Publication
Title
Hyperspectral image classification using non-subsampled shearlet transform
Author
Abstract
In this paper a new supervised classification method for hyperspectral image is introduced. In the proposed method first, 2D non-subsampled shearlet transform is applied to each spectral band of hyperspectral images. After that, minimum noise fraction transform reduces the dimension of shearlet coefficient sub-bands. Finally, the support vector machine is used for classifying the hyperspectral images based on the extracted features. In order to validate the efficiency of the proposed algorithm, two real hyperspectral image datasets are selected. The obtained classification results are compared with some of the state-of-the-art classification algorithms and the proposed method has reached the highest classification accuracy.
Language
English
Source (journal)
Proceedings of the Society of Photo-optical Instrumentation Engineers / SPIE: International Society for Optical Engineering. - Bellingham, Wash.
Source (book)
Conference on Image and Signal Processing for Remote Sensing XXIII, SEP 11-13, 2017, Warsaw, POLAND
Publication
Bellingham : Spie-int soc optical engineering , 2017
ISSN
0277-786X
ISBN
978-1-5106-1318-8
978-1-5106-1319-5
978-1-5106-1318-8
Volume/pages
10427 (2017) , 11 p.
Article Reference
104270K
ISI
000425842500015
Medium
E-only publicatie
Full text (Publisher's DOI)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identification
Creation 29.03.2018
Last edited 23.08.2021
To cite this reference