Integration of Segmentation Techniques for Classification of Hyperspectral Images

Benediktsson, Jon Atli; Ghamisi, Pedram; Couceiro, Micael S.; Fauvel, Mathieu

Opin vísindi
→
Háskóli Íslands
→
Greinar- HÍ
→
View Item

Integration of Segmentation Techniques for Classification of Hyperspectral Images

Title:	Integration of Segmentation Techniques for Classification of Hyperspectral Images
Author:	Benediktsson, Jon Atli orcid.org/0000-0003-0621-9647 Ghamisi, Pedram Couceiro, Micael S. Fauvel, Mathieu 4 authors Show fewer authors
Date:	2014
Language:	English
Scope:	342-346
University/Institute:	Háskóli Íslands University of Iceland
School:	Verkfræði- og náttúruvísindasvið (HÍ) School of Engineering and Natural Sciences (UI)
Department:	Rafmagns- og tölvuverkfræðideild (HÍ) Faculty of Electrical and Computer Engineering (UI)
Series:	IEEE Geoscience and Remote Sensing Letters; 11(1)
ISSN:	1545-598X
DOI:	10.1109/LGRS.2013.2257675
Subject:	Support vector machines; Geophysical image processing; Hyperspectral imaging; Image classification
URI:	https://hdl.handle.net/20.500.11815/138
Show full item record
Citation: P. Ghamisi, M. S. Couceiro, M. Fauvel and J. A. Benediktsson. (2014). Integration of Segmentation Techniques for Classification of Hyperspectral Images. IEEE Geoscience and Remote Sensing Letters, 11(1), 342-346
Abstract: A new spectral-spatial method for classification of hyperspectral images is introduced. The proposed approach is based on two segmentation methods, fractional-order Darwinian particle swarm optimization and mean shift segmentation. The output of these two methods is classified by support vector machines. Experimental results indicate that the integration of the two segmentation methods can overcome the drawbacks of each other and increase the overall accuracy in classification.
Rights: (c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works