基于空间数据挖掘的遥感图像处理  

Analyse of Remotely Sensed Imagery Base of Spatial Data Mining

作　　者：李社[1] 管太阳[1] 林子瑜[1] 

机构地区：[1]东华理工学院地球科学系,江西抚州344000

出　　处：《测绘与空间地理信息》2005年第5期84-87,共4页Geomatics & Spatial Information Technology

摘　　要：数据与数据库的爆炸式增长导致了一个十分突出的问题,即如何高效、智能地从巨量的、有噪音的、随机的数据中提取有效的、潜在有用的信息和知识。近几年来,空间数据挖掘技术的广泛研究正是基于此目的。本文初步探讨了空间数据挖掘技术在遥感图像处理中的应用,其重点阐述了关联规则,以及数据挖掘技术在遥感图像数据处理中的基本方法以及如何对遥感图像数据进行离散化处理。文章最后简要介绍了遥感图像处理的决策树和人工神经网络数据挖掘技术方法。Data mining and knowledge discovery from a large amount of image data such as remote sensing images has become highly required in recent years. The association rule discovery problem in particular has been widely studied. This paper presents preliminary discuss in using data mining techniques to find interesting multidimensional and quantitative association rule from remotely sensed data and study mainly base way of data mining of association rule in analyse of remotely sensed imagery. Finally, it discusses the data mining techniques, such as decision tree and artificial neural network.

关 键 词：空间数据挖掘 关联规则 APRIORI算法 遥感图像 决策树 

分 类 号：P208[天文地球—地图制图学与地理信息工程]