Improved SRGAN Image Super-Resolution Reconstruction Algorithm
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [26]
  • | | | |
  • Comments
    Abstract:

    Image super-resolution reconstruction technology can improve image resolution, which plays an important role in medical, military and other fields. The traditional super-resolution generative adversarial network (SRGAN) algorithm for image super-resolution reconstruction has a slow training convergence speed, and excessive sharpening of high-frequency texture leads to distortion of some details, which affects the quality of reconstructed images. To address these problems, the generator network and loss function of the traditional SRGAN model are improved for image super-resolution reconstruction. The sparse residual dense network (SRDN) is used instead of the traditional SRResNet as the generator network to fully utilize low-resolution image features. Meanwhile, the sparse connection method of SRDN and the depthwise separable convolution are used to reduce the number of model parameters. In addition, a joint perceptual loss of fused the low-frequency features and high-frequency features of VGG is proposed to improve the network’s perceptual loss function by combining with the mean square error loss. Tested on the Set5, Set14, and BSD100 data sets, the results show that the improved SRGAN algorithm outperforms the traditional SRGAN algorithm in three evaluation indexes, namely, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and mean option score (MOS), and the details of the reconstructed images are clearer. The improved SRGAN algorithm shows better overall robustness and comprehensive performance.

    Reference
    [1] 穆瑞娟. 基于低秩稀疏分解和字典学习的图像超分辨率重建研究[硕士学位论文]. 济南: 山东师范大学, 2017.
    [2] Nasrollahi K, Moeslund TB. Super-resolution: A comprehensive survey. Machine Vision and Applications, 2014, 25(6): 1423–1468. [doi: 10.1007/s00138-014-0623-4
    [3] 胡熹. 基于第二代小波的图像超分辨率重建研究[硕士学位论文]. 武汉: 华中科技大学, 2009.
    [4] Peled S, Yeshurun Y. Superresolution in MRI: Application to human white matter fiber tract visualization by diffusion tensor imaging. Magnetic Resonance in Medicine, 2001, 45(1): 29–35. [doi: 10.1002/1522-2594(200101)45:1<29::AID-MRM1005>3.0.CO;2-Z
    [5] Thornton MW, Atkinson PM, Holland DA. Sub-pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super-resolution pixel-swapping. International Journal of Remote Sensing, 2006, 27(3): 473–491. [doi: 10.1080/01431160500207088
    [6] 唐艳秋, 潘泓, 朱亚平, 等. 图像超分辨率重建研究综述. 电子学报, 2020, 48(7): 1407–1420. [doi: 10.3969/j.issn.0372-2112.2020.07.022
    [7] 孙京, 袁强强, 李冀玮, 等. 亮度-梯度联合约束的车牌图像超分辨率重建. 中国图象图形学报, 2018, 23(6): 802–813. [doi: 10.11834/jig.170489
    [8] Zhang L, Wu XL. An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Transactions on Image Processing, 2006, 15(8): 2226–2238. [doi: 10.1109/TIP.2006.877407
    [9] 李泽鹏. 基于深度学习的超分辨率重建[硕士学位论文]. 南昌: 南昌大学, 2020.
    [10] Dong C, Loy CC, He KM, et al. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295–307. [doi: 10.1109/TPAMI.2015.2439281
    [11] Dong C, Loy CC, Tang XO. Accelerating the super-resolution convolutional neural network. Proceedings of the 14th European Conference on Computer Vision. Amsterdam: Springer, 2016. 391–407.
    [12] Tai Y, Yang J, Liu XM. Image super-resolution via deep recursive residual network. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 2790–2798.
    [13] Lai WS, Huang JB, Ahuja N, et al. Deep Laplacian pyramid networks for fast and accurate super-resolution. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 5835–5843.
    [14] Zhang YL, Tian YP, Kong Y, et al. Residual dense network for image super-resolution. Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 2472–2481.
    [15] Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge, MA: MIT Press, 2014. 2672–2680.
    [16] Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 105–114.
    [17] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations. San Diego, 2014.
    [18] Bevilacqua M, Roumy A, Guillemot C, et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. Proceedings of 2012 British Machine Vision Conference. Durham: BMVA Press, 2012. 135.1–135.10.
    [19] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations. Proceedings of the 7th International Conference on Curves and Surfaces. Avignon: Springer, 2010. 711–730.
    [20] 李诚, 张羽, 黄初华. 改进的生成对抗网络图像超分辨率重建. 计算机工程与应用, 2020, 56(4): 191–196. [doi: 10.3778/j.issn.1002-8331.1907-0055
    [21] Ma SJ, Liu WK, Cai W, et al. Lightweight deep residual cnn for fault diagnosis of rotating machinery based on depthwise separable convolutions. IEEE Access, 2019, 7: 57023–57036. [doi: 10.1109/ACCESS.2019.2912072
    [22] Wang XT, Yu K, Wu SX, et al. ESRGAN: Enhanced super-resolution generative adversarial networks. Proceedings of European Conference on Computer Vision. Munich: Springer, 2018. 63–79.
    [23] He KM, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016. 770–778.
    [24] Tong T, Li G, Liu XJ, et al. Image super-resolution using dense skip connections. Proceedings of 2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017. 4809–4817.
    [25] Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. Proceedings of the 13th European Conference on Computer Vision. Zurich: Springer, 2014. 818–833.
    [26] Timofte R, Gu SH, Wu JQ, et al. NTIRE 2018 challenge on single image super-resolution: Methods and results. Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City: IEEE. 2018. 965–96511.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

欧奕敏,魏朝勇,梁艳,江世杰.改进的SRGAN图像超分辨率重建算法.计算机系统应用,2022,31(4):196-203

Copy
Share
Article Metrics
  • Abstract:1052
  • PDF: 2578
  • HTML: 3000
  • Cited by: 0
History
  • Received:June 14,2021
  • Revised:July 07,2021
  • Online: March 22,2022
Article QR Code
You are the first992294Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063