手机浏览器不良图片过滤软件设计与实现
|
摘要
近年来通过互联网和移动通信网络传播的不良信息(主要是淫秽色情内容)对广大未成年人的身心健康造成了恶劣影响。这一问题日益引起社会各界的关注。目前不良图片和不良网站的过滤技术主要有三种：基于URL的过滤、基于文本内容的过滤和基于图像内容的过滤。基于图像内容的过滤技术相比于前两种技术具有更广泛的适应性和更高的灵活性。本课题着重研究基于图像内容的过滤。
截至2010年9月,本人在中国知网CNKI上没有检索到国内有论文研究应用于手机浏览器的基于图像内容的不良图片过滤,在搜索引擎上也没有搜索到国内有已而市或推广的应用于手机浏览器的基于图像内容的不良图片过滤软件。
本人选定基于Windows Mobile 6操作系统和ARM微处理器的智能手机作为开发平台,OpenCV作为图像检测模块的开发工具。经过对智能手机平台软硬件特点的分析,确定合适的基于图像内容的不良图片检测方法。本文提出了一种基于Winsock分层服务提供者LSP技术的浏览器色情图片过滤软件框架。由于Windows Mobile应用程序开发与桌面Windows应用程序开发有许多相似之处,而且OpenCV必须经过移植才能在Windows Mobile上使用,在开发过程中,为了方便调试和性能比较,首先实现了应用于桌面Windows的浏览器不良图片过滤软件,该软件的网络数据截获模块采用了LSP技术,图像检测模块采用了人脸检测、白平衡矫正皮肤检测、支持向量机SVM等技术(皮肤检测又包括肤色检测、纹理检测、皮肤连通区域检测等)。经验证,该软件在桌面Windows上可实时过滤浏览器访问到的不良图片,并具有较高的准确率。然后将原本不能适用于Windows Mobile的OpenCV库移植到了Windows Mobile 6平台上,并将已开发的适用于桌面Windows的浏览器不良图片过滤软件移植到了Windows Mobile 6平台上。经过测试,该软件在Windows Mobile手机上能正常工作,但由于智能手机的硬件条件限制,对于一般的智能手机而言,人脸检测的计算量较大,图像检测模块的耗时较长。
In recent years, with the popularity of the Internet and mobile phones day by day, harmful information, especially pornographic information, spreads through the Internet and the mobile network, resulting in very negative impact on the physical and mental health of minors. The problem arouses more and more concern of society. Up to now there are three major methods for filtering pornographic images and pornographic Web sites, which are filter based on URL that is short for Uniform Resource Locator, filter based on text and filter based on image content. Compared to the first two methods, the adaptability of filter based on image content is wider and its flexibility is higher. The thesis focuses on content-based image filter.
Up to September 2010, I found that there were no articles on content-based pornographic image filter for mobile phones in CNKI that is short for China National Knowledge Infrastructure and no software for mobile phones to filtrate pornographic images comes into market in China in search engines.
Smart mobile phone based on Windows Mobile 6 operating system and ARM microprocessor is selected as the development platform, and OpenCV which is an open source computer vision library is selected as the development tool of the image-detecting module. After the features of the hardware and software of the smart mobile phone platform are analyzed, appropriate content-based methods for filtering pornographic images are selected. A software framework for filtering pornographic Web images is presented, which is based on LSP that is short for Layered Service Provider. Because the application development of Windows Mobile is similar to that of Windows desktop and OpenCV cannot be directly used on Windows Mobile, software filtering pornographic Web images for the Windows desktop is developed at first in order to facilitate debugging and comparision. The principle of the module hooking network messages is LSP, and the principle of the module on image-detectinging is face detection, white-balance correction, skin detection and SVM that is short for Support Vector Machines. And skin detection includes skin color detection, texture detetion and connected skin region detection. When it is tested on Windows desktop, the software can real-time filter pornographic images on webpages and its accuracy is fairly high. And then OpenCV and the software are both ported to Windows Mobile. Testing result shows that the software can work on a Windows Mobile phone, but because of the hardware limit of average smart mobile phones, the calculation amount of face detection is quite large, and the module on image-detecting is a litte slow.
