High Power Laser and Particle Beams, Volume. 34, Issue 6, 064002(2022)

Research on algorithm for restoration of large aperture and thick pinhole imaging based on neural network

Dong Li, Liang Sheng, Yang Li, and Baojun Duan
Author Affiliations
  • State Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, China
  • show less
    Figures & Tables(10)
    Thick pinhole simulation model
    Monte Carlo software results
    Diagram of DnCNN network structure
    Training results
    Wiener filter restoration result
    L-R algorithm restoration results
    10 mm aperture thick pinhole degraded image adds noise
    Neural network restoration results
    • Table 1. RMSE of test data

      View table
      View in Article

      Table 1. RMSE of test data

      aperture/mmaverage RMSE
      516.6067
      1030.4662
      1535.3384
    • Table 2. Comparison of average RMSE of test data

      View table
      View in Article

      Table 2. Comparison of average RMSE of test data

      aperture/mmaverage RMSE
      Wiener filteringLucy-Richardsonneural network
      注:加粗字体为每行最优值。
      546.654 648.316 816.781 9
      1048.873 650.161 231.144 2
      1550.613 450.845 536.294 7
    Tools

    Get Citation

    Copy Citation Text

    Dong Li, Liang Sheng, Yang Li, Baojun Duan. Research on algorithm for restoration of large aperture and thick pinhole imaging based on neural network[J]. High Power Laser and Particle Beams, 2022, 34(6): 064002

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Particle Beams and Accelerator Technology

    Received: Aug. 9, 2021

    Accepted: --

    Published Online: Jun. 2, 2022

    The Author Email:

    DOI:10.11884/HPLPB202234.210345

    Topics