Clustering analysis as a basic tool for hyperspectral remote sensing image

摘要：

Clustering analysis groups data objects based on information only found in the data that describes the objects and the relationships. As it is a spatial method, more research are focused on remote sensing application recently. This paper presents comparison of two classic cluster algorithms used in hyperspectral remote sensing image classification and the results showed that the classification of maximum likelihood algorithm is better than ISODATA algorithm.

关键词： clustering analysis hyperspectral remote sensing supervised/unsupervised classification

作者: Han Xu Xiaojuan Li Xiaowei Gao

作者单位: College of Resource Environment and Tourism, Capital Normal University,Beijing ImageInfo Co., LTD, Beijing

会议类型: 国际会议

会议名称: 第七届多光谱图象处理与模式识别国际学术会议

会议地点: 桂林

会议语种:英文

页码: 1-6

在线出版日期: 2011-11-01（万方平台首次上网日期，不代表论文的发表时间）