期刊名称：International Journal of Electronics, Communication and Soft Computing Science and Engineering
印刷版ISSN：2277-9477
出版年度：2015
卷号：4
期号：Special 2
出版社：IJECSCSE
摘要：This paper presents a new framework for thedimensionality reduction in hyperspectral images. A fuzzy rough settheory is an approach that deals with the concepts of vagueness aswell as indiscernibility and finds the feature subsets preserving thesemantics of the given dataset. Therefore, the use of fuzzy rough setmethod to select the most significant spectral bands from thehyperspectral image is proposed in this paper. The objective of theproposed work is to reduce original bands to the most significantbands. Band reduction is performed on hyperspectral image usingfuzzy rough set feature selection. Experiments are carried out withreal hyperspectral images acquired by the National Aeronautics andSpace Administration Jet Propulsion Laboratory’s AirborneVisible/Infrared Imaging Spectrometer (AVIRIS) and ReflectiveOptics Spectrographic Imaging System (ROSIS).
