Non-saturated binary image learning and recognition using the ratio-memory cellular neural network (RMCNN)

Abstract

dIn this paper, cellular neural network with ratio memory is proposed for non-saturated binary image processing. The Hebbien learning rule will be used to learn the weight of template A. The RMCNN system can recognize one non-saturated binary image and remove most of the noise added to the image pattern during the recognition period. The behavior of recognizing non-saturated binary images will be proved by mathematics equations. The effect will be simulated by Matlab software. With the method for non-saturated binary image processing, this theory can be easily implemented in hardware.