截至2010年9月,本人在中国知网CNKI上没有检索到国内有论文研究应用于手机浏览器的基于图像内容的不良图片过滤,在搜索引擎上也没有搜索到国内有已而市或推广的应用于手机浏览器的基于图像内容的不良图片过滤软件。
本人选定基于Windows Mobile 6操作系统和ARM微处理器的智能手机作为开发平台,OpenCV作为图像检测模块的开发工具。经过对智能手机平台软硬件特点的分析,确定合适的基于图像内容的不良图片检测方法。本文提出了一种基于Winsock分层服务提供者LSP技术的浏览器色情图片过滤软件框架。由于Windows Mobile应用程序开发与桌面Windows应用程序开发有许多相似之处,而且OpenCV必须经过移植才能在Windows Mobile上使用,在开发过程中,为了方便调试和性能比较,首先实现了应用于桌面Windows的浏览器不良图片过滤软件,该软件的网络数据截获模块采用了LSP技术,图像检测模块采用了人脸检测、白平衡矫正皮肤检测、支持向量机SVM等技术(皮肤检测又包括肤色检测、纹理检测、皮肤连通区域检测等)。经验证,该软件在桌面Windows上可实时过滤浏览器访问到的不良图片,并具有较高的准确率。然后将原本不能适用于Windows Mobile的OpenCV库移植到了Windows Mobile 6平台上,并将已开发的适用于桌面Windows的浏览器不良图片过滤软件移植到了Windows Mobile 6平台上。经过测试,该软件在Windows Mobile手机上能正常工作,但由于智能手机的硬件条件限制,对于一般的智能手机而言,人脸检测的计算量较大,图像检测模块的耗时较长。
In recent years, with the popularity of the Internet and mobile phones day by day, harmful information, especially pornographic information, spreads through the Internet and the mobile network, resulting in very negative impact on the physical and mental health of minors. The problem arouses more and more concern of society. Up to now there are three major methods for filtering pornographic images and pornographic Web sites, which are filter based on URL that is short for Uniform Resource Locator, filter based on text and filter based on image content. Compared to the first two methods, the adaptability of filter based on image content is wider and its flexibility is higher. The thesis focuses on content-based image filter.
Up to September 2010, I found that there were no articles on content-based pornographic image filter for mobile phones in CNKI that is short for China National Knowledge Infrastructure and no software for mobile phones to filtrate pornographic images comes into market in China in search engines.
Smart mobile phone based on Windows Mobile 6 operating system and ARM microprocessor is selected as the development platform, and OpenCV which is an open source computer vision library is selected as the development tool of the image-detecting module. After the features of the hardware and software of the smart mobile phone platform are analyzed, appropriate content-based methods for filtering pornographic images are selected. A software framework for filtering pornographic Web images is presented, which is based on LSP that is short for Layered Service Provider. Because the application development of Windows Mobile is similar to that of Windows desktop and OpenCV cannot be directly used on Windows Mobile, software filtering pornographic Web images for the Windows desktop is developed at first in order to facilitate debugging and comparision. The principle of the module hooking network messages is LSP, and the principle of the module on image-detectinging is face detection, white-balance correction, skin detection and SVM that is short for Support Vector Machines. And skin detection includes skin color detection, texture detetion and connected skin region detection. When it is tested on Windows desktop, the software can real-time filter pornographic images on webpages and its accuracy is fairly high. And then OpenCV and the software are both ported to Windows Mobile. Testing result shows that the software can work on a Windows Mobile phone, but because of the hardware limit of average smart mobile phones, the calculation amount of face detection is quite large, and the module on image-detecting is a litte slow.
引文
[1]http://news.163.com/10/0304/18/60UUSL310001124J.html.
[2]http://www.cctv.com/cctvsurvey/special/04/20091203/102981.shtml.
[3]http://www.fjfxh.fjfxh.cn/news.asp?id=249.
[4]http://baike.baidu.com/view/2526346.html.
[5]http://news.163.com/11/0112/08/6Q6E6GTK0001124J.html.
[6]王宇石.基于图像内容的成人图像检测：(博士学位论文).哈尔滨：哈尔滨工业大学,2009.
