• Laser & Optoelectronics Progress
  • Vol. 59, Issue 18, 1810009 (2022)
Zhixun Zhu, Lei Zhao*, Heng Li, and Hairui Wang
Author Affiliations
  • Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, Yunnan , China
  • show less
    DOI: 10.3788/LOP202259.1810009 Cite this Article Set citation alerts
    Zhixun Zhu, Lei Zhao, Heng Li, Hairui Wang. Magnetic Tile Surface Defect Detection Algorithm Based on Improved Homomorphic Filtering and Canny Algorithm[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1810009 Copy Citation Text show less
    Structure chart of successive mean quantization transform
    Fig. 1. Structure chart of successive mean quantization transform
    Image comparison. (a) Original image; (b) enhanced image
    Fig. 2. Image comparison. (a) Original image; (b) enhanced image
    Flow chart of proposed algorithm
    Fig. 3. Flow chart of proposed algorithm
    Detection images of magnetic tile blowhole defect. (a) Original image; (b) Sobel; (c) proposed algorithm
    Fig. 4. Detection images of magnetic tile blowhole defect. (a) Original image; (b) Sobel; (c) proposed algorithm
    Detection images of magnetic tile surface defects. (a) Original images; (b) Sobel; (c) Canny; (d) OTSU; (e) literature [6]; (f) labeled defect; (g) proposed algorithm
    Fig. 5. Detection images of magnetic tile surface defects. (a) Original images; (b) Sobel; (c) Canny; (d) OTSU; (e) literature [6]; (f) labeled defect; (g) proposed algorithm
    Defect types of magnetic tileDetection methodDiceVOESA

    Blowhole defect

    of magnetic tile

    Sobel0.01281.8803-30.4196
    Canny0.00191.9748-155.5714
    OTSU0.00501.9883-337.5893
    Literature [60.00551.9871-306.4554
    Proposed algorithm0.88070.15640.8304

    Crack defect of

    magnetic tile

    Sobel0.03641.7756-14.8284
    Canny0.00891.9355-58.9851
    OTSU0.01181.9744-153.3321
    Literature [60.01201.9741-151.1530
    Proposed algorithm0.84400.09930.8955

    Fray defect of

    magnetic tile

    Sobel0.01831.65330.0949
    Canny0.13310.90090.3789
    OTSU0.61840.7502-0.2005
    Literature [60.62080.7448-0.1866
    Proposed algorithm0.95860.07590.9212

    Break defect of

    magnetic tile

    Sobel0.02710.42480.4606
    Canny0.04571.4359-4.0906
    OTSU0.06831.8632-26.2324
    Literature [60.06881.8622-26.0182
    Proposed algorithm0.94110.09660.9079
    Table 1. Comparison of test result parameters
    Detection methodDiceVOESA
    Sobel0.02371.4335-11.1731
    Canny0.04741.5618-54.5671
    OTSU0.17591.6440-129.3386
    Literature [60.17681.6421-120.9533
    Proposed algorithm0.90610.10710.8888
    Table 2. Comparison of parameters mean value
    Zhixun Zhu, Lei Zhao, Heng Li, Hairui Wang. Magnetic Tile Surface Defect Detection Algorithm Based on Improved Homomorphic Filtering and Canny Algorithm[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1810009
    Download Citation