Opto-Electronic Engineering, Volume. 49, Issue 5, 210371(2022)

Image segmentation learning method for large field single lens computational imaging system

Yinan Ji... Haifeng Li* and Xu Liu* |Show fewer author(s)
Author Affiliations
  • School of Opto-electronic Science and Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China
  • show less
    Figures & Tables(10)
    Amplification of PSF with different fields of view[18]. (a) PSF within about 10 degrees; (b) PSF about 10 degrees to 30 degrees; (c) PSF about 30 degrees to 53 degrees
    The concrete implementation process of the new idea(The red, blue and black boxes represent training, testing and the steps shared by them respectively, and the red, blue and black arrows represent training, testing and the processes shared by them respectively)
    Overall hardware system (sensors in the red box)
    Image shooting and registration process
    Sample of center partial dataset (shot image on the left, original image on the right)
    Sample of edge partial dataset (shot image on the left, original image on the right). The reasons for leaving holes in the middle are detailed in the following article
    Sample of test set after restoration, with two details highlighted in red boxes are listed below each image. (a) Ground truth images; (b) Blurred images; (c) Results obtained by means of Ref.[18]; (d) Results of our method
    Sample of real pictures after restoration, with a detail selected in a red box is listed above or below each image. (a) Blurred images; (b) Results obtained by means of literature [18]; (c) Results of our method
    • Table 1. Comparison of PSNR evaluation results

      View table
      View in Article

      Table 1. Comparison of PSNR evaluation results

      Peng et al.Our figure 1Our figure 2Our figure 3Our figure 4Our average
      PSNR/dB25.8922.5522.6426.5226.9424.66
    • Table 2. Comparison of SSIM evaluation results

      View table
      View in Article

      Table 2. Comparison of SSIM evaluation results

      Peng et al.Our figure 1Our figure 2Our figure 3Our figure 4Our average
      SSIM0.8600.9000.9100.9100.9400.915
    Tools

    Get Citation

    Copy Citation Text

    Yinan Ji, Haifeng Li, Xu Liu. Image segmentation learning method for large field single lens computational imaging system[J]. Opto-Electronic Engineering, 2022, 49(5): 210371

    Download Citation

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

    Category:

    Received: Nov. 22, 2021

    Accepted: --

    Published Online: Jun. 10, 2022

    The Author Email: Li Haifeng (;;;), Liu Xu (;;;)

    DOI:10.12086/oee.2022.210371

    Topics