A Novel Method for L Band SAR Image Segmentation Based on Pulse Coupled Neural Network

Harwikarya Harwikarya (Universitas Mercu Buana)
Sabar Rudiarto (Universitas Mercu Buana)
Glorin Sebastian (Georgia Institute of Technology)

International Journal of Artificial Intelligence Research
Vol 4, No 2 (2020): December 2020

Pulse Coupled Neural Network (PCNN) is claimed as a third generation neural network. PCNN has wide purpose in image processing  such as segmentation, feature extraction, sharpening etc.  Not like another neural network architecture, PCNN do not need training. The only weaknes point  of PCNN is parameter tune due to  seven parameters in its five equations. In this research we proposed a novel method for segmentation based on modified PCNN.  In order to evaluate the proposed method, we processed L Band Multipolarisation  Synthetic Apperture Radar Image. The Results showed all area extracted both by using PCNN and ICM-PCNN from the SAR image are match to the groundtruth. There fore the proposed method is work properly.Copyright © 2017  International Journal of  Artificial Intelegence Research.All rights reserved.