基于特定内容的敏感图像过滤技术的研究
|
摘要
科技的不断进步使网络也随之快速的发展,互联网就像一把双刃剑,人们还在欣喜于网络的强大时许多道德败坏的人也趁机窜了进来,他们上传许多淫秽、色情的图片,严重污染了网络空间。很多研究人员采用封锁黄色网站、对带有敏感字样的文本信息进行过滤等方法来控制色情信息在网络上的传播,但是这些对色情图像的控制都不是很有效,因此基于内容的敏感图像过滤技术应运而生。本文研究基于特定内容的敏感图像过滤技术,研究内容如下。
敏感图像的过滤模块主要有肤色检测模块、纹理检测模块、特征提取模块和分类器模块。在肤色检测模块中,通过实验比较本文提出了色度空间模型和统计直方图模型相结合的方法来进行肤色检测,实验结果表明与传统的色度空间模型、高斯混合模型、统计直方图模型相比检测速度提高到2.32(幅/秒)。在纹理检测模块中,本文对五种常用的纹理算法进行了研究,在此基础上提出了一种将基于粒子群模糊聚类算法的边缘检测方法和Gabor函数相结合来进行皮肤纹理检测的方法,取得了较好的实验结果。通过与DCT变换方法的比较可以看出本文的方法在正检率上提高了16%,误检率下降了22%,实验结果很理想。
在分类器选取中,本文选用决策树作为本文的分类器。实验结果表明,本文对敏感图像的过滤具有明显的效果,能够很好的分辨非正常图像与正常图像。
With the continuous development of technology network progressed rapidly. WEB just like a double-edged sword, many morally corrupt men ran into upload pictures of many obscene, pornographic, causing serious pollution of cyberspace, when we are rejoicing in powerful WEB. Many researchers using blockade pornographic websites, filtering the text information with sensitive words to clean the WEB. But the image control of pornography is not very effective, so the technology of filtering sensitive image that based on content emerged as the times require. In this paper, we study the based on the specific content of the sensitive image filtering techniques. The study included the following.
Sensitive image filtering module includes skin detection module、texture detection module、feature extraction module and classification module. In the skin detection module, compared through experiments, this paper proposed the method of combining color space model and statistical histogram model. Compared with color space model, Gaussian mixture model, and statistical histogram model, the experimental results show that the detection speed up to 2.32 images per second. In the texture detection module, in this paper, five kinds of commonly texture algorithms are researched. In the algorithm of skin texture, a fuzzy clustering algorithm which based on particle swarm optimization and the Gabor wavelet transform edge detection is proposed in this article. It has achieved good results. By comparison with the DCT transformation method can be seen that using this method, the correct detection rate increases 16% and the error detection rate decreases 22%.
In classifier selection, this article selected tree as classifier. Experimental results show that the filtering of sensitive images have a significant effect, it is able to distinguish between sensitive image and normal image.
敏感图像的过滤模块主要有肤色检测模块、纹理检测模块、特征提取模块和分类器模块。在肤色检测模块中,通过实验比较本文提出了色度空间模型和统计直方图模型相结合的方法来进行肤色检测,实验结果表明与传统的色度空间模型、高斯混合模型、统计直方图模型相比检测速度提高到2.32(幅/秒)。在纹理检测模块中,本文对五种常用的纹理算法进行了研究,在此基础上提出了一种将基于粒子群模糊聚类算法的边缘检测方法和Gabor函数相结合来进行皮肤纹理检测的方法,取得了较好的实验结果。通过与DCT变换方法的比较可以看出本文的方法在正检率上提高了16%,误检率下降了22%,实验结果很理想。
在分类器选取中,本文选用决策树作为本文的分类器。实验结果表明,本文对敏感图像的过滤具有明显的效果,能够很好的分辨非正常图像与正常图像。
With the continuous development of technology network progressed rapidly. WEB just like a double-edged sword, many morally corrupt men ran into upload pictures of many obscene, pornographic, causing serious pollution of cyberspace, when we are rejoicing in powerful WEB. Many researchers using blockade pornographic websites, filtering the text information with sensitive words to clean the WEB. But the image control of pornography is not very effective, so the technology of filtering sensitive image that based on content emerged as the times require. In this paper, we study the based on the specific content of the sensitive image filtering techniques. The study included the following.
