| 基于K2结构学习算法的多光谱影像贝叶斯网络分类器 |
| |
| 引用本文： | 陶建斌,舒宁,沈照庆.基于K2结构学习算法的多光谱影像贝叶斯网络分类器[J].地理空间信息,2009,7(2):15-18. |
| |
| 作者姓名： | 陶建斌 舒宁 沈照庆 |
| |
| 作者单位： | 武汉大学遥感信息丁程学院,湖北武汉,430079 |
| |
| 基金项目： | 国家重点基础研究发展规划(973计划) |
| |
| 摘 要： | 用基于启发式搜索的结构学习算法，学习得到多光谱影像的贝叶斯网络结构，分析了TM的波段（特征）间条件独立性假设的合理性，给出了贝叶斯推理中后验概率计算的公式，并通过和最大似然法对比试验分析了简单贝叶斯网络应用于多光谱影像分类的优势。
|
| 关 键 词： | 遥感 贝叶斯网络 结构学习 条件独立性假设 多光谱影像 分类 |
Bayesian Network Classifier for Multi-spectral Image Based on K2 Structure Learning Algorithm |
| |
| TAO Jianbin,SHU Ning,SHEN Zhaoqing.Bayesian Network Classifier for Multi-spectral Image Based on K2 Structure Learning Algorithm[J].Geospatial Information,2009,7(2):15-18. |
| |
| Authors: | TAO Jianbin SHU Ning SHEN Zhaoqing |
| |
| Institution: | School of Remote Sensing and Information Engineering;Wuhan University;Wuhan 430079;China |
| |
| Abstract: | From the structure learning methods of search heuristics, we constructed a Na ve Bayesian Network for the multi-spectral image. We proved that the hypothesis of conditional independence between TM bands was successful, and analyzed the feasibility of applying Na ve Bayesian Networks to the classification of multi-spectral image through experiment. |
| |
| Keywords: | remote sensing Bayesian networks structure learning hypothesis of conditional independence multi-spectral image classification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