[7]Yushi Wang, Qingming Huang, Wen Gao. Pornographic image detection based on multi-level representation. International Journal of Pattern Recognition and Artificial Intelligence,2009,23(8),1633-1655.
[8]董开坤,胡铭曾,方滨兴.基于图像内容过滤的防火墙技术综述.通信学报,2003,24(1)：83-90.
[9]http://www.ltutech.com/.
[10]http://www.clearswift.com/.
[11]http://www.imagebeagle.com/.
[12]Margaret Fleck, David Forsyth, Chris Bregler. Finding naked people. European Conference on Computer Vision,1996,2:593-602.
[13]David Forsyth, Margaret Fleck. Automatic detection of human nudes. International Journal of Computer Vision,1999,32(1):63-77.
[14]Z Wang, G Wiederhold,0 Firschein. System for screening objectionable images. Computer Communications,1998,21:1355-1360.
[15]段立娟.基于内容的图像检索与过滤关键技术研究：(博士学位论文).北京：中国科学院计算技术研究所,2003.
[16]段立娟,高文,林守勋,马继勇.图像检索中的动态相似性度量方法.计算机学报,2001,24(11),1156-1162.
[17]P Viola, M Jones. Rapid object detection using a boosted cascade of simple features. Proceedings of IEEE Conference on CVPR,2001:511-518.
[18]P Viola, M Jones. Robust real-time face detection. Intemational Joumal of Computer Vision,2004,57(2):137-154.
[19]Gary Bradski, Adrian Kaebler.学习 OpenCV. 北京:清华大学出版社,2009.
[20]刘瑞祯,于仕琪OpenCV教程.北京：北京航空航天大学出版社,2007.
[21]Elli Angelopoulou. Understanding the color of human skin. Proceedings of the SPIE Conference on Human Vision and Electronic Imaging Ⅵ(SPIE),2001,4299:243-251.
[22]林福宗.多媒体技术基础.北京：清华大学出版社,2009.
[23]Ze-Nian Li, Mark S Drew多媒体技术教程.北京：机械工业出版社,2007.
[24]江志伟.基于内容的WEB图像过滤技术研究：(博士学位论文).杭州：浙江大学,2007.
[25]Zhiwei Jiang, Min Yao, Wensheng Yi. Filtering objectionable image based on image content. PRICAI 2006:Trends in Artifieial Intelligence,Lecture Notes in Artificial Intelligence,2006,4099:1027-1031.
[26]Albiol A,Tomes L, Delp E J. Optimum color spaces for skin detection. Proceedings of the Intemational Conference on Image Proeessing,2001,1:122-124.
[27]Min Shin, Kyong Chang, Leonid Tsap.Does colorspace transformation make any difference on skin detection. Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision,2002:275-279.
[28]Terrilion J C,Shirazi M N, Fukamachi H,Akamatsu S.Comparative performance of different skin chrominance models and chrominace spaces for the automatic detection of human faces in color images. Proceedings of the International Conference on Face and Gesture Recognition,2000:54-61.
[29]Chai D,Ngan K N. Face segmentation using skin-color map in videophone applications.IEEE Transactions CAS for Video Technology,1999,9(4):551-564.
[30]Michael J Jones, James M Rehg. Statistical color model with application to skin detection. Computer Vision and Pattern Recognition, IEEE Computer Society Conference,1999:274-280.
[31]Vladimir Vezhnevets, Vassili Sazonov, Alia Andreeva. A survey on pixel-based skin color detection techniques. Proceedings of the Graphic Conference,2003:85-92.
[32]Son Lam Phung, Douglas Chai, Abdesselam Bouzerdoum. Adaptive skin segmentation in color images. IEEE International Conference on Acoustics, Speech and Signal Processing,2003:353-356.
[33]左飞,万晋森,刘航Visual C++数字图像处理开发入门与编程实践.北京：电子工业出版社,2007.
[34]http://baike.baidu.com/view/860.htm.
[35]李晶皎,赵丽红,王爱侠.模式识别.北京：电子工业出版社,2010.
[36]Sergios Theodoridis, Konstantinos Koutroumbas模式识别.北京：电子工业出版社,2010.