Sensitive image filtering module includes skin detection module、texture detection module、feature extraction module and classification module. In the skin detection module, compared through experiments, this paper proposed the method of combining color space model and statistical histogram model. Compared with color space model, Gaussian mixture model, and statistical histogram model, the experimental results show that the detection speed up to 2.32 images per second. In the texture detection module, in this paper, five kinds of commonly texture algorithms are researched. In the algorithm of skin texture, a fuzzy clustering algorithm which based on particle swarm optimization and the Gabor wavelet transform edge detection is proposed in this article. It has achieved good results. By comparison with the DCT transformation method can be seen that using this method, the correct detection rate increases 16% and the error detection rate decreases 22%.
In classifier selection, this article selected tree as classifier. Experimental results show that the filtering of sensitive images have a significant effect, it is able to distinguish between sensitive image and normal image.
引文
[1]段丽娟.基于内容的图像检索与过滤关键技术研究[D].中国科学院研究生院博士学位论文.2002：1-5
[2]李雁,申铉京,赵德斌.基于纹理的皮肤检测[J].计算机工程与应用.2003,19：74-77
[3]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].吉林大学硕士学位论文.2004：1-4
[4]Margaret Fleck, David A.Forsyth, Chris Bregler. Finding Naked People[J]. In European Conference on Computer Vision,1996,2:593-602
[5]Z. Wang, G Wiederhold, O. Firschein. System for Screening Objectionable Images[J]. Computer Communications,1998,21:1355-1600
[6]M. J. Jones, J. M. Rehg. Statistical Color Model With Application to Skin Detection[J]. Proceedings of CVPR,1999:274-280
[7]http://www.ltutech.com/en/technology-and-products.technology.html
[8]Alexandru, F. Drimbarean. Image processing techniques to detect and filter objectionable images based on skin tone and shape recognition[C], IEEE, 2001
[9]http://www.clearswift.com/
[10]赵建成.基于内容的图像检索技术的研究与应用[D].华东师范大学硕士学位论文.2007：9-10
[11]章霄,董艳雪,赵文娟,张彦嘉.数字图像处理技术[M].冶金工业出版社,2005：28-36
[12]谷海伟.网络图像的数据捕获及敏感图像识别的关键技术研究[D].吉林大学法学院硕士学位论文.2008：20-21
[13]姚鸿勋,刘明宝,高文等.基于彩色图像的色系坐标变换的面部定位与跟 踪法[J].计算机学报,2000,23(2)：158-165
[14]Castleman Kenneth R. Digital image processing[M].大学出版社,2002
[15]lijuan Duan, Guoqin Cui,Wen Gao and Hongming Zhang. Adult Image Detection Method Base-On Skin Color Model And Support Vector Machine[C]. ACCV2002.2002:22-25
[16]冯红军.图像过滤关键技术的研究及应用[D].北京工业大学工学硕士学位论文.2003：12-13
[17]杨珺,史忠科.基于改进单高斯模型法的交通背景提取[J].光子学报,2009,38(5)：1293-1296
