A new approach for ME image restoration based on CNN

A new approach for image restoration by cellular neural network (CNN) is de veloped in this paper. Based on the statistical characteristics of Gibbs im age model and the analysis of maximum entropy (ME) image restoration, a rea sonable template for binary image restoration is proposed. To process multi level image, a multi-layer cellular neural network is employed and an exten sive algorithm for multilevel image restoration is proposed. The results of computer simulation prove the effectiveness of this approach and show that we can get the effective template of CNN for some special image questions if we apply the statistical characteristics of Gibbs image model and analys e the physical meaning of the questions. Copyright (C) 1999 John Wiley & So ns, Ltd.