杜晨杰1,
林辉品1, 2,,,
赖俊昇3,
胡小方4,
段书凯4
1.杭州电子科技大学电子信息学院 杭州 310018
2.浙江大学电气工程学院 杭州 310027
3.牛津大学工程科学系 英国牛津 OX1 3PJ
4.西南大学人工智能学院 重庆 400715
基金项目:国家自然科学基金(61571394, 61601376),浙江省属高校基本科研业务费项目(GK199900299012-010)
详细信息
作者简介:董哲康:男,1989年生,副教授,主要研究方向为忆阻理论、基于忆阻器的神经形态系统研究
杜晨杰:男,1990年生,博士生,研究方向为忆阻理论、基于忆阻器的神经形态系统研究
林辉品:男,1987年生,讲师,主要研究方向为忆阻理论、基于忆阻器的神经形态系统研究
赖俊昇:男,1991年生,助理教授,主要研究方向为忆阻理论、基于忆阻器的神经形态系统研究
胡小方:女,1984年生,副教授,主要研究方向为忆阻器理论、基于忆阻器的非线性系统研究
段书凯:男,1973年生,教授,主要研究方向为忆阻器理论、微纳系统研究
通讯作者:林辉品 linhuipin@hdu.edu.cn
中图分类号:TN601; TN911.73计量
文章访问数:4474
HTML全文浏览量:1134
PDF下载量:80
被引次数:0
出版历程
收稿日期:2019-11-01
修回日期:2020-01-12
网络出版日期:2020-02-12
刊出日期:2020-06-04
Multi-channel Memristive Pulse Coupled Neural Network Based Multi-frame Images Super-resolution Reconstruction Algorithm
Zhekang DONG1, 2,Chenjie DU1,
Huipin Lin1, 2,,,
Chun sing LAI3,
Xiaofang HU4,
Shukai DUAN4
1. School of Electronic Information, Hangzhou Dianzi University, Hangzhou 310018, China
2. College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
3. Department of Engineering Science, University of Oxford, Oxford OX1 3PJ, United Kingdom
4. College of Artificial Intelligence, Southwest University, Chongqing 400715, China
Funds:The National Natural Science Foundation of China (61571394, 61601376), The Fundamental Research Funds for the Provincial Universities (GK199900299012-010)
摘要
摘要:高清晰度的图像是信息获取和精确分析的前提,研究多帧图像的超分辨率重建能够有效解决因外部拍摄环境引起的图像细节丢失、边缘模糊等问题。该文基于纳米级忆阻器,设计一种多通道忆阻脉冲耦合神经网络模型(MMPCNN),能够有效模拟网络中连接系数的动态变化,解决神经网络中固有的参数估计问题。同时,将提出的网络应用于多帧图像超分辨率重建中,实现低分辨率配准图像的融合操作,并通过基于稀疏编码的单帧图像超分辨率重构算法对获得的初始高分辨率图像进行优化。最终,一系列计算机仿真及分析(主观/客观分析)验证了该文提出方案的正确性和有效性。
关键词:忆阻器/
脉冲耦合神经网络/
多帧图像/
超分辨率重建
Abstract:The high-resolution image is the prerequisite of information acquisition and precise analysis. Multi-frame super-resolution images reconstruction technologies are able to address many image degraded issues (caused by external shooting environment), such as detail information lost, blurred edges, and so forth. According to the nanoscale memristor, a Multi-channel Memristive Pulse Coupled Neural Network (MMPCNN) model is proposed. This model is able to simulate the adaptive-variable linking coefficient in pulse coupled neural network. Meanwhile, the proposed network is applied to the multi-frame super resolution reconstruction for fusing the registered low resolution images. Furthermore, the sparse coding based super resolution method is performed to improve the original high-resolution image. Finally, a series of computer experiments and the relevant subjective/objective analysis jointly illustrate the validity and effectiveness of the entire scheme.
Key words:Memristor/
Pulse coupled neural network/
Multi-frame images/
Super-resolution reconstruction
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=d722128a-1899-4662-88dd-aea86e80611b