计算机科学 ›› 2020, Vol. 47 ›› Issue (9): 135-141.doi: 10.11896/jsjkx.190600146

• 计算机图形学&多媒体 • 上一篇    下一篇

基于残差字典及协作表达的单图像超分辨率算法

田旭1, 常侃1,2,3, 黄升1, 覃团发1,2,3   

  1. 1 广西大学计算机与电子信息学院 南宁530004
    2 广西大学广西多媒体通信与网络技术重点实验室 南宁530004
    3 广西大学广西高校多媒体通信与信息处理重点实验室 南宁530004
  • 收稿日期:2019-06-26 发布日期:2020-09-10
  • 通讯作者: 常侃(pandack0619@163.com)
  • 作者简介:tianxu775825@163.com
  • 基金资助:
    国家自然科学基金项目(61761005,61761007);广西自然科学基金项目(2016GXNSFAA380154)

Single Image Super-resolution Algorithm Using Residual Dictionary and Collaborative Representation

TIAN Xu1, CHANG Kan1,2,3, HUANG Sheng1, QIN Tuan-fa1,2,3   

  1. 1 School of Computer and Electronic Information,Guangxi University,Nanning 530004,China
    2 Guangxi Key Laboratory of Multimedia Communications and Network Technology,Guangxi University,Nanning 530004,China
    3 Guangxi Colleges and Universities Key Laboratory of Multimedia Communications and Information Processing,Guangxi University,Nanning 530004,China
  • Received:2019-06-26 Published:2020-09-10
  • About author:TIAN Xu,born in 1993,postgrduate.His main research interests includeima-ge super-resolution and image denoi-sing.
    CHANG Kan,born in 1983,Ph.D,associate professor,master’s supervisor,is a member of China Computer Federation.His main research interests include image and video processing and compressive sensing,and video coding,etc.
  • Supported by:
    The work was supported by the National Natural Science Foundation of China (61761005,61761007) and Natural Science Foundation of Guangxi Zhuang Autonomous Region (2016GXNSFAA380154).

摘要: 通过传统的单图像超分辨率(Super Resolution,SR)算法重建的高分辨率图像往往存在高频信息不足、边缘模糊的问题。为了提升重建图像的质量,提出了一种基于残差字典及协作表达的单图像SR算法(Residual Dictionary and Collaborative Representation,RDCR)。在训练环节,该算法结合字典学习及协作表达的思想,首先训练一个主字典及主投影矩阵,其次利用重建的样本图像训练多层残差字典及多层残差投影矩阵;在测试环节,通过逐层重建残差信息,得到不断精细化的高频信息,以提升重建的高分辨率图像的质量。通过实验证明,相比传统算法A+,所提算法在4倍上采样下的Set5及Set14图像集上可以分别获得0.20dB及0.18dB的峰值信噪比增益,在运算时间上所提算法与A+接近。

关键词: 超分辨率, 稀疏表示, 协作表达, 字典学习

Abstract: Usually,the traditional single image super resolution (SR) algorithms generate the high resolution (HR) images with insufficient high-frequency information and blurred edges.To improve the quality of the reconstructed HR images,this paper proposes a single image SR algorithm by using residual dictionary and collaborative representation(Residual Dictionary and Collaborative Representation,RDCR).In the training phase,firstly,based on the ideas of dictionary learning and collaborative representation,a main dictionary and the corresponding main projection matrices are learned.After that,the reconstructed image samples are utilized to train multiple layers of residual dictionaries and residual projection matrices.In the testing phase,high-frequency information is gradually refined by reconstructing the residual information layer by layer.Extensive experimental results show that,at a scale factor of 4,the average peak signal-to-noise ratio (PSNR) values obtained by the proposed method on Set5 and Set14 are 0.20dB and 0.18dB higher than the traditional method A+,respectively.And the running time of the proposed method is close to that of A+.

