有很大的误检率。所以,本文又对色情图像进一步分析,实验研究对女性胸部以及私处的判定方式。最终整合肤色提取、人脸检测、人体敏感部位检测等信息,设计实现不良图像检测系统。
本文的主要研究工作和取得的成果如下：
(1)实现在YCbCr空间的基于贝叶斯的肤色分类模型,并改进模型,设计实现一种结合Cr分量阈值分割和YCbCr空间贝叶斯分类的肤色提取算法。
(2)对肤色检测采用纹理分析、形态学变换等方式优化肤色检测结果。
(3)实验实现了现有根据色彩分析以及图形几何特征的胸部检测方法。
(4)实验设计实现基于adaboost的胸部检测与色彩分析结合的女性胸部检测模型。
(5)综合肤色检测、人脸检测以及敏感部位检测等技术,依据决策树的思想整合设计实现色情图像检测系统。
With the development of the information, network has become one of the most important and the most convenient tool for the dissemination of information. The Internet brings us great convenience at the same time, all kinds of bad information also subsequently and diffusion. Violence, pornography and other unhealthy information filled in anywhere on the web. According to statistics, the number of Internet pornography sites must have about 500000, and the influenced Internet users, especially teenage netizen is uncountable. So how to effectively prevent the pornographic information transmission has always been an important topic for the development of the Internet health. Based on this, this paper presents the design and Implementation Based on skin color image defect detection system, used to judge whether the image is a bad image.
The image with a large bare skin area is a most important feature to determine whether the graphics for the erotic images. Skin detection is the foundation of the judgement of pornographic images, so this paper is mainly on skin detection technology research, we realized a skin detect method in YCbCr space with the Bayesian classification criteria and threshold segmentation technology. In order to accurately extraction results, this method is then introduced to texture analysis techniques, to further ensure that the color extraction accuracy. But simply rely on color judgment as pornographic image detection only standard, it cann't guarantee of pornographic image determining accuracy. As sexy star portrait, in these images there are lots of skin area too, the judges may have great error rate. So this paper on the erotic images for further analysis, experimental research on women's breasts and genitals estimation. Finally the integration of skin extraction, face detection, character information such as the sensitive parts of detection, design and achieve a bad image detection system.
The main research work and achievements are as follows:
(1) In YCbCr color space, implemente a skin classification model which based on Bayesian.And we improved this model, design and implementation of a combination of Cr component threshold segmentation and YCbCr space skin color extraction algorithm of Bayesian classification.
(2) On the basis of the above results by using texture analysis, morphological transformation and optimization of skin color detection results, and achieve better effect for skin color detection.
(3) Experiments and achieve the chest examination method according to the analysis of image color and the pattern geometry. (4) Experiments design the female chest detection model based on AdaBoost chest examination and color analysis combined.
(5) Combined with skin color detection, face detection and sensitive detection technique, based on the decision tree thought integration design of pornographic image detection system.
图像中大面积的裸露皮肤是判定该图像是否为色情图像的最重要的一个特征标志,肤色检测是色情图像判定的基础,所以本文主要对肤色检测技术进行研究,并实现一种在YCbCr空间的结合贝叶斯分类准则和阈值分割等技术的肤色提取方法。为了精确肤色提取结果,在此方法上再引入纹理分析等技术,进一步保证肤色提取的准确率。但是单纯的依靠对肤色的判定作为色情图像检测的唯一标准,不能保证色情图像检测的准确率。例如对穿着性感的明星写真或是头像证件照等图像的判定上,由于这类图片也存在大量的裸露皮肤,判定会有很大的误检率。所以,本文又对色情图像进一步分析,实验研究对女性胸部以及私处的判定方式。最终整合肤色提取、人脸检测、人体敏感部位检测等信息,设计实现不良图像检测系统。
本文的主要研究工作和取得的成果如下：
(1)实现在YCbCr空间的基于贝叶斯的肤色分类模型,并改进模型,设计实现一种结合Cr分量阈值分割和YCbCr空间贝叶斯分类的肤色提取算法。
(2)对肤色检测采用纹理分析、形态学变换等方式优化肤色检测结果。
(3)实验实现了现有根据色彩分析以及图形几何特征的胸部检测方法。
(4)实验设计实现基于adaboost的胸部检测与色彩分析结合的女性胸部检测模型。
(5)综合肤色检测、人脸检测以及敏感部位检测等技术,依据决策树的思想整合设计实现色情图像检测系统。
With the development of the information, network has become one of the most important and the most convenient tool for the dissemination of information. The Internet brings us great convenience at the same time, all kinds of bad information also subsequently and diffusion. Violence, pornography and other unhealthy information filled in anywhere on the web. According to statistics, the number of Internet pornography sites must have about 500000, and the influenced Internet users, especially teenage netizen is uncountable. So how to effectively prevent the pornographic information transmission has always been an important topic for the development of the Internet health. Based on this, this paper presents the design and Implementation Based on skin color image defect detection system, used to judge whether the image is a bad image.
