Image super resolution reconstruction algorithm based on generative countermeasure network

Guo-qi LIU; Jin-feng LIU; Dong-hui ZHU

doi:10.37188/CJLCD.2021-0227

您当前的位置：

首页 >

文章列表页 >

Image super resolution reconstruction algorithm based on generative countermeasure network

Image Processing | 更新时间：2021-12-10

- Image super resolution reconstruction algorithm based on generative countermeasure network
- Chinese Journal of Liquid Crystals and Displays Vol. 36, Issue 12, Pages: 1720-1727(2021)
- 作者机构：
  
  宁夏大学信息工程学院, 宁夏银川 750021
- 作者简介：
- 基金信息：
  
  Ningxia National Natural Science Foundation(2021AAC03084)
- DOI：10.37188/CJLCD.2021-0227
  CLC： TP391.4
- Received：01 September 2021，
  
  Revised：19 September 2021，
  
  Published：2021-12
- 稿件说明：
移动端阅览
Guo-qi LIU, Jin-feng LIU, Dong-hui ZHU. Image super resolution reconstruction algorithm based on generative countermeasure network[J]. Chinese journal of liquid crystals and displays, 2021, 36(12): 1720-1727.
DOI：

Guo-qi LIU, Jin-feng LIU, Dong-hui ZHU. Image super resolution reconstruction algorithm based on generative countermeasure network[J]. Chinese journal of liquid crystals and displays, 2021, 36(12): 1720-1727. DOI： 10.37188/CJLCD.2021-0227.

摘要

SRGAN是基于深度学习的图像超分辨率的典型方法，重建效果较好，但该算法还存在一些缺陷，在提高图像质量和运行速度上仍然有较大提升空间。本文在SRGAN网络模型的基础上提出了一个优化模型。因为批量归一化（BN）层在超分辨图像重建中常常会忽略一些图像的细节，同时增加网络的复杂度，所以在SRGAN的生成器中去除了BN层，并引入ECA通道注意力，使每个残差块生成特征图获得相应的权重，以便处理更多的图像细节。经过公开数据集的训练和对比实验，结果表明提出的改进模型相比于对比模型，重建图像的细节恢复更丰富，视觉效果更好，峰值信噪比和结构相似性表现更佳，模型总参数量更少。

Abstract

SRGAN is a typical method of image super-resolution based on deep learning

the reconstruction effect is good

but the algorithm still has some shortcomings

and there is still more room for improving the image quality and operation speed. An optimization model is proposed based on the SRGAN network model. Because the batch normalization (BN) layer often ignores some image details in super-resolution image reconstruction and increases the complexity of the network at the same time

the BN layer is removed from the generator of SRGAN and the ECA channel attention is introduced so that each residual block generating feature map gets a corresponding weight in order to process more image details. After training and comparison experiments on public datasets

the results show that the proposed improved model has richer image details recovery

better visual effects

better peak signal-to-noise ratio and structural similarity performance

and fewer total number of model parameters compared to the comparison model.

关键词

Keywords

references

邵洪禹 , 李英超 , 王超 , 等 . 超分辨望远光学系统像差影响及优化设计 . 中国光学 , 2020 . 13 ( 1 ): 106 - 120 . DOI: 10.3788/CO.20201301.0106 http://doi.org/10.3788/CO.20201301.0106 .

H Y SHAO , Y C LI , C WANG , 等 . Aberration effect and optimization design of super-resolution telescope optical system . Chinese Optics , 2020 . 13 ( 1 ): 106 - 120 . DOI: 10.3788/CO.20201301.0106 http://doi.org/10.3788/CO.20201301.0106 .

A KAPPELER , S YOO , Q Q DAI , 等 . Video super-resolution with convolutional neural networks . IEEE Transactions on Computational Imaging , 2016 . 2 ( 2 ): 109 - 122 . DOI: 10.1109/TCI.2016.2532323 http://doi.org/10.1109/TCI.2016.2532323 .

JADERBERG M, SIMONYAN K, ZISSERMAN A. Spatial transformer networks[C]// Proceedings of the 28 th International Conference on Neural Information Processing Systems . Montreal: ACM, 2015: 2017-2025.

