SAR image segmentation method based on SOM neural network algorithm

Jingjing Shen; Enliang Wang; Hao Chen; Hua Zhang; Ling Yao

doi:10.1117/12.2639898

19 October 2022 SAR image segmentation method based on SOM neural network algorithm

Jingjing Shen, Enliang Wang, Hao Chen, Hua Zhang, Ling Yao

Author Affiliations +

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 1229445 (2022) https://doi.org/10.1117/12.2639898
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

SAR (Synthetic Aperture Radar) has the characteristics of high resolution, all-weather and all-day, and has many applications in the fields of environment, resources and agriculture. Aiming at the first difficult step of analysis and processing in SAR images: SAR image segmentation technology, which has the disadvantages of complex background and large interference in different scenes, resulting in poor target image segmentation, a SAR image segmentation method based on SOM neural network algorithm is proposed, which is to first get the distance between two vectors by neural network algorithm, and then eliminate the interference and noise, and finally implemented by MATLAB simulation for images with different backgrounds, it is found that the SAR image segmentation method based on SOM neural network algorithm has progress and improvement in the accuracy and time consumption of segmented scenes compared with the traditional segmentation method.

Citation Download Citation

Jingjing Shen, Enliang Wang, Hao Chen, Hua Zhang, and Ling Yao "SAR image segmentation method based on SOM neural network algorithm", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 1229445 (19 October 2022); https://doi.org/10.1117/12.2639898

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE