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

Abstract

In this paper, cellular neural network with ratio memory is proposed for non-saturated binary image processing. The Hebbien leaming lule will be used to leam the weight oftemplate A. The RMCNN system can recognize one non-saNmted binary image and remove most ofthe noise added to the image pattem 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 sothare. With the method for non-SaNrated binarylmage processing, this theory can be easily implemented in hardware.