The image with a large bare skin area is a most important feature to determine whether the graphics for the erotic images. Skin detection is the foundation of the judgement of pornographic images, so this paper is mainly on skin detection technology research, we realized a skin detect method in YCbCr space with the Bayesian classification criteria and threshold segmentation technology. In order to accurately extraction results, this method is then introduced to texture analysis techniques, to further ensure that the color extraction accuracy. But simply rely on color judgment as pornographic image detection only standard, it cann't guarantee of pornographic image determining accuracy. As sexy star portrait, in these images there are lots of skin area too, the judges may have great error rate. So this paper on the erotic images for further analysis, experimental research on women's breasts and genitals estimation. Finally the integration of skin extraction, face detection, character information such as the sensitive parts of detection, design and achieve a bad image detection system.
The main research work and achievements are as follows:
(1) In YCbCr color space, implemente a skin classification model which based on Bayesian.And we improved this model, design and implementation of a combination of Cr component threshold segmentation and YCbCr space skin color extraction algorithm of Bayesian classification.
(2) On the basis of the above results by using texture analysis, morphological transformation and optimization of skin color detection results, and achieve better effect for skin color detection.
(3) Experiments and achieve the chest examination method according to the analysis of image color and the pattern geometry. (4) Experiments design the female chest detection model based on AdaBoost chest examination and color analysis combined.
(5) Combined with skin color detection, face detection and sensitive detection technique, based on the decision tree thought integration design of pornographic image detection system.
引文
[1]《第23次中国互联网络发展状况统计报告》[EB/OL]. http://www.ala.org/cipa/Law.Pdf, 2009-1-13.
[2]The Children's Internet Protection Act[EB/OL].http://www.ala.org/cipa/LawPdf, 2003-6-23.
[3]Joshua Keating. The List:Look Who's Censoring the Internet Now [EB/OL].http://www.foreignpolicy.com/,2009-3-24.
[4]《中华人民共和国未成年人保护法(修订)》[EB/OL].http://www.legalinfo.gov.cn/misc/2007-05/content_621277.html
[5]platom for Internet Content Selection[EB/OL].http://www.w3.org/PICS/
[6]太平洋科技新闻组,Inuki."网络色情业竟是IT业火车头"[EB/OL]. http://www.line.com.cn/news/hy/0403/332785.html.,2004.3.
[7]中国互联网络信息中心.“第十五次中国互联网络发展状况统计报告"[EB/OL]. http://www.cnnic.net.cn/,2004.3.
[8]北京展翅鸟科技公司,网络爸爸www.tueagles.com/baba. http://www.tueagles.com/baba/softnews/1020.htm,2003.10.
[9]美萍电脑软件工作室,美萍反黄专家. http://www.mpsoft.net/shield.html,2005.3.
[10]飞涛软件工作室,护花使者URLhttp://www.18ie.com/,2005.3.
[11]D.A.Forsyth,M.Fleck,C.Bregler.Finding naked people[C].In Proc.Fourth European Conference on Computer Vision,1996:593-602.
