A simplified pulse-coupled neural network based sea-ice classifier with graphical interactive training
Juha Karvonen · 2002
The author has applied the pulse-coupled neural network (PCNN) for sea ice segmentation and classification. In this paper a simplified version of the PCNN, which is faster to execute and requires less memory, is used. Additionally, the author is using an on line training algorithm. During the interactive training phase, the users can adjust some parameters of the PCNN using a set of training images.