Neural-fuzzy classification for segmentation of remotely sensed images

NCU Institutional Repository > 研究中心 > 太空及遙測研究中心 > 期刊論文 > Item 987654321/27683

請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/27683

題名:	Neural-fuzzy classification for segmentation of remotely sensed images
作者:	Chen,SW;Chen,CF;Chen,MS;Cherng,S;Fang,CY;Chang,KE
貢獻者:	太空及遙測研究中心
關鍵詞:	SENSING DATA;NETWORK;VALIDITY
日期:	1997
上傳時間:	2010-06-29 18:52:08 (UTC+8)
出版者:	中央大學
摘要:	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.
關聯:	IEEE TRANSACTIONS ON SIGNAL PROCESSING
顯示於類別:	[太空及遙測研究中心] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	579	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....