期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：1998
卷号：XXXII Part 1
页码：113-118
出版社：Copernicus Publications
摘要：Three methods of fusing information from maximum liklihood and neural network methods for multispectraldata classification are discussed in this paper. The purpose of the fusion is to enhance the interpretation of apixel under study with the classifier that has a minimum uncertainity in assigning the pixel to one of desiredclasses. The classification performance with the fusion techniques is found to be superior to that of theindividual classifiers.
关键词：Hierarchial classification; Information Fusion; Neural Networks.
