• Laser & Optoelectronics Progress
  • Vol. 57, Issue 10, 101022 (2020)
Piao Zhou1, Qiang Li1, Shuguang Zeng1、*, Sheng Zheng1, Yanshan Xiao1, Shaowei Zhang1, and Xiaolei Li2
Author Affiliations
  • 1College of Science, China Three Gorges University, Yichang, Hubei 443002, China
  • 2College of Electrical Engineering & Renewable Energy, China Three Gorges University, Yichang, Hubei 443002, China;
  • show less
    DOI: 10.3788/LOP57.101022 Cite this Article Set citation alerts
    Piao Zhou, Qiang Li, Shuguang Zeng, Sheng Zheng, Yanshan Xiao, Shaowei Zhang, Xiaolei Li. Surface Crack Detection Method for Ceramic Tile Based on Hessian Matrix Multi-Scale Filtering[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101022 Copy Citation Text show less
    Image of ceramic tile.(a) Typical ceramic tile crack image; (b) 3D image of surface gray distribution of a typical ceramic tile
    Fig. 1. Image of ceramic tile.(a) Typical ceramic tile crack image; (b) 3D image of surface gray distribution of a typical ceramic tile
    Multi-scale Hessian matrix filtering ceramic tile surface crack detection process
    Fig. 2. Multi-scale Hessian matrix filtering ceramic tile surface crack detection process
    Image multi-scale filtering. (a) Original image of crack area Iσ(σ=0); (b) spatial scale image Iσ(σ=1); (c) spatial scale image Iσ(σ=5); (d) spatial scale image Iσ(σ=10); (e) spatial scale image Iσ(σ=15); (f) spatial scale range image Iσ(σ=1)~Iσ(σ=15)
    Fig. 3. Image multi-scale filtering. (a) Original image of crack area Iσ(σ=0); (b) spatial scale image Iσ(σ=1); (c) spatial scale image Iσ(σ=5); (d) spatial scale image Iσ(σ=10); (e) spatial scale image Iσ(σ=15); (f) spatial scale range image Iσ(σ=1)~Iσ(σ=15)
    Test results of crack area defect. (a) Hessian crack enhancement image; (b) crack binarization image
    Fig. 4. Test results of crack area defect. (a) Hessian crack enhancement image; (b) crack binarization image
    Detection process of ceramic tile crack. (a) Red channel image of ceramic tile; (b) spatial scale range image Iσ(σ=1)~Iσ(σ=15); (c) Hessian crack enhancement image; (d) result of crack detection
    Fig. 5. Detection process of ceramic tile crack. (a) Red channel image of ceramic tile; (b) spatial scale range image Iσ(σ=1)~Iσ(σ=15); (c) Hessian crack enhancement image; (d) result of crack detection
    Test results of different algorithms. (a) Red channel image of ceramic tile; (b) method of Ref. [8]; (c) method of Ref. [9]; (d) method of Ref. [11]; (e) method of Ref. [21]; (f) method of Ref. [22]; (e) proposed method
    Fig. 6. Test results of different algorithms. (a) Red channel image of ceramic tile; (b) method of Ref. [8]; (c) method of Ref. [9]; (d) method of Ref. [11]; (e) method of Ref. [21]; (f) method of Ref. [22]; (e) proposed method
    AlgorithmNumber oferrorsAccuracy /%Time /s
    Method of Ref. [8]18820.6
    Method of Ref. [9]15854.3
    Method of Ref. [11]1189742.6
    Method of Ref. [21]24765.5
    Method of Ref. [22]20800.8
    Proposed method5952.9
    Table 1. Accuracy of detection by six algorithms
    Piao Zhou, Qiang Li, Shuguang Zeng, Sheng Zheng, Yanshan Xiao, Shaowei Zhang, Xiaolei Li. Surface Crack Detection Method for Ceramic Tile Based on Hessian Matrix Multi-Scale Filtering[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101022
    Download Citation