Key words: Collaborative representation, Dictionary learning, Sparse representation, Super resolution

中图分类号: 

  • TP751
[1] DONG W S,ZHANG L,SHI G M,et al.Image Deblurring and super resolution by adaptive sparse domain selection and adaptive regularization [J].IEEE Transactions on Image Processing,2011,20(7):1838-1857.
[2] DONG W S,ZHANG L,SHI G M,et al.Nonlocally centralized sparse representation for image restoration [J].IEEE Transactions on Image Processing,2013,22(4):1620-1630.
[3] REN C,HE X,PU Y,et al.Enhanced non-local total variation model and multi-directional feature prediction prior for single image super resolution [J].IEEE Transactions on Image Processing,2019,28(8):3778-3793.
[4] CHANG K,ZHANG X,DING P L K,et al.Data-adaptive low-rank modeling and external gradient prior for single image super-resolution [J].Signal Processing,2019,161:36-49.
[5] FREEMAN W T,JONES T R,PASZTOR E C.Example based super-resolution [J].IEEE Computer Graphics and Applications,2002,22(2):56-65.
[6] YANG J C,WRIGHT J,HUANG T,et al.Image super resolution via sparse representation [J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.
[7] ZEYDE R,ELAD M,PROTTER M.On single image scale-upusing sparse-representations[C]//International Conference on Curves and Surfaces.2010:711-730.
[8] TIMOFTE R,SMET V D,GOOL L V.Anchored neighborhood regression for fast example based super resolution[C]//International Conference on Computer Vision(ICCV).IEEE,2013:241-246.
[9] TIMOFTE R,SMET V D,GOOL L V.A+:adjusted anchored neighborhood regression for fast super resolution[C]//Asian Conference on Computer Vision (ACCV).IEEE,2014:111-126.
[10] TIMOFTE R,RASMUS R,GOOL L V.Seven ways to improve example based single image super resolution[C]//Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2016:375-379.
[11] ZHANG J,ZHAO C,XIONG R,et al.Image Super-Resolution via Dual-Dictionary Learning and Sparse Representation [C]//IEEE International Symposium on Circuits and Systems (ISCAS).2012:1688-1691.
[12] PAN Z X,YU J,XIAO C B,et al.Single Image Super Resolution Based on Adaptive Multi-Dictionary Learning [J].Acta Electronica Sinica,2015,43(2):209-216.
[13] WANG R G,LIU L L,YANG J,et al.Image super-resolution based on clustering and collaborative representation [J].Opto-Electronic Engineering,2018,45(4):9-18.
[14] QIU K,YI B S,XIANG M,et al.Collaborative Sparse Dictionary Learning for Reconstruction of Single Image Super Resolution [J].Acta Optica Sinica,2018,38(9):130-136.
[15] QING X J,SHAN Y Y,XIAO J J,et al.Self-Learning Single Image Super-resolution Reconstruction Based on Compressive Sensing and SVR [J].Computer Science,2017,44(11):169-174.
[16] HUANG J B,SINGH A,AHUJA N.Single image super-resolution from transformed self-exemplars[C]//Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2015:5197-5206.
[17] DONG C,LOY C C,HE K,et al.Image super-resolution using deep convolutional networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307.
[18] DONG C,LOY C C.Accelerating the super-resolution convolutional neural network[C]//European Conference on Computer Vision (ECCV).IEEE,2016:391-407.
[19] BEE L,SANGHYUM S,HEEWON K,et al.Enhanced deep residual networks for single image super-resolution[C]//Compu-ter Vision and Pattern Recognition Workshop (CVPRW).IEEE,2017:136-144.
