Paper
27 November 2019 A texture segmentation method for high resolution remote sensing images combining gray edge information
Author Affiliations +
Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113210N (2019) https://doi.org/10.1117/12.2542182
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China
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.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Na Wang "A texture segmentation method for high resolution remote sensing images combining gray edge information", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113210N (27 November 2019); https://doi.org/10.1117/12.2542182
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Remote sensing

Edge detection

Fuzzy logic

Image resolution

Image processing algorithms and systems

Image processing

Back to Top