| 基于SVM的SAR图像分类研究 |
| |
| 引用本文： | 汤井田,胡丹,龚智敏.基于SVM的SAR图像分类研究[J].遥感技术与应用,2008,23(3):341-345. |
| |
| 作者姓名： | 汤井田 胡丹 龚智敏 |
| |
| 作者单位： | （1.中南大学信息物理工程学院,湖南 长沙 410083;;
2.武汉科技大学资源环境工程学院,湖北 武汉 430000） |
| |
| 摘 要： | 支持向量机（SVM）是一种卓越的分类方法,灰度共生矩阵（GLCM）则是一种很好的纹理分析方法，而纹理是合成孔径雷达（SAR）图像分类的一个重要特征，故而提出了一种使用灰度共生矩阵进行特征提取的应用支持向量的SAR图像分类法。实验结果证明了支持向量机算法的可行性和有效性。
|
| 关 键 词： | 支持向量机 灰度共生矩阵 特征提取 纹理分类 SAR图像 |
Study of Classification by Support Vector Machine on Synthetic Aperture Radar Image |
| |
| TANG Jing-tian,HU Dan,GONG Zhi-min.Study of Classification by Support Vector Machine on Synthetic Aperture Radar Image[J].Remote Sensing Technology and Application,2008,23(3):341-345. |
| |
| Authors: | TANG Jing-tian HU Dan GONG Zhi-min |
| |
| Affiliation: | (1.Physical Information Engineering College of Central South University,Changsha 410083,China;2.Environment and Resource College of Wuhan University of Science and Technology,Wuhan 410083,China) |
| |
| Abstract: | Support Vector Machine (SVM) has excellent performance in classification.The Gray Level Co-occurrence Matrix (GLCM) is a promising method for texture analysis.Texture is an important feature in Synthetic Aperture Radar (SAR) image.So the arithmetic of texture classification by SVM was investigated, using GLCM to extract features.Compared to the method using image's gray information directly for SVM classifying, the experimental results show the feasibility and effectiveness of the new method. |
| |
| Keywords: | nullzz |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《遥感技术与应用》浏览原始摘要信息 |
|
点击此处可从《遥感技术与应用》下载全文 |