IRANI M, PELEG S. Super resolution from image sequences[C]//10th International Conference on Pattern Recognition. Atlantic City: IEEE, 1990: 115-120.

H STARK , P OSKOUI . High-resolution image recovery from image-plane arrays, using convex projections . Journal of the Optical Society of America A , 1989 . 6 ( 11 ): 1715 - 1726 . DOI: 10.1364/JOSAA.6.001715 http://doi.org/10.1364/JOSAA.6.001715 .

赵秀影 , 苏耘 , 董艳芹 , 等 . 一种基于小波与双三次插值的CCD图像超分辨方法 . 计算机应用研究 , 2009 . 26 ( 6 ): 2365 - 2367 . DOI: 10.3969/j.issn.1001-3695.2009.06.110 http://doi.org/10.3969/j.issn.1001-3695.2009.06.110 .

X Y ZHAO , Y SU , Y Q DONG , 等 . Kind of super-resolution method of CCD image based on wavelet and bicubic interpolation . Application Research of Computers , 2009 . 26 ( 6 ): 2365 - 2367 . DOI: 10.3969/j.issn.1001-3695.2009.06.110 http://doi.org/10.3969/j.issn.1001-3695.2009.06.110 .

张永红 , 段东海 . 基于邻近均值图像插值的数字图像隐藏技术 . 微计算机应用 , 2009 . 30 ( 6 ): 39 - 42 . DOI: 10.3969/j.issn.2095-347X.2009.06.008 http://doi.org/10.3969/j.issn.2095-347X.2009.06.008 .

Y H ZHANG , D H DUAN . Digital image hiding technology based on neighbor mean image interpolation . Microcomputer Applications , 2009 . 30 ( 6 ): 39 - 42 . DOI: 10.3969/j.issn.2095-347X.2009.06.008 http://doi.org/10.3969/j.issn.2095-347X.2009.06.008 .

DONG C, LOY C C, HE K M, et al . Learning a deep convolutional network for image super-resolution[C]//13 th European Conference on Computer Vision . Zurich: Springer, 2014: 184-199.

KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas: IEEE, 2016: 1646-1654.

IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// Proceedings of the 32 nd International Conference on International Conference on Machine Learning . Lille: ACM, 2015: 448-456.

LIM B, SON S, KIM H, et al . Enhanced deep residual networks for single image super-resolution[C] // Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops . Honolulu: IEEE, 2017: 1132-1140.

LAI W S, HUANG J B, AHUJA N, et al . Deep Laplacian pyramid networks for fast and accurate super-resolution[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 5835-5843.

ZHANG Y L, TIAN Y P, KONG Y, et al . Residual dense network for image super-resolution[C]// Proceedings of the 2018 IEEE / CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City: IEEE, 2018: 2472-2481.

LEDIG C, THEIS L, HUSZÁR F, et al . Photo-realistic single image super-resolution using a generative adversarial network[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 105-114.

X W XU , J W WANG , B F ZHONG , 等 . Deep learning-based tool wear prediction and its application for machining process using multi-scale feature fusion and channel attention mechanism . Measurement , 2021 . 177 109254 DOI: 10.1016/j.measurement.2021.109254 http://doi.org/10.1016/j.measurement.2021.109254 .

WANG Q L, WU B G, ZHU P F, et al . ECA-Net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE / CVF Conference on Computer Vision and Pattern Recognition ( CVPR ). Seattle: IEEE, 2020: 11531-11539.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Correction of vignetting images based on Retinex-Net network model

Fourier ptychography based on multi-scale feature fusion network

Underwater image enhancement method based on improved conditions generate adversarial networks

Technical research of composite residual network in low illumination image enhancement

Related Author

LIU Guo-qi

LIU Jin-feng

ZHU Dong-hui

HUANG Dandan

WANG Fei

LIU Zhi

GAO Han

WANG Huiji

Related Institution

School of Information Engineering， Ningxia University

School of Electronic Information Engineering， Changchun University of Technology

Space Optoelectronics Technology National and Local Joint Engineering Research Center， Changchun University of Technology

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