作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2010, Vol. 36 ›› Issue (16): 157-160. doi: 10.3969/j.issn.1000-3428.2010.16.057

• 人工智能及识别技术 • 上一篇    下一篇

基于梯度和颜色特征的图像垃圾邮件过滤

刘 芬,帅建梅   

  1. (中国科学技术大学自动化系,合肥 230027)
  • 出版日期:2010-08-20 发布日期:2010-08-17
  • 作者简介:刘 芬(1984-),女,硕士研究生,主研方向:模式识别,信息安全;帅建梅,高级工程师
  • 基金资助:
    国家“863”计划基金资助项目(2006AA01Z449)

Image Spam Filtering Based on Gradient and Color Feature

LIU Fen, SHUAI Jian-mei   

  1. (Department of Automation, University of Science and Technology of China, Hefei 230027)
  • Online:2010-08-20 Published:2010-08-17

摘要: 提出以图像的梯度直方图和颜色直方图作为分类特征,分析最小二乘支持向量机(LS-SVM)算法以及该算法与传统SVM算法的区别,比较传统分类算法与LS-SVM算法的分类准确度,将LS-SVM算法用于图像垃圾邮件过滤。实验结果表明,该方法能提高图像垃圾邮件的检测率。

关键词: 图像垃圾邮, 最小二乘支持向量机, 支持向量机, 分类特征

Abstract: This paper proposes uses gradient histogram and color histogram as classification feature to analyze the difference between Least Square-Support Vector Machine(LS-SVM) algorithm and Support Vector Machine(SVM) algorithm. It compares the LS-SVM algorithm with several traditional algorithms and introduces LS-SVM algorithm into image spam filtering. Experimental results show that the method can improve the detection rate of image spam.

Key words: image spam, Least Square-Support Vector Machine(LS-SVM), Support Vector Machine(SVM) classification feature

中图分类号: