TEXTURE PROCESSING OF SYNTHETIC-APERTURE RADAR DATA USING 2ND-ORDER SPATIAL STATISTICS

Authors
ROTUNNO OC TREITZ PM SOULIS ED HOWARTH PJ KOUWEN N
Citation
Oc. Rotunno et al., TEXTURE PROCESSING OF SYNTHETIC-APERTURE RADAR DATA USING 2ND-ORDER SPATIAL STATISTICS, Computers & geosciences, 22(1), 1996, pp. 27-34
Citations number
29
Categorie Soggetti
Mathematical Method, Physical Science","Geosciences, Interdisciplinary","Computer Science Interdisciplinary Applications
Journal title
Computers & geosciences → ACNP
ISSN journal
00983004
Volume
22
Issue
1
Year of publication
1996
Pages
27 - 34
Database
ISI
SICI code
0098-3004(1996)22:1<27:TPOSRD>2.0.ZU;2-#
Abstract
A method is presented for generating second-order spatial statistics ( texture) from digital image data using the neighboring gray-level depe ndence matrix (NGLDM). Texture processing of a high-resolution airborn e synthetic aperture radar image in an agricultural environment improv ed crop classification over the raw data. Classification of the large- number emphasis feature, based on the NGLDM (window size = 11 x 11, al pha = 24 and beta = 1), showed a 30.5% improvement in validation accur acy over the tonal data.