資料探勘於曾文水庫集水區影像分類之研究

CHUR > College of Architecture and Design > Department of Civil Engineering > Seminar Papers > Item 987654321/26662

Please use this identifier to cite or link to this item: http://chur.chu.edu.tw/handle/987654321/26662

Title:	資料探勘於曾文水庫集水區影像分類之研究
Authors:	陳莉 Chen, Li
Contributors:	土木工程學系 Civil Engineering
Keywords:	資料探勘;影像分類;土地覆蓋判釋 data mining;land-cover;classification
Date:	2006
Issue Date:	2014-06-26 20:44:44 (UTC+8)
Abstract:	衛星影像配合分類理論在從事地面覆蓋或土使用之相關調查時，具有即時性、大範圍，及減省大量的人力和物力等特性。本研究即是以資料探勘方式進行曾文水庫集水區SPOT 衛星影像的分類作業，以對土地覆蓋進行判釋；所使用的分類理論包含類神經網路、決策樹，以及支持向量機等三種方式，結合影像分類特徵使用SPOT 影像中綠光、近紅外光及紅光波段值外，再從原有三波段內各別萃取出三種特徵值，分別為二階角動差、對比、熵，故共有十二個分類特徵以供分類。三種分類理論若以整體精度為評估對象，則以支持向量機及類神經網路的成果較 The image of the satellite cooperates with the categorized theory while engaged in the relevant investigation used in covering or land on the grounding. The main characteristics of remote sensing include wide cover and up-to-date. It is able to serve as a
Appears in Collections:	[Department of Civil Engineering] Seminar Papers

Files in This Item:

File	Description	Size	Format
s_230_0479.pdf		34Kb	Adobe PDF	129	View/Open