• Laser & Optoelectronics Progress
  • Vol. 58, Issue 24, 2410009 (2021)
Yong Chen*, Jin Chen, Yapeng Ai, and Meifeng Tao
Author Affiliations
  • School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu 730070, China
  • show less
    DOI: 10.3788/LOP202158.2410009 Cite this Article Set citation alerts
    Yong Chen, Jin Chen, Yapeng Ai, Meifeng Tao. Mural Image Inpainting Based on Edge Missing Reconstruction and Improved Priority[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2410009 Copy Citation Text show less
    Principle of the Criminisi algorithm
    Fig. 1. Principle of the Criminisi algorithm
    Images before and after edge fitting. (a) Image with edge missing; (b) image with edge fitting
    Fig. 2. Images before and after edge fitting. (a) Image with edge missing; (b) image with edge fitting
    Fitting process of the second-order Bézier curve
    Fig. 3. Fitting process of the second-order Bézier curve
    Schematic diagram of the second-order Bézier curve
    Fig. 4. Schematic diagram of the second-order Bézier curve
    Schematic diagram of Bézier curve fitting. (a) Curve before fitting; (b) curve after fitting
    Fig. 5. Schematic diagram of Bézier curve fitting. (a) Curve before fitting; (b) curve after fitting
    Edge fitting experiment of damaged murals. (a) Original image; (b) mask image; (c) manually selected control point 1; (d) manually selected control point 2; (e) our algorithm
    Fig. 6. Edge fitting experiment of damaged murals. (a) Original image; (b) mask image; (c) manually selected control point 1; (d) manually selected control point 2; (e) our algorithm
    Process of fusion to generate image to be repaired
    Fig. 7. Process of fusion to generate image to be repaired
    Repair results of different algorithms. (a) Original mural; (b) mask image; (c) Criminisi algorithm; (d) our algorithm
    Fig. 8. Repair results of different algorithms. (a) Original mural; (b) mask image; (c) Criminisi algorithm; (d) our algorithm
    Repair result of the real mural. (a) Original mural; (b) mask image; (c) Criminisi algorithm; (d) our algorithm; (e) local repair result of Criminisi algorithm; (f) local repair result of our algorithm
    Fig. 9. Repair result of the real mural. (a) Original mural; (b) mask image; (c) Criminisi algorithm; (d) our algorithm; (e) local repair result of Criminisi algorithm; (f) local repair result of our algorithm
    Repair results of different algorithms. (a) Original image; (b) mark image; (c) XTh = 2000; (d) XTh = 1000; (e) XTh = 500; (f) XTh = 300; (g) XTh = 200; (h) XTh =100; (i) XTh =50; (j) our algorithm
    Fig. 10. Repair results of different algorithms. (a) Original image; (b) mark image; (c) XTh = 2000; (d) XTh = 1000; (e) XTh = 500; (f) XTh = 300; (g) XTh = 200; (h) XTh =100; (i) XTh =50; (j) our algorithm
    Repair results of artificially damaged murals by different algorithms. (a) Original mural; (b) artificially damaged mask image; (c) Criminisi algorithm; (d) algorithm of Ref. [8]; (e) algorithm of Ref. [10]; (f) our algorithm
    Fig. 11. Repair results of artificially damaged murals by different algorithms. (a) Original mural; (b) artificially damaged mask image; (c) Criminisi algorithm; (d) algorithm of Ref. [8]; (e) algorithm of Ref. [10]; (f) our algorithm
    Repair result of the real broken mural. (a) Original mural; (b) mask image; (c) Criminisi algorithm; (d) algorithm of Ref. [8]; (e) algorithm of Ref. [10]; (f) our algorithm
    Fig. 12. Repair result of the real broken mural. (a) Original mural; (b) mask image; (c) Criminisi algorithm; (d) algorithm of Ref. [8]; (e) algorithm of Ref. [10]; (f) our algorithm
    MuralCriminisiRef. [8]Ref. [10]Ours
    134.7037.0437.6544.93
    237.3132.5234.9844.93
    332.9533.6532.5238.08
    441.1032.7629.7541.86
    529.3429.1130.0237.05
    Table 1. PSNR of image repaired by different algorithms unit: dB
    MuralCriminisiRef. [8]Ref. [10]Ours
    10.98700.98820.98770.9929
    20.98030.97770.98040.9830
    30.99120.99120.98600.9947
    40.98040.98110.97620.9849
    50.97850.98160.97960.9905
    Table 2. SSIM for image restoration with different algorithms
    Yong Chen, Jin Chen, Yapeng Ai, Meifeng Tao. Mural Image Inpainting Based on Edge Missing Reconstruction and Improved Priority[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2410009
    Download Citation