Laser & Optoelectronics Progress, Volume. 59, Issue 18, 1810011(2022)

Millimeter-Wave Radiation Image Deblurring Based on Residual Recursive Network

Guohao Xu, Yuanyuan Liu*, and Lu Zhu
Author Affiliations
  • School of Information Engineering, East China Jiaotong University, Nanchang 330013, Jangxi, China
  • show less
    Figures & Tables(11)
    RSRN structure
    Hierarchical blur extraction module structure
    Structure of encoder LE
    Internal structure of residual block (Res)
    Structure of decoder LD
    Internal structure of MSEB module
    Some millimeter wave radiation image samples in dataset
    Blur effect display
    Visual comparison
    • Table 1. Number of images in training set and test set

      View table

      Table 1. Number of images in training set and test set

      DatasetOriginal datasetPreprocessed dataset
      Number of images in training set29795958
      Number of images in test set330660
      Total number of images33096618
    • Table 2. Comparison of performance of different methods

      View table

      Table 2. Comparison of performance of different methods

      MethodPSNRSSIMParam /MB
      SRN[13]39.490.987383.76
      MTRNN[15]39.230.987372.64
      SIUN3235.770.9819124.5
      MPRNet3335.670.9800720.1
      Proposed method39.690.987742.56
    Tools

    Get Citation

    Copy Citation Text

    Guohao Xu, Yuanyuan Liu, Lu Zhu. Millimeter-Wave Radiation Image Deblurring Based on Residual Recursive Network[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1810011

    Download Citation

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

    Category: Image Processing

    Received: Jun. 9, 2021

    Accepted: Jul. 28, 2021

    Published Online: Aug. 22, 2022

    The Author Email: Liu Yuanyuan (lyy.78@163.com)

    DOI:10.3788/LOP202259.1810011

    Topics