[37]傅曦,齐宇,徐骏Windows Mobile手机应用开发.北京：人民邮电出版社,2005.
[38]张冬泉,谭南林,王雪梅Windows CE实用开发技术.北京：电子工业出版社,2006.
[39]汪兵.EVC高级编程及其应用开发.北京：中国水利水电出版社,2005.
[40]Alex Karpus. An OpenCV Implementation of a QR Barcode Reader for the iPhone and Windows Mobile Platforms:Honours Project. Ottawa:Carleton University,2009.
[41]王艳平Windows网络与通信程序设计.北京：人民邮电出版社,2009.
[42]Wei Ilua, Jim Ohlund, Barry Butterklee. Unraveling the mysteries of writing a Winsock 2 Layered Service Provider.Microsoft Systems Journal,1999,61:96-113.
[43]王旭阳.基于Windows的多种网络数据包过滤方案的比较分析.电脑开发与应用,2007,20(7)：54-55,68.
[44]张宏怡,普杰信.基于Windows的网络数据包拦截技术.信息技术,2004,28(2)：12-13,33.
[45]赵晓晖.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：(硕士学位论文).长春：吉林大学,2005.
[46]范晓.基于IE浏览器的色情图片过滤器的设计和实现：(硕士学位论文).长春：吉林大学,2004.
[47]范晓,申铉京.基于IE浏览器的色情图片过滤.吉林大学学报(信息科学版),2004,22(6)：631-637.
[48]汪晓平,钟军Visual C++网络通信协议分析与应用实现.北京：人民邮电出版社,2003.
[49]高守传,周书锋Windows网络程序设计完全讲义.北京：中国水利水电出版社,2010.
[50]谢希仁.计算机网络.北京：电子工业出版社,2008.
[51]陈智飞,王映辉.一种网络不良图像过滤软件框架.计算机技术与发展,2010,20(7)：149-151,155.
[2]http://www.cctv.com/cctvsurvey/special/04/20091203/102981.shtml.
[3]http://www.fjfxh.fjfxh.cn/news.asp?id=249.
[4]http://baike.baidu.com/view/2526346.html.
[5]http://news.163.com/11/0112/08/6Q6E6GTK0001124J.html.
[6]王宇石.基于图像内容的成人图像检测：(博士学位论文).哈尔滨：哈尔滨工业大学,2009.
[7]Yushi Wang, Qingming Huang, Wen Gao. Pornographic image detection based on multi-level representation. International Journal of Pattern Recognition and Artificial Intelligence,2009,23(8),1633-1655.
[8]董开坤,胡铭曾,方滨兴.基于图像内容过滤的防火墙技术综述.通信学报,2003,24(1)：83-90.
[9]http://www.ltutech.com/.
[10]http://www.clearswift.com/.
[11]http://www.imagebeagle.com/.
[12]Margaret Fleck, David Forsyth, Chris Bregler. Finding naked people. European Conference on Computer Vision,1996,2:593-602.
[13]David Forsyth, Margaret Fleck. Automatic detection of human nudes. International Journal of Computer Vision,1999,32(1):63-77.
[14]Z Wang, G Wiederhold,0 Firschein. System for screening objectionable images. Computer Communications,1998,21:1355-1360.
[15]段立娟.基于内容的图像检索与过滤关键技术研究：(博士学位论文).北京：中国科学院计算技术研究所,2003.
[16]段立娟,高文,林守勋,马继勇.图像检索中的动态相似性度量方法.计算机学报,2001,24(11),1156-1162.
[17]P Viola, M Jones. Rapid object detection using a boosted cascade of simple features. Proceedings of IEEE Conference on CVPR,2001:511-518.
[18]P Viola, M Jones. Robust real-time face detection. Intemational Joumal of Computer Vision,2004,57(2):137-154.
[19]Gary Bradski, Adrian Kaebler.学习 OpenCV. 北京:清华大学出版社,2009.
[20]刘瑞祯,于仕琪OpenCV教程.北京：北京航空航天大学出版社,2007.
[21]Elli Angelopoulou. Understanding the color of human skin. Proceedings of the SPIE Conference on Human Vision and Electronic Imaging Ⅵ(SPIE),2001,4299:243-251.
