| 基于影像多种特征的决策树分类方法 |
| |
| 引用本文： | 闫利,孙颖超.基于影像多种特征的决策树分类方法[J].地理空间信息,2009,7(6):15-17. |
| |
| 作者姓名： | 闫利 孙颖超 |
| |
| 作者单位： | 武汉大学,测绘学院,湖北,武汉,430079 |
| |
| 基金项目： | 国家863计划资助项目(2007AA12Z154) |
| |
| 摘 要： | 阐述了决策树分类CART算法原理,将纹理信息、NDVI指数引入决策树方法对影像进行分类,并将分类结果与最大似然分类结果进行比较,研究表明决策树分类方法相对传统分类方法总体精度提高了8.9148%,Kappa系数提高了0.1074。
|
| 关 键 词： | 图像分类 决策树 纹理 NDVI CART算法 |
Method for Decision-tree Classifier Using Multi-feature of Images |
| |
| YAN Li,SUN Yingchao.Method for Decision-tree Classifier Using Multi-feature of Images[J].Geospatial Information,2009,7(6):15-17. |
| |
| Authors: | YAN Li SUN Yingchao |
| |
| Institution: | School of Geodesy and Geomatics;Wuhan University;Wuhan 430079;China |
| |
| Abstract: | The paper discussed decision-tree classification principle and CART algorithm,introduced the texture information and NDVI index into decision-tree method to complete classification,and compared with the maximum likelihood classification results.Results show that the Decision-tree classification method improves the overall accuracy of 8.9048%,Kappa coefficient of 0.1074 inceased by comparision with traditional classification methods relatively. |
| |
| Keywords: | image classification decision-tree texture NDVI CART algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
