Share Email Print

Proceedings Paper

High-resolution remote sensing image automatic segmentation by Gabor texture feature
Author(s): Fang Xu; Qing He; Jiangqin Ma
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The paper presents an high-resolution Remote Sensing image segmentation method, which uses distributions of local binary patterns/contrasts (LBP/C) of Gabor texture features for measuring the similarity of adjacent image regions during the segmentation process. The method and algorithmic is integrated into split-merge plus refinement framework. The central rationale of the method is that automatically segmenting image into different regions corresponding to Gabor texture feature. In the procedure for split-merge and refinement, segmentation is realized by comparing correlation coefficient between different Gabor features LBP/C histogram of sub-regions. The image can be segmented into different regions that frequently correspond to different land-use or other objects. Experimental results show that it is effective to uses the Gabor texture features in high-resolution remote sensing image segmentation.

Paper Details

Date Published: 30 October 2009
PDF: 7 pages
Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953F (30 October 2009); doi: 10.1117/12.833940
Show Author Affiliations
Fang Xu, Wuhan Univ. (China)
Qing He, Wuhan Univ. (China)
Jiangqin Ma, Wuhan Univ. (China)

Published in SPIE Proceedings Vol. 7495:
MIPPR 2009: Automatic Target Recognition and Image Analysis
Tianxu Zhang; Bruce Hirsch; Zhiguo Cao; Hanqing Lu, Editor(s)

© SPIE. Terms of Use
Back to Top