Remote sensing image segmentation based on a modified pulse coupled neural network

Sun Li; Nian Hua

doi:10.1117/12.2505168

12 December 2018 Remote sensing image segmentation based on a modified pulse coupled neural network

Sun Li, Nian Hua

Proceedings Volume 10846, Optical Sensing and Imaging Technologies and Applications; 108461S (2018) https://doi.org/10.1117/12.2505168
Event: International Symposium on Optoelectronic Technology and Application 2018, 2018, Beijing, China

Abstract

In order to adaptively adjust the model parameters and the global threshold for image segmentation, an improved pulse coupled neural network (PCNN) model based on human visual system (HVS) is proposed in this paper. Due to the property of HVS that human visual sensitivity to an image varies with different regions of the image where different regions correspond to different information rate area of the image, we analyze the characteristics of the improved model and its parameter optimization principle，and propose an improved segmentation algorithm. According to the gray scale of pixels, the algorithm adaptively realizes the division of the image information area. It not only preserves the excellent characteristics of PCNN for image segmentation, but also effectively preserves the gradation of image itself. The experiment results show that the algorithm proposed is efficient and has good segmentation effect, and has a wide application prospect in remote sensing image processing.

Citation Download Citation

Sun Li and Nian Hua "Remote sensing image segmentation based on a modified pulse coupled neural network", Proc. SPIE 10846, Optical Sensing and Imaging Technologies and Applications, 108461S (12 December 2018); https://doi.org/10.1117/12.2505168

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

Includes PDF, HTML & Video, when available