[18]何东健,耿楠,张义宽等.数字图像处理[M].西安电子科技大学出版社第二版,2008：89,226-231
[19]陈天华.数字图像处理[M].清华大学出版社第一版,2007：282-288
[20]郑南宁.计算机视觉与模式识别[M].国防工业出版社第一版,1998：89-95
[21]章毓晋.基于内容的视觉信息检索[M].科学出版社,2003：84-88
[22]徐欣欣,袁华,张凌.利用颜色和纹理特征的图像过滤方法[J].华南理工大学学报(自然科学版).2004,32(S)：24-27
[23]刘达志.基于内容的敏感图像过滤系统研究与设计[D].解放军信息工程大学硕士学位论文.2005：34-38
[24]R. M. Haralick. Statistical and Structural. Approaches to Texture[C]. Proc. of IEEE.1979,67(5):45-69
[25]http://www.cnblogs.com/itzou/archive/2005/11/30/288145.html
[26]杨金峰.基于内容敏感图像过滤关键技术研究及应用[D].吉林大学硕士学位论文.2004：25-27
[27]江志伟.基于内容的WEB图像过滤技术研究[D].浙江大学博士学位论文.2007：5-9
[28]冉启文.小波变换与分数傅里叶变换理论及应用[M].哈尔滨工业大学出版社第一版.2001：58-61
[29]蒋先刚.数字图像模式识别工程软件设计[M].中国水利水电出版社第一版.2008：28-30
[30]David A. Forsyth and Margaret M. Fleek. Automatic detection of human nudes[J]. International Journal of Computer Vision,1999,32(1):63-77
[31]胡峰丽.基于内容的图像检索技术研究[D].辽宁师范大学硕士学位论文.2007：15-17
[32]http://zhidao.baidu.com/question/86617957.html
[33]Kennedy J, Eberhart R C, Shi Y. Swarm Intelligence[C]. Sari Francisco: Morgan Kaufman Publishers,2001
[34]王凌,刘波.微粒群优化与调度计算[M].清华大学出版社第一版.2008：1-2
[35]Kennedy and R.C.Eberhart. Particle swarm optimization[C]. In:IEEE International Conference on Neural Networks(ICNN'95),1995,4:1942-1947
[36]高新波.模糊聚类分析及其应用[M].西安电子科技大学出版社第一版.2004：2-3,49-55
[37]张李秋.一种基于纹理特征提取的图像检索方法[D].电子科技大学硕士学位论文.2007：6
[38]石振刚,高立群,葛雯.基于粒子群模糊聚类算法的边缘检测仿真[J].东北大学学报(自然科学版).2008,29(8)：1083-1086
[39]D.A.Forsyth, Identifying nude Pictures[C], IEEE,1996
[40]陈柏生.一种二值图像连通区域标记的新方法[J].计算机工程与应用.2006,25：46-47
[41]赵晓辉.基于内容的敏感图片过滤技术的研究及其在IE浏览器中的实现[D].吉林大学法学院硕士学位论文.2003：22-25
[42]李雄飞,李军.数据挖掘与知识发现[M].高等教育出版社第一版.2003：12-13,161-173
[43]范晓.基于IE浏览器的色情图片过滤器的设计和实现.吉林大学法学院硕 士学位论文.2004：30-31.
[44]W.Y. Ma, B.S. Manjunath. Texture features and learning similarity[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1996:425-430
[45](印度K.P. Soman Shyam Diwakar V. Ajay著,范明,牛常勇译.数据挖掘基础教程[M].机械工业出版社第一版.2009：40-51
[46]胡可云,田凤占,黄厚宽.数据挖掘理论与应用[M].清华大学出版社,北京交通大学出版社第一版.2008：34-38
[2]李雁,申铉京,赵德斌.基于纹理的皮肤检测[J].计算机工程与应用.2003,19：74-77
[3]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].吉林大学硕士学位论文.2004：1-4
[4]Margaret Fleck, David A.Forsyth, Chris Bregler. Finding Naked People[J]. In European Conference on Computer Vision,1996,2:593-602
[5]Z. Wang, G Wiederhold, O. Firschein. System for Screening Objectionable Images[J]. Computer Communications,1998,21:1355-1600
[6]M. J. Jones, J. M. Rehg. Statistical Color Model With Application to Skin Detection[J]. Proceedings of CVPR,1999:274-280
[7]http://www.ltutech.com/en/technology-and-products.technology.html
[8]Alexandru, F. Drimbarean. Image processing techniques to detect and filter objectionable images based on skin tone and shape recognition[C], IEEE, 2001
