摘要
图像融合是图像处理领域的重要分支。由于神经网络在图像特征提取和分类中优势显著,因此将神经网络技术应用于图像融合领域中也是近年来的研究热点。首先对基于浅层和深度神经网络的红外与可见光图像融合算法做出概述,并详细地介绍图像融合技术的研究进展,展示融合算法的研究成果。其次选取六种图像质量评价指标,对所述算法获得的融合图像进行客观评价,最后根据实验结果对未来的研究提出展望。
Image fusion is an important branch of image processing.Because neural network has obvious superiority in image feature extraction and classification,applying neural network technology to the field of image fusion is a research hot spot in recent years.Firstly,this paper summarizes the infrared and visible image fusion algorithms for shallow and deep neural networks,introduces the research progress of image fusion technology in detail,and shows the research results of fusion algorithms.Secondly,six image quality evaluation metrics are selected to objectively evaluate the fusion image obtained by these algorithms.Finally,the prospects for future research are proposed based on experimental results.
作者
王娟
柯聪
刘敏
熊炜
袁旭亮
丁畅
WANG Juan;KE Cong;LIU Min;XIONG Wei;YUAN Xuliang;DING Chang(Hubei Key Laboratory for High-fficiency Utilization of Solar Energy and Operation Control of Energy Storage System,Hubei University of Technology,Wuhan 430068,China;Post-Doctoral Research Workstation,Wuhan Huaan Science and Technology Co.,Ld.,Wuhan 430068,China)
出处
《激光杂志》
北大核心
2020年第7期7-12,共6页
Laser Journal
基金
国家自然科学基金(No.61901165)
湖北省自然科学基金项目(No.2019CFB530)。
关键词
图像融合
神经网络
评价指标
image fusion
neural network
evaluation metrics
作者简介
王娟(1983-),女,讲师,硕导,主要研究模式识别和智能系统。E-mail:happywj@hbut.edu.cn;通信作者:刘敏(1979-),女,副教授,硕导,主要研究图像处理。E-mail:463467853@qq.com。
