Memristive network-based genetic algorithm and its application to image edge detection  

作　　者：YU Yongbin YANG Chenyu DENG Quanxin NYIMA Tashi LIANG Shouyi ZHOU Chen 

机构地区：[1]School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu 610054,China [2]School of Information Science and Technology,Tibet University,Lhasa 850000,China [3]Department of Economics,Stony Brook University,New York 11794,U.S.

出　　处：《Journal of Systems Engineering and Electronics》2021年第5期1062-1070,共9页系统工程与电子技术（英文版）

基　　金：This work was supported by the National Natural Science Foundation of China(61550110248);the Sichuan Science and Technology Department project(2019YFG0190);the University of Electronic Science and Technology of China project(H04W170186).

摘　　要：This paper proposes a mem-computing model of memristive network-based genetic algorithm(MNGA)by building up the relationship between the memristive network(MN)and the genetic algorithm(GA),and a new edge detection algorithm where image pixels are defined as individuals of population.First,the computing model of MNGA is designed to perform mem-computing,which brings new possibility of the hardware implementation of GA.Secondly,MNGA-based edge detection integrating image filter and GA operator deployed by MN is proposed.Finally,simulation results demonstrate that the figure of merit(FoM)of our model is better than the latest memristor-based swarm intelligence.In summary,a new way is found to build proper matching of memristor to GA and aid image edge detection.

关 键 词：memristive network(MN) genetic algorithm(GA) edge detection mem-computing 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]