[12]D.A.Forsyth.Identifying nude pictures[J].IEEE,1996:103-108
[13]Michael J.Jones and James M.Rehg.Statistical Color Model with Application to Skin Detection[J].Cambridge Research laboratory Technical Report Series,CRL 1998/11:274-280
[14]Hamdy A.,Elmahdy M, Elsabrouty M. A new colour space for skin tone detection [J].IEEE,2009:497-500
[15]段立娟,崔国勤,高文,张洪明.多层次特定类型图像过滤方法[J].计算机辅助设计与图形学学报,2002/14：404-409.
[16]许强,赵宏,江早.一种新颖的智能网络图像内容监测系统模型[J].软件学报；2002/03：424-432
[17]孙庆杰,吴恩华.基于矩形拟合的人体检测[J].软件学报.,2003,14(8)：1388-1393.
[18]Albiol A., Torres L.,Delp E. J.. An unsupervised color image segmentation algorithm for face detection applications[C]. In Proceedings of the 2001 international conference on image processing,2001:681-684.
[19]J.Ruiz-del-Solar et al.Skin Detection using Neighborhood Information[C].6th Int.Conf.on Face and Gesture Recognition-FGR 2004:463-468.
[20]CCIR, "Encoding parameters of digital television for studios", CCIRRecommendation 601-2, Int. Radio Consult. Committee, Geneva, Switzerland,1990..
[21]Freund,Y.and Schapire,R.E..A decision theoreticgeneralization of on-line learning and an application toboosting[J] Journal of Computer and System Science,55(1):1997:119-139.
[22]MihranTuceryan,Anil KJain.TexuterAnalysis[C].TheHandbookofPattemRecongition andComputerVision(2nd Edition)WorldScientific PublishingCo.,1998:207-248
[23]R.Schapire,Y.Freund,P.Bartlett,W.Lee.Boosting the margin:a new explanation for the effectiveness of votingmethods[C].In Proc.14th International Conference on Machinelearning,1977:322-330. Morgan Kaufmann.
[24]R. Lienhart,J. Maydt, An Extended Set of Haar-Like Features for Rapid Object Detection[J]. Proc. IEEE Int"l Conf. Image Processing,vol.1,2002:900-903.
[25]Morgan Kaufmann,Intel Cooperation.OpenCV参考手册[M],2001：全部.
[26]Qing Fang Zheng,Ming Ji Zhang,Wei Qiang Wang.A HybridApproach to Dectect Adult Web Images [C].5th Pacific RimConference on Tokyo,Japan,2004.
[27]吴相豪,申铉京.基于像素的三种肤色检测模型的比较与研究[J].计算机应用研究,2003.09精扩本：430-432.
[28]杨金锋,傅周宇,谭铁牛,胡卫明.一种新型的基于内容的图像识别与过滤方法[J].通信学报,2004-7,25(7)：93-104.
[29]胡冠宇.基于肤色之裸体影像侦测之研究[D].台湾国立成功大学,硕士论文,2004：全部.
[30]Rainer Lienhart, Jochen Maydt.An Extended Set of Haar-IikeFeatures for Rapid Object Detection[J].IEEE ICIP 2002,Vol.1:900-903.
[31]J.P.Marques de Sa著,吴逸飞译.《模式识别——原理、方法及应用》[M]，清华大学出版社,北京，,2002：12-18.
[32][美] Scott Roberts.Microsoft Internet Explorer5.程序设计[M].北京：清华大学出版社.2001/2第1版：245-290,429-442.
[33]凌旭峰,杨杰,叶晨洲.彩色序列图像的人脸检测和识别系统[J].电子学报，2003.31(4)：544-547.
[34]阮彤,冯东雷,李京；基于贝叶斯网络的信息过滤模型研究[J]；计算机研究与发展；2002年12期
[35]Douglas Chai,Abdesselam Bouzerdoum.A Bayesian Approachto Skin Color Classificat-ion in YCbCr Color Space.[C]IEEE.2000:421-424
[36]S.L. Phung, A. Bouzerdoum, D. Chai, A novel skin color model in YCBCR color space and its application to human face detection. [C] Proceedings of IEEE International Conference on Image Processing, vol. Ⅰ 2002:289-292.
[37]J Yang,W Lu,A Waibel.Skin-color modeling and adaptation[C].In:Proc ACCV,1998:687-694.
