基于颜色和边缘特征直方图的图像型垃圾邮件分类模型倡.pdf

文档介绍：第 27 卷第 7 .7
2010 年 7 月 Vol .2010No
Application Research puters Jul
基于颜色和边缘特征直方图的
图像型垃圾邮件分类模型倡
刘峤, 秦志光, 程红蓉, 钱伟中
(电子科技大学计算机科学与工程学院, 成都 610054)
摘要: 提出了一种新型的图像分类识别方法,该方法不依赖于对图像内容文字信息的提取,而是直接采用图
像的颜色信息和图形边缘特征来构造用于图像模式分类的统计模型。通过在公开数据集上的实验结果表明,提
出的模型对图像型垃圾邮件具有良好的分类能力,分类性能优于现有相关方法。由于该方法对图像型垃圾邮件
的分类准确率高,且不受图像文字识别干扰技术的影响,具有良好的应用前景。
关键词: 图像识别; 颜色直方图; 边缘特征; 图像型垃圾邮件分类
中图分类号: 文献标志码: 文章编号: 1001唱3695(2010)07唱2608唱03
TP A
: /. .
doi j issn
Image spam classification model based on color and edge histogram statistics
, 唱, 唱, 唱
LIU Qiao QIN Zhi guang CHENG Hong rong QIAN Wei zhong
( School puter Science Engineering, University of Electronic Science Technology of China, Chengdu 610054, China)
& &
Abstract: ,
This paper presented, a novel approach for image spam classification task which did not rely on text information唱
contained in the images but made use of the color. and edge features that could be extracted from image files directly to con
struct the statistical model. for pattern classification Experimental results on real public datasets, demonstrate good performance
of the proposed model. Since the approach is immune to content obscuring techniques it offers a promising alternative for
practical application
Key words: ; ; ;
image recognition color histogram edge histogram image spam classi