Expected Patch Log Likelihood Based on Multi-layer Prior Information Learning

  • ShunFeng WangEmail author
  • JiaCen Xie
  • YuHui Zheng
  • Tao Jiang
  • ShuHang Xue
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 474)


How to preserve the edge and texture details has been a difficult problem in image denoising. In this paper, we propose a multi-layer prior information learning method, which combines the statistical and geometric features of the image to describe the attributes of the prior information more accurately and completely. The experimental results show that our proposed method is superior to the EPLL (Expected patch log likelihood) method with a single statistical characteristic for a priori learning in both visual and quantitative evaluation.


Image denoising Image prior Expected patch log likelihood Statistical characteristic Geometric characteristic 


  1. 1.
    Wen, Y.W., Chan, R.H.: Parameter selection for total-variation-based image restoration using discrepancy principle. IEEE Trans. Image Process. 21, 1770–1781 (2012)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Peleg, T., Eldar, Y.C., Elad, M.: Exploiting statistical dependencies in sparse representations for signal recovery. IEEE Trans. Sig. Process. 60, 2286–2303 (2012)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Zoran D, Weiss Y.: From learning models of natural image patches to whole image restoration. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 479–486. IEEE (2011)Google Scholar
  4. 4.
    Yang, S., Wang, M., Chen, Y., et al.: Single-image super-resolution reconstruction via learned geometric dictionaries and clustered sparse coding. IEEE Trans. Image Process. 21(9), 4016 (2012). A Publication of the IEEE Signal Processing SocietyMathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • ShunFeng Wang
    • 1
    Email author
  • JiaCen Xie
    • 1
  • YuHui Zheng
    • 2
  • Tao Jiang
    • 1
  • ShuHang Xue
    • 3
  1. 1.College of Math and StatisticNanjing University of Information Science and TechnologyNanjingChina
  2. 2.College of Computer and SoftwareNanjing University of Information Science and TechnologyNanjingChina
  3. 3.College of Atmospheric SciencesNanjing University of Information Science and TechnologyNanjingChina

Personalised recommendations