• Acta Optica Sinica
  • Vol. 39, Issue 1, 0115002 (2019)
Xing Tong*, Danhua Cao**, Yubin Wu, and Xingru Jiang
Author Affiliations
  • School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China
  • show less
    DOI: 10.3788/AOS201939.0115002 Cite this Article Set citation alerts
    Xing Tong, Danhua Cao, Yubin Wu, Xingru Jiang. Button Defect-Free Image Reconstruction and Defect Detection Algorithm Based on Low-Rank Information[J]. Acta Optica Sinica, 2019, 39(1): 0115002 Copy Citation Text show less
    Block diagram of defect detection algorithm
    Fig. 1. Block diagram of defect detection algorithm
    Flow chart of image preprocessing and its effect
    Fig. 2. Flow chart of image preprocessing and its effect
    Button defect-free image reconstruction and residual image with defects. (a) Original image; (b) defect-free image; (c) residual image
    Fig. 3. Button defect-free image reconstruction and residual image with defects. (a) Original image; (b) defect-free image; (c) residual image
    Pixel value distribution of original and residual images. (a) Original image; (b) residual image
    Fig. 4. Pixel value distribution of original and residual images. (a) Original image; (b) residual image
    (a) Residual image; (b) binary image
    Fig. 5. (a) Residual image; (b) binary image
    Result diagrams of different defection methods. (a1)-(a3) Original images of three samples; (b1)-(b3) results by background substraction method; (c1)-(c3) results by linear regression method; (d1)-(d3) results by proposed method
    Fig. 6. Result diagrams of different defection methods. (a1)-(a3) Original images of three samples; (b1)-(b3) results by background substraction method; (c1)-(c3) results by linear regression method; (d1)-(d3) results by proposed method
    ROC curves by proposed method
    Fig. 7. ROC curves by proposed method
    Effect of different parameter C on detection effect. (a) Original image; (b) detection effect at C=1; (c) detection effect at C=3; (d) detection effect at C=6
    Fig. 8. Effect of different parameter C on detection effect. (a) Original image; (b) detection effect at C=1; (c) detection effect at C=3; (d) detection effect at C=6
    Recognition rate of algorithm versus illumination
    Fig. 9. Recognition rate of algorithm versus illumination
    Sample No.Number ofdefect-free buttonsNumber ofdefective buttonsSize /pixel×pixel
    1200110256×256
    2132128152×152
    313288169×169
    Table 1. Detail information of test samples
    Sample No.Subtraction methodLinear regression methodProposed method
    TPRTNRRTPRTNRRTPRTNRR
    10.8050.8550.8230.9350.8270.8971.0000.9550.976
    20.7310.5940.640.9810.8750.9100.9810.9060.944
    30.9090.7050.830.9441.0000.96520.9861.0000.990
    Table 2. Results by different methods
    Lighting condition No.12345
    Light source output value150155160165170
    Actual light intensity /lx51006400750086009800
    Table 3. Correspondence between light source scale and actual light intensity
    Xing Tong, Danhua Cao, Yubin Wu, Xingru Jiang. Button Defect-Free Image Reconstruction and Defect Detection Algorithm Based on Low-Rank Information[J]. Acta Optica Sinica, 2019, 39(1): 0115002
    Download Citation