NSST域下SPCNN与SR结合的多源图像融合  

Multi-source image fusion with SPCNN and SR based on image features

作　　者：张丽霞[1,2] 曾广平 宣兆成[1] ZHANG Li-xia;ZENG Guang-ping;XUAN Zhao-cheng(School of Information Technology Engineering,Tianjin University of Technology and Education,Tianjin 300222;School of Computer & Communication Engineering,University of Science and Technology Beijing,Beijing 100083,China)

机构地区：[1]天津职业技术师范大学信息技术工程学院,天津300222 [2]北京科技大学计算机与通信工程学院,北京100083

出　　处：《计算机工程与科学》2020年第11期2042-2049,共8页Computer Engineering & Science

基　　金：国家自然科学基金(11772228)。

摘　　要：为了凸显不同源图像的不同特征,提出了基于图像特征的参数自动设定的SPCNN模型。结合稀疏表示,提出了一种适合多源图像融合的方法。首先源图像经NSST变换分解为高频系数和低频系数。对高频系数利用图像固有特征自动设置参数的SPCNN模型实现点火,并依据点火总次数和加权融合规则完成融合。对低频系数采用稀疏表示实现融合。最后,通过逆NSST变换重构图像。实验结果表明,本文所提融合方法优于其他5种经典方法,融合图像符合人眼视觉感知系统,结构清晰,细节明显。In order to highlight the different features of different input images,a SPCNN model with automatic-setting parameter based on features is proposed,which is combined with sparse representation to fuse the multi-source images.The fusion process has four steps.Firstly,the source images are decomposed into high frequency coefficients and low frequency coefficient by NSST.Each high frequency coefficient is fired by the SPCNN model with automatic-set parameters based on the inherent characteristics,and the fused image is completed according to the total number of firing and the weighted fusion strategy.The low frequency coefficients are fused by a sparse representation.Finally,the fused image is reconstructed by inverse NSST.The experimental results show that the proposed method is superior to the other five classical methods and the fused image conforms to the human visual perception system,with clear structure and obvious details.

关 键 词：自适应参数SPCNN 稀疏表示 NSST 图像融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]