• Laser & Optoelectronics Progress
  • Vol. 60, Issue 14, 1410014 (2023)
Huijuan Fu1, Xiaoqi Xi1, Yu Han1, Lei Li1, Xinguang Wang2, and Bin Yan1、*
Author Affiliations
  • 1College of Information System Engineering, Information Engineering University, Zhengzhou 450001, Henan, China
  • 2Henan Provincial Institute of Cultural Heritage and Archaeology, Zhengzhou 450001, Henan, China
  • show less
    DOI: 10.3788/LOP221785 Cite this Article Set citation alerts
    Huijuan Fu, Xiaoqi Xi, Yu Han, Lei Li, Xinguang Wang, Bin Yan. Micro-CT Image Denoising Algorithm Based on Deep Residual Encoding-Decoding[J]. Laser & Optoelectronics Progress, 2023, 60(14): 1410014 Copy Citation Text show less
    DRED-CNN structure
    Fig. 1. DRED-CNN structure
    Composition of convolution block and deconvolution block
    Fig. 2. Composition of convolution block and deconvolution block
    Residual learning network structure
    Fig. 3. Residual learning network structure
    Composition of lab-level micro-CT system
    Fig. 4. Composition of lab-level micro-CT system
    Denoising results of different methods for bronze coins
    Fig. 5. Denoising results of different methods for bronze coins
    Denoising results of different methods for bronze residual coins
    Fig. 6. Denoising results of different methods for bronze residual coins
    SOD /mmSDD /mmVoxel size /μmTube voltage /kVPower /WTime of exposure /s
    80.01200.0127.26140103.0/0.1
    Table 1. Scanning parameters for bronze coins
    MethodAverage PSNRAverage SSIM
    LDCT33.83350.9163
    BM3D34.14150.9508
    Multiscale-RED35.07930.9424
    RED-CNN35.89790.9644
    DRED-CNN38.86580.9745
    Table 2. Reconstruction quality evaluation of different methods for images
    Huijuan Fu, Xiaoqi Xi, Yu Han, Lei Li, Xinguang Wang, Bin Yan. Micro-CT Image Denoising Algorithm Based on Deep Residual Encoding-Decoding[J]. Laser & Optoelectronics Progress, 2023, 60(14): 1410014
    Download Citation