[9]http://www.clearswift.com/
[10]赵建成.基于内容的图像检索技术的研究与应用[D].华东师范大学硕士学位论文.2007：9-10
[11]章霄,董艳雪,赵文娟,张彦嘉.数字图像处理技术[M].冶金工业出版社,2005：28-36
[12]谷海伟.网络图像的数据捕获及敏感图像识别的关键技术研究[D].吉林大学法学院硕士学位论文.2008：20-21
[13]姚鸿勋,刘明宝,高文等.基于彩色图像的色系坐标变换的面部定位与跟 踪法[J].计算机学报,2000,23(2)：158-165
[14]Castleman Kenneth R. Digital image processing[M].大学出版社,2002
[15]lijuan Duan, Guoqin Cui,Wen Gao and Hongming Zhang. Adult Image Detection Method Base-On Skin Color Model And Support Vector Machine[C]. ACCV2002.2002:22-25
[16]冯红军.图像过滤关键技术的研究及应用[D].北京工业大学工学硕士学位论文.2003：12-13
[17]杨珺,史忠科.基于改进单高斯模型法的交通背景提取[J].光子学报,2009,38(5)：1293-1296
[18]何东健,耿楠,张义宽等.数字图像处理[M].西安电子科技大学出版社第二版,2008：89,226-231
[19]陈天华.数字图像处理[M].清华大学出版社第一版,2007：282-288
[20]郑南宁.计算机视觉与模式识别[M].国防工业出版社第一版,1998：89-95
[21]章毓晋.基于内容的视觉信息检索[M].科学出版社,2003：84-88
[22]徐欣欣,袁华,张凌.利用颜色和纹理特征的图像过滤方法[J].华南理工大学学报(自然科学版).2004,32(S)：24-27
[23]刘达志.基于内容的敏感图像过滤系统研究与设计[D].解放军信息工程大学硕士学位论文.2005：34-38
[24]R. M. Haralick. Statistical and Structural. Approaches to Texture[C]. Proc. of IEEE.1979,67(5):45-69
[25]http://www.cnblogs.com/itzou/archive/2005/11/30/288145.html
[26]杨金峰.基于内容敏感图像过滤关键技术研究及应用[D].吉林大学硕士学位论文.2004：25-27
[27]江志伟.基于内容的WEB图像过滤技术研究[D].浙江大学博士学位论文.2007：5-9
[28]冉启文.小波变换与分数傅里叶变换理论及应用[M].哈尔滨工业大学出版社第一版.2001：58-61
[29]蒋先刚.数字图像模式识别工程软件设计[M].中国水利水电出版社第一版.2008：28-30
[30]David A. Forsyth and Margaret M. Fleek. Automatic detection of human nudes[J]. International Journal of Computer Vision,1999,32(1):63-77
[31]胡峰丽.基于内容的图像检索技术研究[D].辽宁师范大学硕士学位论文.2007：15-17
[32]http://zhidao.baidu.com/question/86617957.html
[33]Kennedy J, Eberhart R C, Shi Y. Swarm Intelligence[C]. Sari Francisco: Morgan Kaufman Publishers,2001
[34]王凌,刘波.微粒群优化与调度计算[M].清华大学出版社第一版.2008：1-2
[35]Kennedy and R.C.Eberhart. Particle swarm optimization[C]. In:IEEE International Conference on Neural Networks(ICNN'95),1995,4:1942-1947
[36]高新波.模糊聚类分析及其应用[M].西安电子科技大学出版社第一版.2004：2-3,49-55
[37]张李秋.一种基于纹理特征提取的图像检索方法[D].电子科技大学硕士学位论文.2007：6
[38]石振刚,高立群,葛雯.基于粒子群模糊聚类算法的边缘检测仿真[J].东北大学学报(自然科学版).2008,29(8)：1083-1086
[39]D.A.Forsyth, Identifying nude Pictures[C], IEEE,1996
[40]陈柏生.一种二值图像连通区域标记的新方法[J].计算机工程与应用.2006,25：46-47
[41]赵晓辉.基于内容的敏感图片过滤技术的研究及其在IE浏览器中的实现[D].吉林大学法学院硕士学位论文.2003：22-25
[42]李雄飞,李军.数据挖掘与知识发现[M].高等教育出版社第一版.2003：12-13,161-173
[43]范晓.基于IE浏览器的色情图片过滤器的设计和实现.吉林大学法学院硕 士学位论文.2004：30-31.
[44]W.Y. Ma, B.S. Manjunath. Texture features and learning similarity[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1996:425-430
[45](印度K.P. Soman Shyam Diwakar V. Ajay著,范明,牛常勇译.数据挖掘基础教程[M].机械工业出版社第一版.2009：40-51
[46]胡可云,田凤占,黄厚宽.数据挖掘理论与应用[M].清华大学出版社,北京交通大学出版社第一版.2008：34-38