| 基于对应分析的训练样本的选择 |
| |
| 引用本文： | 虞欣.基于对应分析的训练样本的选择[J].测绘科技情报,2007(2). |
| |
| 作者姓名： | 虞欣 |
| |
| 作者单位： | 武汉大学遥感信息工程学院 武汉市珞喻路129号，430079 |
| |
| 摘 要： | 本文提出一种基于对应分析的训练样本的选择方法。它从训练样本中自动地选择有代表性的典型训练样本,使得在自动分类中充分利用所采集的样本信息,以便得到满意的分类结果。通过实验与分析证明,该方法是可行的,它明显优于人工随机选择训练样本的方式。与基于Q型因子分析的训练样本选择方法相比,可以更快地得到较少的典型样本,满意的分类精度。
|
| 关 键 词： | 对应分析 因子分析 训练样本 影像分类 |
Selcection of Training Samples Based on Correspondence Analysis |
| |
| Authors: | YU Xin School of Remote Sensing and Information Engineering Wuhan University Luoyu Road Wuhan China |
| |
| Institution: | YU Xin School of Remote Sensing and Information Engineering,Wuhan University,129 Luoyu Road,Wuhan 430079,China |
| |
| Abstract: | In this paper,a new method about selction of training samples based on correspondence analysis is proposed,which can automatically select representative and integral training samples for capturing sufficient samples information and improve classification accuracy. The experimental results demonstrate its feasibility and it can cut down computational costs and outperforms than manual selection of training samples and the method based on Q-factor analysis. |
| |
| Keywords: | Correspondence analysis Factor Analysis Training samples Image classification |
| 本文献已被 CNKI 等数据库收录！ |