[38]P. Viola, M. J. Jones, and D. Snow. Detecting pedestrians using patterns of motion and appearance.[C] The 9th ICCV, Nice, France, volume 1,2003:734-741.
[39]孙巍巍.基于人脸与指纹的多模态身份识别系统研究[D].南京理工大学.2011.10：全部
[40]范晓,申铉京.基于IE浏览器的色情图片过滤器[J].吉林大学学报(信息版),2004,22(6)：631-637.
[41]冯军红,刘桂林,高立新等.基于小样本训练集的肤色模型建立方法[J/OL].CNKI(http://cnki.jlu.edu.cn/cjfd/mainframe.asp?encode=&display=&navigate=),Augu st.2003.
[42]汪涛等.基于平均值退火的二值纹理恢复[J].计算机学报.1994,17(8)：618-623.
[43]李欣亮,廖孟扬等.利用自适应算法的快速估计参数进行图像纹理分割[J].电子学报,1995年第1期：105-108.
[44]徐琼.基于小波变换的纹理边缘检测方法[J].重庆交通学报,1999,18(2)：149-152.
[45]R.M.Haralick,K.Shanmugam and I.Dinstein.Textural FeaturesFor Image Classification[J].IEEE Trans.Syst.,Man,Cybern. vol SMC-3,1973:610-621.
[46]M.R.Turner.Texture Discrimination by Gabor Functions.Biol.Cybern.l986,vol 55:71-82.
[47]吴相豪.基于肤色检测的敏感图像过滤器的研究与实现.[D]硕士论文.2003.2：19-22.
[48]R.M.Haralike.StatisticalStructural Approaches toTexture.[J]Proc.of IEEE. vol.67,No.5,1979:45-69.
[49]Duda,R.O.模式分类[M].北京：机械工业出版社,2003年9月第1版：1-15.
[50]尹显东,唐丹,邓君等.基于内容的特定图像过滤方法[J].计算机测量与控制,2004,12(3)：283-286.
[51]谭伟恒.基于人体特征的肤色检测算法在敏感图像过滤中的应用.[D]吉林大学,硕士论文.2006.6：1-24,38-46.
[52]杨金锋.基于内容敏感图像过滤关键技术研究及应用.[D]吉林大学,硕士论文.2006.6：45-55,63-66.
[53]R. C. Gonzalez and R. E. Woods.数字图像处理(第二版)[M].北京：电子工业出版社,2008.
[54]Quinlan J.R.,Discovering rules from large collections of examples:A case study,In:Michie,D.editor,Expert Systems in the Microelectronic Age,Edinburgh Uni versityPress,Scotland,(1979).
[55]高秀娟.图像分割的理论、方法及应用[D].长春：吉林大学,2006
[56]Dalal N, Triggs B. Histograms of Oriented Gradients for HumanDetection[C]//Proc. Of International Conference on Computer Vision and Pattern Recognition. San Diego, USA:[s. n.],2005:886-893.
[57]L.Breiman,J.H.Friedman,R.A.Olshen,etl.Classification and Regression Trees [M].New York:Wadsworth International Group,1984
[58]Quinlan.J.R.Induction of decision trees [J].Machine Learning,1986,1 (1):81-106
[59]Quinlan J.R.C4.5:Programs for machine learning [M].San Mateo,California:Morgan Kaufmann publishers,1993
[2]The Children's Internet Protection Act[EB/OL].http://www.ala.org/cipa/LawPdf, 2003-6-23.
[3]Joshua Keating. The List:Look Who's Censoring the Internet Now [EB/OL].http://www.foreignpolicy.com/,2009-3-24.
[4]《中华人民共和国未成年人保护法(修订)》[EB/OL].http://www.legalinfo.gov.cn/misc/2007-05/content_621277.html
[5]platom for Internet Content Selection[EB/OL].http://www.w3.org/PICS/
[6]太平洋科技新闻组,Inuki."网络色情业竟是IT业火车头"[EB/OL]. http://www.line.com.cn/news/hy/0403/332785.html.,2004.3.
[7]中国互联网络信息中心.“第十五次中国互联网络发展状况统计报告"[EB/OL]. http://www.cnnic.net.cn/,2004.3.
