图像型垃圾邮件监控系统研究与设计  

Research and Design of Monitoring System on Image Spam

作　　者：汪金涛[1] 曹玉东[1] 王梓宁[2] 刘艳洋 

机构地区：[1]辽宁工业大学电子与信息工程学院,辽宁锦州121001 [2]辽宁科技学院电气与信息工程学院,辽宁本溪117004

出　　处：《辽宁工业大学学报（自然科学版）》2016年第2期78-80,86,共4页Journal of Liaoning University of Technology(Natural Science Edition)

基　　金：国家自然科学基金项目(61272214);辽宁工业大学教师科研启动基金项目(X201216)

摘　　要：研究并设计了一个级联型邮件过滤系统,降低了图像型邮件错误分类的可能性。提出将垃圾图像做进一步分类的方案。首先利用图像的底层特征,使用支持向量机实现粗分类,识别出大多数正常邮件图像;然后基于词袋模型实现更精确地分类;最后提取垃圾邮件图像的文本区域信息,利用最近邻分类算法,比对敏感词库,将垃圾邮件细分为广告类、票据类、色情类和反动言论类等,实现有效地管理和监控图像型垃圾邮件。A cascaded image spam system was designed which decreased probability of error classification. A scheme on classifying image spam was further proposed. Firstly, a coarse classification was realized with low-level feature and Support Vector Machine. Then, an accurate classification was realized based on bag-of-words model. Finally, the image spam was categorized into advertisements, false invoice, pornography and illegal comments etc. The system can manage and monitor image spam effectively.

关 键 词：垃圾邮件监控 分类器 特征提取 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]