Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 57, Issue 22, 221015(2020)

Algorithm for Dunhuang Mural Inpainting Based on Gabor Transform and Group Sparse Representation

Yong Chen1,2、*, Meifeng Tao1, Yapeng Ai1, and Jin Chen1
Author Affiliations
  • 1School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, China
  • 2Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics & Image Processing, Lanzhou, Gansu 730070, China;
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (8)
    Equations (0)
    References (17)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(8)
    Schematic of structural group establishment

    Fig. 1. Schematic of structural group establishment

    Download full size
    Gabor characteristic maps obtained under 5 scales and 8 directions

    Fig. 2. Gabor characteristic maps obtained under 5 scales and 8 directions

    Download full size
    Comparison among mural inpainting results with random pixel missing. (a) Original image; (b) mural images with random pixel missing; (c) CDD algorithm; (d) algorithm in Ref.[11]; (e) algorithm in Ref.[12]; (f) proposed algorithm

    Fig. 3. Comparison among mural inpainting results with random pixel missing. (a) Original image; (b) mural images with random pixel missing; (c) CDD algorithm; (d) algorithm in Ref.[11]; (e) algorithm in Ref.[12]; (f) proposed algorithm

    Download full size
    Comparison among mural inpainting results with artificial scratch. (a) Original image; (b) image with artificial scratch ; (c) CDD algorithm; (d) Criminisi algorithm; (e) algorithm in Ref.[7]; (f) algorithm in Ref.[11]; (g) algorithm in Ref.[12]; (h) proposed algorithm; (i) local enlargement of repaired area using CDD algorithm; (j) local enlargement of repaired area using Criminisi algorithm; (k) local enlargement of repaired area using algorithm in Ref.[7]; (l) local enlargement of repaired ar

    Fig. 4. Comparison among mural inpainting results with artificial scratch. (a) Original image; (b) image with artificial scratch ; (c) CDD algorithm; (d) Criminisi algorithm; (e) algorithm in Ref.[7]; (f) algorithm in Ref.[11]; (g) algorithm in Ref.[12]; (h) proposed algorithm; (i) local enlargement of repaired area using CDD algorithm; (j) local enlargement of repaired area using Criminisi algorithm; (k) local enlargement of repaired area using algorithm in Ref.[7]; (l) local enlargement of repaired ar

    Download full size
    Comparison of mural inpainting results with real damage. (a) Original image; (b) mask image; (c) CDD algorithm; (d) Criminisi algorithm; (e) algorithm in Ref.[7]; (f) algorithm in Ref.[11]; (g) algorithm in Ref.[12]; (h) proposed algorithm

    Fig. 5. Comparison of mural inpainting results with real damage. (a) Original image; (b) mask image; (c) CDD algorithm; (d) Criminisi algorithm; (e) algorithm in Ref.[7]; (f) algorithm in Ref.[11]; (g) algorithm in Ref.[12]; (h) proposed algorithm

    Download full size
    Comparison of mural inpainting results with real damage. (a) Original image; (b) mask image; (c) CDD algorithm; (d) Criminisi algorithm; (e) algorithm in Ref.[7]; (f) algorithm in Ref.[11]; (g) algorithm in Ref.[12]; (h) proposed algorithm

    Fig. 6. Comparison of mural inpainting results with real damage. (a) Original image; (b) mask image; (c) CDD algorithm; (d) Criminisi algorithm; (e) algorithm in Ref.[7]; (f) algorithm in Ref.[11]; (g) algorithm in Ref.[12]; (h) proposed algorithm

    Download full size

    • Table 1. Comparison among mural inpainting results with random pixel missing

      View table

      Table 1. Comparison among mural inpainting results with random pixel missing

      Image No.CDD algorithmAlgorithm in Ref.[11]Algorithm in Ref.[12]Proposed algorithm
      PSNR /dBSSIMTime /sPSNR /dBSSIMTime /sPSNR /dBSSIMTime /sPSNR /dBSSIMTime /s
      121.5740.69026.28826.8180.761239.65424.6450.796800.47626.9180.921882.573
      224.2040.73626.55728.7130.752197.60127.8770.797794.77629.4810.847873.624
      321.9840.77125.82428.3330.808204.44226.0690.864792.75228.5970.905869.701

    • Table 2. Comparison among mural inpainting results with artificial scratch

      View table

      Table 2. Comparison among mural inpainting results with artificial scratch

      AlgorithmPSNR /dBSSIM
      CDD algorithm32.8490.972
      Criminisi algorithm30.1970.963
      Algorithm in Ref.[7]35.5250.980
      Algorithm in Ref.[11]35.0850.979
      Algorithm in Ref.[12]34.7540.978
      Proposed algorithm35.6490.985
    Tools

    Get Citation

    Copy Citation Text

    Yong Chen, Meifeng Tao, Yapeng Ai, Jin Chen. Algorithm for Dunhuang Mural Inpainting Based on Gabor Transform and Group Sparse Representation[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221015

    Download Citation

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

    Category: Image Processing

    Received: Mar. 19, 2020

    Accepted: Apr. 20, 2020

    Published Online: Oct. 27, 2020

    The Author Email: Yong Chen (edukeylab@126.com)

    DOI:10.3788/LOP57.221015

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology