• Acta Optica Sinica
  • Vol. 40, Issue 21, 2111001 (2020)
Ju Tang1、2、3, Kaiqiang Wang1、2、3, Wei Zhang1、2、3, Xiaoyan Wu4, Guodong Liu4, Jianglei Di1、2、3、*, and Jianlin Zhao1、2、3、**
Author Affiliations
  • 1School of Physical Science and Technology, Northwestern Polytechnical University, Xi'an, Shaanxi 710129, China
  • 2Shaanxi Key Laboratory of Optical Information Technology, Xi'an, Shaanxi 710129, China
  • 3Key Laboratory of Material Physics and Chemistry Under Extraordinary Conditions, Ministry of Education, Xi'an, Shaanxi 710129, China
  • 4Institute of Fluid Physics, China Academy of Engineering Physics, Mianyang, Sichuan 621900, China
  • show less
    DOI: 10.3788/AOS202040.2111001 Cite this Article Set citation alerts
    Ju Tang, Kaiqiang Wang, Wei Zhang, Xiaoyan Wu, Guodong Liu, Jianglei Di, Jianlin Zhao. Deep Learning Based Image Restoration Method of Optical Synthetic Aperture Imaging System[J]. Acta Optica Sinica, 2020, 40(21): 2111001 Copy Citation Text show less
    Imaging effect of optical synthetic aperture imaging system. (a) Original image; (b) image of synthetic aperture array distribution; (c) imaging map
    Fig. 1. Imaging effect of optical synthetic aperture imaging system. (a) Original image; (b) image of synthetic aperture array distribution; (c) imaging map
    Comparison of MTF between synthetic aperture system and its equivalent single aperture system. (a) Section curve of main peak of MTF; (b) diagram of MTF of synthetic aperture system; (c) diagram of MTF of equivalent single aperture system
    Fig. 2. Comparison of MTF between synthetic aperture system and its equivalent single aperture system. (a) Section curve of main peak of MTF; (b) diagram of MTF of synthetic aperture system; (c) diagram of MTF of equivalent single aperture system
    Restoration effect of blind deconvolution method. (a) Restoration maps of blind deconvolution method; (b) ringing phenomenon; (c) comparison of section gray curves
    Fig. 3. Restoration effect of blind deconvolution method. (a) Restoration maps of blind deconvolution method; (b) ringing phenomenon; (c) comparison of section gray curves
    Structure of U-net
    Fig. 4. Structure of U-net
    Comparison of recovery effects of U-net1 under different training datasets
    Fig. 5. Comparison of recovery effects of U-net1 under different training datasets
    Comparison of effects of different recovery methods. (a) Original images; (b) imaging maps; (c) images obtained by blind deconvolution; (d) images obtained by U-net2A; (e) images obtained by U-net2B
    Fig. 6. Comparison of effects of different recovery methods. (a) Original images; (b) imaging maps; (c) images obtained by blind deconvolution; (d) images obtained by U-net2A; (e) images obtained by U-net2B
    Experiment Experiment 1Experiment 2
    DatasetTrain set 1Test set 1Train set 2ATrain set 2BTest set 2
    Number of maps2-5005010001000300
    Number of map types1121010
    Corresponding networkU-net1(N)U-net2AU-net2BU-net2A, U-net2B
    Table 1. Correspondence table of different datasets and networks
    ParameterImaging mapRestoration map
    Blind deconvolutionU-net1
    (2)(5)(10)(50)(100)(250)(500)
    PSNR /dB16.5222.9919.6320.5122.2123.4323.3322.7322.99
    SSIM0.480.820.640.710.750.780.800.800.81
    Table 2. Average PSNR and SSIM of test set 1
    ParameterImaging mapRestoration map
    Blind deconvolutionU-net2AU-net2B
    PSNR /dB16.0821.8720.5122.21
    SSIM0.390.780.740.77
    Table 3. Average PSNR and SSIM of test set 2
    Ju Tang, Kaiqiang Wang, Wei Zhang, Xiaoyan Wu, Guodong Liu, Jianglei Di, Jianlin Zhao. Deep Learning Based Image Restoration Method of Optical Synthetic Aperture Imaging System[J]. Acta Optica Sinica, 2020, 40(21): 2111001
    Download Citation