A New Image Process CNN

作     者：Zhuo Xinjian School of Information Engineering, Beijing University of Posts and,Telecommunications, Beijing,100876, China 

会议名称：《中国运筹学会第七届学术交流会》

会议日期：2004年

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

关 键 词：cellular neural network(CNN) bobustness translation 

摘      要：A set of cellular neural network (CNN) templates are proposed. ThisCNN can change each black pixel into thite and vice-versa, and translate the changedimages in each of 8 compass directions at the same time, respectively Robustnessanalysis gives template parameter inequalities which guarantee the correspondingCNN working well for performing prescribed tasks. Simulation examples are given.