[8]北京展翅鸟科技公司,网络爸爸www.tueagles.com/baba. http://www.tueagles.com/baba/softnews/1020.htm,2003.10.
[9]美萍电脑软件工作室,美萍反黄专家. http://www.mpsoft.net/shield.html,2005.3.
[10]飞涛软件工作室,护花使者URLhttp://www.18ie.com/,2005.3.
[11]D.A.Forsyth,M.Fleck,C.Bregler.Finding naked people[C].In Proc.Fourth European Conference on Computer Vision,1996:593-602.
[12]D.A.Forsyth.Identifying nude pictures[J].IEEE,1996:103-108
[13]Michael J.Jones and James M.Rehg.Statistical Color Model with Application to Skin Detection[J].Cambridge Research laboratory Technical Report Series,CRL 1998/11:274-280
[14]Hamdy A.,Elmahdy M, Elsabrouty M. A new colour space for skin tone detection [J].IEEE,2009:497-500
[15]段立娟,崔国勤,高文,张洪明.多层次特定类型图像过滤方法[J].计算机辅助设计与图形学学报,2002/14：404-409.
[16]许强,赵宏,江早.一种新颖的智能网络图像内容监测系统模型[J].软件学报；2002/03：424-432
[17]孙庆杰,吴恩华.基于矩形拟合的人体检测[J].软件学报.,2003,14(8)：1388-1393.
[18]Albiol A., Torres L.,Delp E. J.. An unsupervised color image segmentation algorithm for face detection applications[C]. In Proceedings of the 2001 international conference on image processing,2001:681-684.
[19]J.Ruiz-del-Solar et al.Skin Detection using Neighborhood Information[C].6th Int.Conf.on Face and Gesture Recognition-FGR 2004:463-468.
[20]CCIR, "Encoding parameters of digital television for studios", CCIRRecommendation 601-2, Int. Radio Consult. Committee, Geneva, Switzerland,1990..
[21]Freund,Y.and Schapire,R.E..A decision theoreticgeneralization of on-line learning and an application toboosting[J] Journal of Computer and System Science,55(1):1997:119-139.
[22]MihranTuceryan,Anil KJain.TexuterAnalysis[C].TheHandbookofPattemRecongition andComputerVision(2nd Edition)WorldScientific PublishingCo.,1998:207-248
[23]R.Schapire,Y.Freund,P.Bartlett,W.Lee.Boosting the margin:a new explanation for the effectiveness of votingmethods[C].In Proc.14th International Conference on Machinelearning,1977:322-330. Morgan Kaufmann.
[24]R. Lienhart,J. Maydt, An Extended Set of Haar-Like Features for Rapid Object Detection[J]. Proc. IEEE Int"l Conf. Image Processing,vol.1,2002:900-903.
[25]Morgan Kaufmann,Intel Cooperation.OpenCV参考手册[M],2001：全部.
[26]Qing Fang Zheng,Ming Ji Zhang,Wei Qiang Wang.A HybridApproach to Dectect Adult Web Images [C].5th Pacific RimConference on Tokyo,Japan,2004.
[27]吴相豪,申铉京.基于像素的三种肤色检测模型的比较与研究[J].计算机应用研究,2003.09精扩本：430-432.
[28]杨金锋,傅周宇,谭铁牛,胡卫明.一种新型的基于内容的图像识别与过滤方法[J].通信学报,2004-7,25(7)：93-104.
[29]胡冠宇.基于肤色之裸体影像侦测之研究[D].台湾国立成功大学,硕士论文,2004：全部.
[30]Rainer Lienhart, Jochen Maydt.An Extended Set of Haar-IikeFeatures for Rapid Object Detection[J].IEEE ICIP 2002,Vol.1:900-903.
[31]J.P.Marques de Sa著,吴逸飞译.《模式识别——原理、方法及应用》[M]，清华大学出版社,北京，,2002：12-18.
[32][美] Scott Roberts.Microsoft Internet Explorer5.程序设计[M].北京：清华大学出版社.2001/2第1版：245-290,429-442.