[22]林福宗.多媒体技术基础.北京：清华大学出版社,2009.
[23]Ze-Nian Li, Mark S Drew多媒体技术教程.北京：机械工业出版社,2007.
[24]江志伟.基于内容的WEB图像过滤技术研究：(博士学位论文).杭州：浙江大学,2007.
[25]Zhiwei Jiang, Min Yao, Wensheng Yi. Filtering objectionable image based on image content. PRICAI 2006:Trends in Artifieial Intelligence,Lecture Notes in Artificial Intelligence,2006,4099:1027-1031.
[26]Albiol A,Tomes L, Delp E J. Optimum color spaces for skin detection. Proceedings of the Intemational Conference on Image Proeessing,2001,1:122-124.
[27]Min Shin, Kyong Chang, Leonid Tsap.Does colorspace transformation make any difference on skin detection. Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision,2002:275-279.
[28]Terrilion J C,Shirazi M N, Fukamachi H,Akamatsu S.Comparative performance of different skin chrominance models and chrominace spaces for the automatic detection of human faces in color images. Proceedings of the International Conference on Face and Gesture Recognition,2000:54-61.
[29]Chai D,Ngan K N. Face segmentation using skin-color map in videophone applications.IEEE Transactions CAS for Video Technology,1999,9(4):551-564.
[30]Michael J Jones, James M Rehg. Statistical color model with application to skin detection. Computer Vision and Pattern Recognition, IEEE Computer Society Conference,1999:274-280.
[31]Vladimir Vezhnevets, Vassili Sazonov, Alia Andreeva. A survey on pixel-based skin color detection techniques. Proceedings of the Graphic Conference,2003:85-92.
[32]Son Lam Phung, Douglas Chai, Abdesselam Bouzerdoum. Adaptive skin segmentation in color images. IEEE International Conference on Acoustics, Speech and Signal Processing,2003:353-356.
[33]左飞,万晋森,刘航Visual C++数字图像处理开发入门与编程实践.北京：电子工业出版社,2007.
[34]http://baike.baidu.com/view/860.htm.
[35]李晶皎,赵丽红,王爱侠.模式识别.北京：电子工业出版社,2010.
[36]Sergios Theodoridis, Konstantinos Koutroumbas模式识别.北京：电子工业出版社,2010.
[37]傅曦,齐宇,徐骏Windows Mobile手机应用开发.北京：人民邮电出版社,2005.
[38]张冬泉,谭南林,王雪梅Windows CE实用开发技术.北京：电子工业出版社,2006.
[39]汪兵.EVC高级编程及其应用开发.北京：中国水利水电出版社,2005.
[40]Alex Karpus. An OpenCV Implementation of a QR Barcode Reader for the iPhone and Windows Mobile Platforms:Honours Project. Ottawa:Carleton University,2009.
[41]王艳平Windows网络与通信程序设计.北京：人民邮电出版社,2009.
[42]Wei Ilua, Jim Ohlund, Barry Butterklee. Unraveling the mysteries of writing a Winsock 2 Layered Service Provider.Microsoft Systems Journal,1999,61:96-113.
[43]王旭阳.基于Windows的多种网络数据包过滤方案的比较分析.电脑开发与应用,2007,20(7)：54-55,68.
[44]张宏怡,普杰信.基于Windows的网络数据包拦截技术.信息技术,2004,28(2)：12-13,33.
[45]赵晓晖.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：(硕士学位论文).长春：吉林大学,2005.
[46]范晓.基于IE浏览器的色情图片过滤器的设计和实现：(硕士学位论文).长春：吉林大学,2004.
[47]范晓,申铉京.基于IE浏览器的色情图片过滤.吉林大学学报(信息科学版),2004,22(6)：631-637.
[48]汪晓平,钟军Visual C++网络通信协议分析与应用实现.北京：人民邮电出版社,2003.
[49]高守传,周书锋Windows网络程序设计完全讲义.北京：中国水利水电出版社,2010.
[50]谢希仁.计算机网络.北京：电子工业出版社,2008.
[51]陈智飞,王映辉.一种网络不良图像过滤软件框架.计算机技术与发展,2010,20(7)：149-151,155.