[20] LI J,FANG F,MEI K,et al.Multi-scale residual network for image super-resolution[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:517-532.
[21] LIAN Y Y,WU X J.Research on Image Super-Resolution Reconstruction of Super Deep Convolutional Neural Network[J].Computer Engineering,2019,45(1):217-220.
[1] 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮.
基于DNGAN的磁共振图像超分辨率重建算法
Super-resolution Reconstruction of MRI Based on DNGAN
计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[2] 周颖, 常明新, 叶红, 张燕.
基于元迁移的太阳能电池板缺陷图像超分辨率重建方法
Super Resolution Reconstruction Method of Solar Panel Defect Images Based on Meta-transfer
计算机科学, 2022, 49(3): 185-191. https://doi.org/10.11896/jsjkx.210100234
[3] 陈贵强, 何军.
自然场景下遥感图像超分辨率重建算法研究
Study on Super-resolution Reconstruction Algorithm of Remote Sensing Images in Natural Scene
计算机科学, 2022, 49(2): 116-122. https://doi.org/10.11896/jsjkx.210700095
[4] 冷佳旭, 王佳, 莫梦竟成, 陈泰岳, 高新波.
基于深度学习的视频超分辨率重构进展综述
Survey on Video Super-resolution Based on Deep Learning
计算机科学, 2022, 49(2): 123-133. https://doi.org/10.11896/jsjkx.211000007
[5] 郭琳, 李晨, 陈晨, 赵睿, 范仕霖, 徐星雨.
基于通道注意递归残差网络的图像超分辨率重建
Image Super-resolution Reconstruction Using Recursive ResidualNetwork Based on ChannelAttention
计算机科学, 2021, 48(8): 139-144. https://doi.org/10.11896/jsjkx.200500150
[6] 周文辉, 石敏, 朱登明, 周军.
基于残差注意力网络的地震数据超分辨率方法
Seismic Data Super-resolution Method Based on Residual Attention Network
计算机科学, 2021, 48(8): 24-31. https://doi.org/10.11896/jsjkx.200900034
[7] 程松盛, 潘金山.
基于深度学习特征匹配的视频超分辨率方法
Video Super-resolution Method Based on Deep Learning Feature Warping
计算机科学, 2021, 48(7): 184-189. https://doi.org/10.11896/jsjkx.200800224
[8] 王伟, 胡涛, 李欣蔚, 沈思婉, 姜小明, 刘峻源.
白细胞图像超分辨率重建研究
Study on Super-resolution Image Reconstruction of Leukocytes
计算机科学, 2021, 48(4): 164-168. https://doi.org/10.11896/jsjkx.200100099
[9] 李培冠, 於志勇, 黄昉菀.
基于稀疏表示的电力负荷数据补全
Power Load Data Completion Based on Sparse Representation
计算机科学, 2021, 48(2): 128-133. https://doi.org/10.11896/jsjkx.191200152
[10] 陆要要, 袁家斌, 何珊, 王天星.
基于超分辨率重建的低质量视频人脸识别方法
Low-quality Video Face Recognition Method Based on Super-resolution Reconstruction
计算机科学, 2021, 48(11A): 295-302. https://doi.org/10.11896/jsjkx.201200159
[11] 谢海平, 李高源, 杨海涛, 赵洪利.
超分辨率重构遥感图像分类研究
Classification Research of Remote Sensing Image Based on Super Resolution Reconstruction
计算机科学, 2021, 48(11A): 424-428. https://doi.org/10.11896/jsjkx.210300132
[12] 刘遵雄, 朱成佳, 黄稷, 蔡体健.
多跳连接残差注意网络的图像超分辨率重建
Image Super-resolution by Residual Attention Network with Multi-skip Connection
计算机科学, 2021, 48(11): 258-267. https://doi.org/10.11896/jsjkx.201000033
[13] 张帆, 贺文琪, 姬红兵, 李丹萍, 王磊.
基于块对角化表示的多视角字典对学习
Multi-view Dictionary-pair Learning Based on Block-diagonal Representation
计算机科学, 2021, 48(1): 233-240. https://doi.org/10.11896/jsjkx.200800211
[14] 宋娅菲, 谌雨章, 沈君凤, 曾张帆.
基于改进残差网络的水下图像重建方法
Underwater Image Reconstruction Based on Improved Residual Network
计算机科学, 2020, 47(6A): 500-504. https://doi.org/10.11896/JsJkx.200100084
[15] 程哲, 白茜, 张浩, 王世普, 梁宇.
使用深层卷积神经网络提高Hi-C 数据分辨率
Improving Hi-C Data Resolution with Deep Convolutional Neural Networks
计算机科学, 2020, 47(6A): 70-74. https://doi.org/10.11896/JsJkx.190900065
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!