Share Email Print
cover

Proceedings Paper • new

A texture segmentation method for high resolution remote sensing images combining gray edge information
Author(s): Na Wang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A texture segmentation method for high resolution remote sensing image Combining gray edge information is proposed. Firstly, an initial segmentation strategy based on gray edge detection is proposed to segment the image initially. Then the texture features of the image are extracted by using the Gauss Markov random field model. In the feature space, the mean values of each class of features in the initial segmentation are obtained, and then the feature vectors are clustered as initial points to complete the segmentation. This method solves two drawbacks of the standard fuzzy C-means clustering algorithm in image segmentation: slow operation speed and large dependence on the initial value. The real remote sensing image is segmented by this algorithm. Experiments show that this method has faster speed and better stability.

Paper Details

Date Published: 27 November 2019
PDF: 5 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113210N (27 November 2019); doi: 10.1117/12.2542182
Show Author Affiliations
Na Wang, LiaoNing Construction Vocational College (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top