影像增强对ISODATA遥感影像分类结果的影响  

The Influence of Image Enhancement on ISODATA Remote Sensing Image Classification

作　　者：杨燕[1] 曾学宏 汪生燕 

机构地区：[1]青海省基础地理信息中心,青海西宁810001 [2]青海省第一测绘院,青海西宁810001

出　　处：《测绘与空间地理信息》2014年第4期129-132,136,共5页Geomatics & Spatial Information Technology

摘　　要：ISODATA算法是遥感影像非监督分类的典型算法之一。在进行非监督分类前,需要对遥感影像进行必要的处理,影像增强就是其中最为重要的步骤之一。本文通过对ISODATA算法和影像增强算法的阐述,分析了影像增强算法与非监督分类结合的方式和局限性。并通过实验分析了常用影像增强算法对非监督分类结果的影响,科学合理的选择适当的影像增强算法来提高非监督分类的可靠性。ISODATA algorithm is one of the typical algorithms for remote sensing image unsupervised classification .Image enhance-ment is one of the necessary steps before making unsupervised classification of remote sensing images .This article elaborates the ISO-DATA algorithm and image enhancement algorithms , and analyzes the limitation of combination of image enhancement algorithms with unsupervised classification methods .Experimental analysis by using image enhancement before unsupervised classification is conduc -ted to make a scientific and rational selection of appropriate image enhancement algorithms to improve the reliability of unsupervised classification.

关 键 词：影像增强 ISODATA 分类结果 

分 类 号：P237[天文地球—摄影测量与遥感] TP75[天文地球—测绘科学与技术]