Neural-fuzzy classification for segmentation of remotely sensed images

NCUIR > Research Center > Center for Space and Remote Sensing Research > journal & Dissertation > Item 987654321/27683

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/27683

Title:	Neural-fuzzy classification for segmentation of remotely sensed images
Authors:	Chen,SW;Chen,CF;Chen,MS;Cherng,S;Fang,CY;Chang,KE
Contributors:	太空及遙測研究中心
Keywords:	SENSING DATA;NETWORK;VALIDITY
Date:	1997
Issue Date:	2010-06-29 18:52:08 (UTC+8)
Publisher:	中央大學
Abstract:	An unsupervised classification technique conceptualized in terms of neural and fuzzy disciplines for the segmentation of remotely sensed images is presented, The process consists of three major steps: 1) pattern transformation; 2) neural classification; 3) fuzzy grouping. In the first step, the multispectral patterns of image pixels are transformed into what we call coarse patterns, In the second step, a delicate classification of pixels is attained by applying an ART neural classifier to the transformed pixel patterns. Since the resultant clusters of pixels are usually too keen to be of practical significance, in the third step, a fuzzy clustering algorithm is invoked to integrate pixel clusters. A function for measuring clustering validity is defined with which the optimal number of classes can be automatically determined by the clustering algorithm, The proposed technique is applied to both synthetic and real images. High classification rates have been achieved far synthetic images. We also feel comfortable with the results of the real images because their spectral variances are even smaller than those of synthetic ones examined.
Relation:	IEEE TRANSACTIONS ON SIGNAL PROCESSING
Appears in Collections:	[Center for Space and Remote Sensing Research ] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	539	View/Open

社群 sharing

Loading...