期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：2
页码：2632
DOI：10.15680/IJIRCCE.2017.0502189
出版社：S&S Publications
摘要：Remote sensing image processing is nowadays a mature research area. The techniques developed in thefield allow many real-life applications with great societal value. For instance, urban monitoring, fire detection or floodprediction, deforestation and crop monitoring, weather prediction, land use mapping, land cover mapping can have agreat impact on economical and environmental issues. It is universal known fact that satellites scan the images of earthsurface. But in practical it is impossible to verify manually all those images for the required region.Then it would betterto focus on those images that contain the required region. So there should be a method to identify the required regionlies within that particular image. In this paper, a simple method to extract regions of interest (ROI) from images isproposed using segmentation and classification techniques. Segmentation is achieved by using Mahalanobis Distanceand Classification is achieved by using support vector machines.
关键词：Remote sense image processing; Region of Interest; Mahalanobis Distance; Supervised Classification;Unsupervised Classification
