| 基于灰度—梯度共生矩阵的图像型垃圾邮件识别方法 |
| |
| 引用本文： | 冯兵,李芝棠,花广路.基于灰度—梯度共生矩阵的图像型垃圾邮件识别方法[J].通信学报,2013,34(Z2):1-3. |
| |
| 作者姓名： | 冯兵 李芝棠 花广路 |
| |
| 作者单位： | 1. 华中科技大学 计算机科学与技术学院，湖北 武汉 430074；2. 下一代互联网接入系统国家工程实验室，湖北 武汉 430074；
3. 华中科技大学 网络与计算中心, 湖北 武汉 430074 |
| |
| 摘 要： | 为了逃避基于文本的垃圾邮件系统的检测，越来越多的垃圾邮件制造者将文本信息嵌入到图像中。为了有效地检测出图像型垃圾邮件，提出了一种基于灰度—梯度共生矩阵(GGCM, gray-gradient co-occurrence matrix)的图像型垃圾邮件识别方法。先通过灰度—梯度共生矩阵提取图像的特征信息，然后运用最小二乘支持向量机（LS-SVM, least squares support vector machines）进行分类。实验表明，该方法具有较高的分类精度和较好的实时性。
|
| 关 键 词： | 图像型垃圾邮件 灰度—梯度共生矩阵 最小二乘支持向量机 纹理特征 |
| 收稿时间： | 9/6/2013 12:00:00 AM |
Image spam identification method based on
gray-gradient co-occurrence matrix |
| |
| Bing FENG,Zhi-tang LI,Gang-lu HUA.Image spam identification method based on
gray-gradient co-occurrence matrix[J].Journal on Communications,2013,34(Z2):1-3. |
| |
| Authors: | Bing FENG Zhi-tang LI Gang-lu HUA |
| |
| Affiliation: | 1. School of Computer Science and Technology,Huazhong University of Science and Technology,Wuhan 430074,China;2. National Engineering Laboratory for Next Generation Internet Access System,Wuhan 430074,China;3. Network and Computing Center,Huazhong University of Science and Technology,Wuhan 430074,China |
| |
| Abstract: | In order to avoid the detection of the spam system based on text,more and more spammers have embedded text information into the image.An image spam identification method based on gray-gradient co-occurrence matrix (GGCM) was proposed to detect image spam effectively.The feature of image was extracted through GGCM firstly,and then LS-SVM was used to do classification.The test results show that this method has higher classification accuracy and better real-time performance |
| |
| Keywords: | image spam gray-gradient co-occurrence matrix LS-SVM texture feature |
|
| 点击此处可从《通信学报》浏览原始摘要信息 |
|
点击此处可从《通信学报》下载全文 |