[33]凌旭峰,杨杰,叶晨洲.彩色序列图像的人脸检测和识别系统[J].电子学报，2003.31(4)：544-547.
[34]阮彤,冯东雷,李京；基于贝叶斯网络的信息过滤模型研究[J]；计算机研究与发展；2002年12期
[35]Douglas Chai,Abdesselam Bouzerdoum.A Bayesian Approachto Skin Color Classificat-ion in YCbCr Color Space.[C]IEEE.2000:421-424
[36]S.L. Phung, A. Bouzerdoum, D. Chai, A novel skin color model in YCBCR color space and its application to human face detection. [C] Proceedings of IEEE International Conference on Image Processing, vol. Ⅰ 2002:289-292.
[37]J Yang,W Lu,A Waibel.Skin-color modeling and adaptation[C].In:Proc ACCV,1998:687-694.
[38]P. Viola, M. J. Jones, and D. Snow. Detecting pedestrians using patterns of motion and appearance.[C] The 9th ICCV, Nice, France, volume 1,2003:734-741.
[39]孙巍巍.基于人脸与指纹的多模态身份识别系统研究[D].南京理工大学.2011.10：全部
[40]范晓,申铉京.基于IE浏览器的色情图片过滤器[J].吉林大学学报(信息版),2004,22(6)：631-637.
[41]冯军红,刘桂林,高立新等.基于小样本训练集的肤色模型建立方法[J/OL].CNKI(http://cnki.jlu.edu.cn/cjfd/mainframe.asp?encode=&display=&navigate=),Augu st.2003.
[42]汪涛等.基于平均值退火的二值纹理恢复[J].计算机学报.1994,17(8)：618-623.
[43]李欣亮,廖孟扬等.利用自适应算法的快速估计参数进行图像纹理分割[J].电子学报,1995年第1期：105-108.
[44]徐琼.基于小波变换的纹理边缘检测方法[J].重庆交通学报,1999,18(2)：149-152.
[45]R.M.Haralick,K.Shanmugam and I.Dinstein.Textural FeaturesFor Image Classification[J].IEEE Trans.Syst.,Man,Cybern. vol SMC-3,1973:610-621.
[46]M.R.Turner.Texture Discrimination by Gabor Functions.Biol.Cybern.l986,vol 55:71-82.
[47]吴相豪.基于肤色检测的敏感图像过滤器的研究与实现.[D]硕士论文.2003.2：19-22.
[48]R.M.Haralike.StatisticalStructural Approaches toTexture.[J]Proc.of IEEE. vol.67,No.5,1979:45-69.
[49]Duda,R.O.模式分类[M].北京：机械工业出版社,2003年9月第1版：1-15.
[50]尹显东,唐丹,邓君等.基于内容的特定图像过滤方法[J].计算机测量与控制,2004,12(3)：283-286.
[51]谭伟恒.基于人体特征的肤色检测算法在敏感图像过滤中的应用.[D]吉林大学,硕士论文.2006.6：1-24,38-46.
[52]杨金锋.基于内容敏感图像过滤关键技术研究及应用.[D]吉林大学,硕士论文.2006.6：45-55,63-66.
[53]R. C. Gonzalez and R. E. Woods.数字图像处理(第二版)[M].北京：电子工业出版社,2008.
[54]Quinlan J.R.,Discovering rules from large collections of examples:A case study,In:Michie,D.editor,Expert Systems in the Microelectronic Age,Edinburgh Uni versityPress,Scotland,(1979).
[55]高秀娟.图像分割的理论、方法及应用[D].长春：吉林大学,2006
[56]Dalal N, Triggs B. Histograms of Oriented Gradients for HumanDetection[C]//Proc. Of International Conference on Computer Vision and Pattern Recognition. San Diego, USA:[s. n.],2005:886-893.
[57]L.Breiman,J.H.Friedman,R.A.Olshen,etl.Classification and Regression Trees [M].New York:Wadsworth International Group,1984
[58]Quinlan.J.R.Induction of decision trees [J].Machine Learning,1986,1 (1):81-106
[59]Quinlan J.R.C4.5:Programs for machine learning [M].San Mateo,California:Morgan Kaufmann publishers,1993