[1]苏进胜,张明军,俞文静.一种基于融合的单幅图像超分辨率重建[J].计算机技术与发展,2022,32(05):53-57.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 009]
　SU Jin-sheng,ZHANG Ming-jun,YU Wen-jing.Single Image Super-resolution Reconstruction Based on Image Fusion[J].,2022,32(05):53-57.[doi:10. 3969 / j. issn. 1673-629X. 2022. 05. 009]
点击复制

一种基于融合的单幅图像超分辨率重建()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年05期
页码:
53-57
栏目:
图形与图像
出版日期:
2022-05-10

文章信息/Info

Title:
Single Image Super-resolution Reconstruction Based on Image Fusion
文章编号:
1673-629X(2022)05-0053-05
作者:
苏进胜; 张明军; 俞文静
广州软件学院 网络技术系,广东 广州 510990
Author(s):
SU Jin-sheng; ZHANG Ming-jun; YU Wen-jing
Dept. of Network Technology,Software Engineering Institute of Guangzhou,Guangzhou 510990,China
关键词:
超分辨率重建; 图像融合; 深度学习; 卷积神经网络; 生成对抗网络
Keywords:
super-resolution reconstruction; image fusion; deep learning; convolution neural network; generative adversarial network
分类号:
TP391. 41;TP183
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 05. 009
摘要:
图像超分辨率重建是由一幅或者多幅低分辨率图像序列重建与之对应的高分辨率图像。 高分辨率图像具有更高像素密度,可以提供更多的图像细节,这些细节往往在一些具体应用场景中起到关键性作用。 针对单幅低分辨率重建超分辨率应用问题,提出了一种基于图像融合的方法,该方法选取两种或者两种以上利用生成对抗网络算法进行超分辨率图像的重建算法,然后对它们各自重建的图像进行图像融合。 图像融合使用将两幅或多幅图像综合成一幅新的图像。 融合能利用两幅( 或多幅) 图像在时空上的相关性及信息上的互补性,可以使得融合后得到的图像对场景有更全面、清晰的描述,从而更有利于人眼的识别。 借鉴了集成学习的思想,该文使用 BasicSR、SRGAN 和 ESRGAN 这三种超分辨率重建算法生成的超分辨率图像进行两两交叉融合进行仿真实验。 实验结果表明,这种利用不同生成对抗网络重建的超分辨率图像进行融合简单有效,融合后的超分辨率图像质量在两个指标上 PSNR 和 SSIM 上总体优于融合前的图像质量。
Abstract:
Image super - resolution reconstruction is to reconstruct the corresponding high - resolution image from one or more low -resolution image sequences. High-resolution images have higher pixel density and can provide more image details,which often play a key role in some specific application scenarios. Aiming at the application of single - frame low - resolution reconstruction and super -resolution,we propose a method? based on image fusion. The respective reconstructed images are image fused. Image fusion uses the integration of two or more images into? ? ? ? a new image. Fusion can make use of the temporal and spatial correlation and information complementarity of two ( or more) images,which? ? ? can make the image obtained after fusion have a more comprehensive and clear description of the scene,which is more conducive to human? ? eye recognition. We draw on the idea of ensemble learning and use the super-resolution images generated by the three super-resolution reconstruction algorithms of Basic SR,SRGAN and ESRGAN to carry out two -by -two cross fusion for simulation experiments. The experimental results show that this kind of super-resolution image fusion reconstructed by different generation confrontation networks is simple and effective. The super - resolution image quality after fusion is generally better than the image quality before fusion in terms of PSNR and SSIM.

相似文献/References:

[1]冉柯柯 王继成.基于比值法图像拼接的等比例改进算法[J].计算机技术与发展,2010,(02):5.
　RAN Ke-ke,WANG Ji-cheng.An Improved Mosaic Algorithm Based on Ratio Matching Using Geometric Proportion[J].,2010,(05):5.
[2]杨亚 王铮 张素兰 郭飞飞.基于小波变换的多聚焦图像融合[J].计算机技术与发展,2010,(03):56.
　YANG Ya,WANG Zheng,ZHANG Su-lan,et al.Multi - focus Image Fusion Scheme Based on Wavelet Transform[J].,2010,(05):56.
[3]焦晶萍 廖文和 沈建新.一种基于模板匹配法的眼底图像拼接方法[J].计算机技术与发展,2010,(04):148.
　JIAO Jing-ping,LIAO Wen-he,SHEN Jian-xin.A Fundus Image Mosaic Method Based on Template Matching[J].,2010,(05):148.
[4]玄立超 谢亦才.一种新的基于Curvelet变换的遥感图像融合算法[J].计算机技术与发展,2009,(05):119.
　XUAN Li-chao,XIE Yi-cai.A New Remote Sensing Image Fusion Algorithm Based on Curvelet Transform[J].,2009,(05):119.
[5]田闯 刘文波.基于Curvelet变换多聚焦图像融合[J].计算机技术与发展,2008,(07):29.
　TIAN Chuang,LIU Wen-bo.Multifocus Image Fusion Using Curvelet Transform[J].,2008,(05):29.
[6]杨晓慧 朱秀阁.基于非下采样Contourlets的CT／MRI图像自适应融合[J].计算机技术与发展,2008,(12):116.
　YANG Xiao-hui,ZHU Xiu-ge.Adaptive CT/MRI Image Fusion Based on Nonsubsampled Contourlets[J].,2008,(05):116.
[7]刘凯峰 张德祥.基于小波变换区域方差的遥感图像融合新算法[J].计算机技术与发展,2007,(05):177.
　LIU Kai-feng,ZHANG De-xiang.A New Fusion Algorithm of Remote Sensing Image Based on Local Deviation of Wavelet Transform[J].,2007,(05):177.
[8]舒坚 胡茂林.空间频率图像的智能融合[J].计算机技术与发展,2006,(03):37.
　SHU Jian,HU Mao-lin.Intelligent Fusion of Image in Spatial Frequency[J].,2006,(05):37.
[9]王春霞 苏红旗 范郭亮.图像超分辨率重建技术综述[J].计算机技术与发展,2011,(05):124.
　WANG Chun-xia,SU Hong-qi,FAN Guo-liang.Overview on Super Resolution Image Reconstruction[J].,2011,(05):124.
[10]冯太平 闫仁武.基于非抽样Contourlet变换的多聚焦图像融合算法[J].计算机技术与发展,2012,(02):57.
　FENG Tai-ping,YAN Ren-wu.Multi-Focus Image Fusion Algorithm Based on Nonsubsampled Contourlet Transform[J].,2012,(05):57.

更新日期/Last Update: 2022-05-10