• Laser & Optoelectronics Progress
  • Vol. 57, Issue 20, 201020 (2020)
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/LOP57.201020 Cite this Article Set citation alerts
    Yong Chen, Jin Chen, Yapeng Ai, Meifeng Tao. Dunhuang Mural Inpainting Algorithm Based on Sequential Similarity Detection and Cuckoo Optimization[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201020 Copy Citation Text show less
    Schematic diagram of Criminisi algorithm
    Fig. 1. Schematic diagram of Criminisi algorithm
    Changes in various data during mural restoration. (a) Mask image; (b) change in confidence; (c) change in date item; (d) change in priority
    Fig. 2. Changes in various data during mural restoration. (a) Mask image; (b) change in confidence; (c) change in date item; (d) change in priority
    Restoration effect of images at each threshold. (a)Original image; (b)mask image; (c) Yth=10000; (d) Yth=5000; (e) Yth=2000; (f) Yth=1000; (g) Yth=500; (h) Yth=200; (i) Yth=50; (j) dynamic threshold of proposed method
    Fig. 3. Restoration effect of images at each threshold. (a)Original image; (b)mask image; (c) Yth=10000; (d) Yth=5000; (e) Yth=2000; (f) Yth=1000; (g) Yth=500; (h) Yth=200; (i) Yth=50; (j) dynamic threshold of proposed method
    Restoration results of mural 1. (a) Original image; (b) mask image; (c) traditional Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11] ; (f) proposed method; (g) enlarged restored area of traditional Criminisi method; (h) enlarged restored area of method in Ref.[9]; (i) enlarged restored area of method in Ref.[11];(j) enlarged restored area of proposed method
    Fig. 4. Restoration results of mural 1. (a) Original image; (b) mask image; (c) traditional Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11] ; (f) proposed method; (g) enlarged restored area of traditional Criminisi method; (h) enlarged restored area of method in Ref.[9]; (i) enlarged restored area of method in Ref.[11];(j) enlarged restored area of proposed method
    Restoration results of mural 2. (a) Original image; (b) mask image; (c) Criminisi method; (d) method in Ref.[9];(e) method in Ref.[11]; (f) proposed method
    Fig. 5. Restoration results of mural 2. (a) Original image; (b) mask image; (c) Criminisi method; (d) method in Ref.[9];(e) method in Ref.[11]; (f) proposed method
    Restoration results of mural 3. (a) Original image; (b) mask image; (c) Criminisi method; (d) method in Ref.[9];(e) method in Ref.[11]; (f) proposed method
    Fig. 6. Restoration results of mural 3. (a) Original image; (b) mask image; (c) Criminisi method; (d) method in Ref.[9];(e) method in Ref.[11]; (f) proposed method
    Restoration results of mural 4. (a) Original image; (b) mask image; (c) traditional Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11]; (f) proposed method; (g) enlarged restored area of traditional Criminisi method; (h) enlarged restored area of method in Ref.[9]; (i) enlarged restored area of method in Ref.[11]; (j) enlarged restored area of proposed method
    Fig. 7. Restoration results of mural 4. (a) Original image; (b) mask image; (c) traditional Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11]; (f) proposed method; (g) enlarged restored area of traditional Criminisi method; (h) enlarged restored area of method in Ref.[9]; (i) enlarged restored area of method in Ref.[11]; (j) enlarged restored area of proposed method
    Mural restoration results in large areas. (a) Original image; (b) mask image; (c) Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11]; (f) proposed method
    Fig. 8. Mural restoration results in large areas. (a) Original image; (b) mask image; (c) Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11]; (f) proposed method
    Mural restoration results in real damaged areas. (a) Original images; (b) mask images; (c) Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11]; (f) proposed method
    Fig. 9. Mural restoration results in real damaged areas. (a) Original images; (b) mask images; (c) Criminisi method; (d) method in Ref.[9]; (e) method in Ref.[11]; (f) proposed method
    MethodSSDA with fixed thresholdProposed method
    1000050002000100050020050
    PSNR /dB32.5633.7132.8233.7633.6932.2032.0936.68
    Time /s8.658.288.047.196.906.375.806.26
    Table 1. PSNR and time under different methods
    No.Mask imageCriminisi methodMethod in Ref.[9]Method in Ref.[11]Proposed method
    122.168632.877235.264235.925437.1888
    224.627133.001234.162833.095635.0714
    326.547637.144840.406739.214541.9898
    434.362540.327343.421641.862043.5608
    530.256837.298539.985638.756440.0258
    626.254530.169832.418332.421532.6986
    725.658930.589631.524430.989631.8652
    823.254629.325629.158929.362430.0526
    932.256839.542841.026940.156342.0024
    1021.235133.458534.562434.802434.8569
    Table 2. PSNR values of restoration results of each algorithmunit: dB
    No.Criminisi methodMethod in Ref.[9]Method in Ref.[11]Proposed method
    12664.5629395.1932557.4610346.5987541.3256322.7564376.2413284.8241
    Table 3. Restoration time of each algorithm unit: s
    Yong Chen, Jin Chen, Yapeng Ai, Meifeng Tao. Dunhuang Mural Inpainting Algorithm Based on Sequential Similarity Detection and Cuckoo Optimization[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201020
    Download Citation