结合分组联合字典的图像超分辨率重建  

Super-Resolution Reconstruction of Image Based on Grouping Joint Dictionary

作　　者：岳彦敏 刘丛[1] YUE Yan-min;LIU Cong(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《软件导刊》2021年第12期159-162,共4页Software Guide

基　　金：国家自然科学基金项目(61703278)。

摘　　要：为提高图像超分辨率重建质量,针对单一联合字典缺乏公共适用性问题,提出一种结合分组联合字典的超分辨率重建算法。首先,利用K-Means算法对训练样本进行分组,并用迭代软阈值算法得到分组联合字典,使每组样本不仅可以用其对应的子联合字典线性表示,还可被总的联合字典线性表示;其次,在重建过程中,低分辨率图像块根据其所属的类别来选择合适的分组联合字典,重建出对应的高分辨率图像块;最后,将重建出的高分辨率图像块整合得到高分辨率图像,并将其应用于遥感图像超分辨率重建。实验结果表明,该方法将遥感图像的峰值信噪比(PSNR)提升了约1.36dB,获得了较好的重建效果。In order to improve the quality of super-resolution reconstruction of remote sensing images,a super-resolution reconstruc⁃tion algorithm based on grouping joint dictionary is proposed in this paper,aiming at the shortcoming of single joint dictionary lacking common applicability.Firstly,the K-means algorithm is used to group the training samples,and an iterative soft threshold algorithm is used to get the grouping joint dictionary,so that each group of samples can not only be represented linearly by its corresponding sub joint dictionary,but also by the total joint dictionary.Secondly,in the process of reconstruction,the low-resolution image blocks can be reconstructed by selecting appropriate grouping joint dictionaries according to the categories they belong to.Finally,the reconstruct⁃ed high-resolution blocks are integrated to obtain high-resolution images,and it is applied to super-resolution reconstruction of remote sensing images.The experimental results show that this method can improve the peak signal-to-noise ratio(PSNR)of remote sensing images by about 1.36dB,and achieve better reconstruction effect.

关 键 词：超分辨率 分组联合字典 稀疏表示 遥感图像 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]