[1]陈俊伟,张丽春,吕 岳.基于截图内容的图片垃圾邮件过滤系统[J].智能系统学报,2008,3(5):416-422.
CHEN Jun-wei,ZHANG L i-chun,LU¨Yue.A spam image f ilter ing system based on user-spec if ied image content[J].CAAI Transactions on Intelligent Systems,2008,3(5):416-422.
点击复制
CHEN Jun-wei,ZHANG L i-chun,LU¨Yue.A spam image f ilter ing system based on user-spec if ied image content[J].CAAI Transactions on Intelligent Systems,2008,3(5):416-422.
基于截图内容的图片垃圾邮件过滤系统
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
3
期数:
2008年第5期
页码:
416-422
栏目:
学术论文—智能系统
出版日期:
2008-10-25
- Title:
- A spam image f ilter ing system based on user-spec if ied image content
- 文章编号:
- 1673-4785 (2008) 05-0416-07
- 分类号:
- TP391. 4
- 文献标志码:
- A
- 摘要:
- 垃圾邮件制造者常常将文字嵌入到图像中,产生了大量的图片垃圾邮件. 为解决这一问题,提出并实现了一个基于截图内容的图片垃圾邮件过滤方案. 首先由用户从垃圾邮件中截取某一子域图片,每一截图对应一类垃圾图片,所有的截图构成一个自定义的垃圾图片“黑名单”. 其次对读入的每一封图片邮件,其内置图片与“黑名单”中的图片进行图像匹配. 最后若存在匹配项,则判定该邮件含有用户已指定的垃圾图片信息. 将此图片垃圾邮件过滤方案应用于一个小型的邮件收发系统,使用3 534幅垃圾邮件图片进行实验,结果证明了该垃圾邮件过滤方案有效.
- Abstract:
- Spammers often embed text in images in innocuous seeming emails, resulting in large numbers of spam images which are difficult to filter out. To solve this p roblem, a spam image filtering system was developed that ap2 p lies user2specified identification of spam image content. First, users were asked to identify spam images from emails to generate a class of spam images. These imageswere then added to a blacklist. Next, images in incoming e2mailswere matched with images stored in the image blacklist. Finally, if a matching image was found, the e2mail was judged as spam because it contained images identified as spam by users. Testing with an e2mail server contai2 ning 3534 samp le images p roved the p roposed method effectively intercep ts spam e2mails
- 参考文献/References:
-
[ 1 ] HEYMANN P, KOUTR IKA G, HECTOR G M. Fighting spam on socialweb sites: a survey of app roaches and future challenges [ J ]. IEEE Internet Computing, 2007, 11 ( 6) : 36245.
?[ 2 ] ARADHYE H B, MYERS G K, HERSON J A. Image a2 nalysis for efficient categorization of image2based spam e2 mail [ C ] / / Eighth International Conference on Document Analysis and Recognition ( ICDAR’05). Seoul, South Kore2 a, 2005: 9142918.
[ 3 ] KUMAGA IN, AR ITSUGIM. On app lying an image p ro2 cessing technique to detecting spam [ C ] / / Proceedings of the 21st International Conference on Data Engineering. To2 kyo, Japan, 2005: 1642168.
[ 4 ] B IGGIO B, FUMERA G, P ILLA I I, ROL I F. Image spam filtering using visual information [ C ] / / 14 th International Conference on Image Analysis and Processing ( ICIAP 2007). Modena, Italy, 2007: 1052110.
[ 5 ] HOLMES N. In defense of spam [ J ]. Computer, 2005, 38 (4) : 86288.
[ 6 ] LOWE D G. Object recognition from local scale2invariant features [ C ] / / International Conference on Computer Vi2 sion. Corfu, Greece, 1999: 115021157.
?[ 7 ] 游素亚,杨 静. 图像边缘检测技术的发展与现状[ J ]. 电子科技导报, 1995, (8) : 25228.
?YOU Suya, YANG J ing. Image edge detection and its de2 velopment [ J ]. Electronic Science & Technology Review, 1995 (8) : 25228.
?[ 8 ] V IVARELL I F, W ILL IAMS K I. Discovering hidden fea2 tureswith Gaussian p rocesses regression[C ] / / Proceedings of the 1998 Conference on Advances in Neural Information Processing Systems II. Cambridge, MA, USA: M IT Press, 1999: 6132619.
[ 9 ] BROWN M, LOWE D G. Invariant features from interest point group s [ C ] / / British Machine Vision Conference, BMVC 2002. Cardiff, Wales, 2002: 6562665.
?[ 10 ] LOWE D G. Distinctive image features from scale2invari2 ant keypoints [ J ]. International Journal of Computer Vi2 sion, 2004, 60 (11) : 912110.
[ 11 ] BEIS J , LOWE D G. Shape indexing using app roximate nearest2neighbour search in high dimensional spaces [C ] / / Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Juan, PR, USA, 1997: 100021006.
[ 12 ] DREDZE M, GEVARYAHU R, BACHRACH A E. Learning fast classifiers for image spam[C ] / / Proceedings of the Conference on E-mail and Anti2Spam ( CEAS). West Point, NY, US, 2007: 2552261.
备注/Memo
收稿日期: 2008-07-15.
基金项目:国家自然科学基金资助项目(60475006) .
作者简介:?陈俊伟,男, 1984 年生,硕士研究生. 主要研究方向为图像处理和模式识别.
张丽春,女, 1982 年生,硕士研究生. 主要研究方向为图像处理和模式识别,发表论文2篇.
吕岳,男, 1968年生,教授,博士生导师,上海市自动化学会模式识别专业委员会副主任, 上海市计算机学会普适计算专业委员会副主任. 主要研究方向为图像处理、模式识别、智能系统,授权专利2项,发表论文60余篇.
通信作者:陈俊伟. E-mail: ilyjyz2002@163. com
更新日期/Last Update:
2009-05-18