Advertisement

Super-Resolution Imaging Using Convolutional Neural Networks

  • Yingyi SunEmail author
  • Wenhua Xu
  • Jie Zhang
  • Jian Xiong
  • Guan Gui
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)

Abstract

Convolutional neural networks (CNN) have been applied to many classic problems in computer vision. This paper utilized CNNs to reconstruct super-resolution images from low-resolution images. To improve the performance of our model, four optimizations were added in the training process. After comparing the models with these four optimizations, Adam and RMSProp were found to achieve the optimal performance in peak signal to noise ratio (PSNR) and structural similarity index (SSIM). Considering both reconstruction accuracy and training speed, simulation results suggest that RMSProp optimization in the most scenarios.

Keywords

Super-resolution imaging Convolutional neural networks Gradient descent Adam RMSprop 

References

  1. 1.
    Dong C, Chen CL, He K, Tang X. Image Super-Resolution Using Deep Convolutional Networks. IEEE Trans Pattern Anal Mach Intell. 2016;38(2):295–307.CrossRefGoogle Scholar
  2. 2.
    J. Allebach and P. W. B. T.-I. C. on I. P. Wong 1996. Proceedings, “Edge-directed interpolation,” Int. Conf. Image Process., vol. 3, no. 3, pp. 707–710, 1996.Google Scholar
  3. 3.
    Li X, Orchard MT. New edge-directed interpolation. IEEE Trans Image Process. 2001;10(10):1521–7.CrossRefGoogle Scholar
  4. 4.
    Zhang L, Wu X. An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process. 2006;15(8):2226–38.CrossRefGoogle Scholar
  5. 5.
    Ouyang W, X. B. T.-I. I. C. on Wang CV. Joint deep learning for pedestrian detection. In: IEEE international conference on computer vision; 2014. p. 2056–63.Google Scholar
  6. 6.
    He K, Zhang X, Ren S, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell. 2015;37(9):1904–16.CrossRefGoogle Scholar
  7. 7.
    Krizhevsky A, Sutskever I, GEBT-IC on Hinton NIPS. ImageNet classification with deep convolutional neural networks. In: International conference on neural information processing systems; 2012. p. 1097–105.Google Scholar
  8. 8.
    Ouyang W, Zeng X, Wang X, Qiu S, Luo P, Tian Y, Li H, Yang S, Wang Z, Li H. DeepID-Net: deformable deep convolutional neural networks for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 2014;99:2403–12.Google Scholar
  9. 9.
    Sun Y, Wang X, Tang X. Deep learning face representation by joint identification-verification, vol. 27; 2014. p. 1988–96.Google Scholar
  10. 10.
    Nair V, GEBT-IC on IC on Hinton ML. Rectified linear units improve restricted boltzmann machines. In: International conference on international conference on machine learning; 2010, p. 807–14.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Yingyi Sun
    • 1
    Email author
  • Wenhua Xu
    • 1
  • Jie Zhang
    • 1
  • Jian Xiong
    • 1
  • Guan Gui
    • 1
  1. 1.College of Telecommunication and Information EngineeringNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations