• Acta Optica Sinica
  • Vol. 38, Issue 8, 0815027 (2018)
Kebin Li1、2、*, Houyun Yu1、2、*, and Shenjiang Zhou1
Author Affiliations
  • 1 College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu 210016, China
  • 2 Wuxi Institute, Nanjing University of Aeronautics and Astronautics, Wuxi, Jiangsu 214187, China
  • show less
    DOI: 10.3788/AOS201838.0815027 Cite this Article Set citation alerts
    Kebin Li, Houyun Yu, Shenjiang Zhou. Surface Scratch Detection of Mechanical Parts Based on Morphological Features[J]. Acta Optica Sinica, 2018, 38(8): 0815027 Copy Citation Text show less
    Structural compositions of scratch defect detection system
    Fig. 1. Structural compositions of scratch defect detection system
    ROI images extracted under combination lighting mode. (a) Original image with low angle lighting; (b) original image with high angle lighting; (c) mask template; (d) ROI image
    Fig. 2. ROI images extracted under combination lighting mode. (a) Original image with low angle lighting; (b) original image with high angle lighting; (c) mask template; (d) ROI image
    Four kinds of morphological median filter kernels in different directions. (a) 0°; (b) 90°; (c) 45°; (d) 135°
    Fig. 3. Four kinds of morphological median filter kernels in different directions. (a) 0°; (b) 90°; (c) 45°; (d) 135°
    Background difference images for scratch extraction. (a) Background image by 13×13 median filter; (b) background image by morphological median filter; (c) background difference image by morphological median filter; (d) segmentation image of scratch binarization
    Fig. 4. Background difference images for scratch extraction. (a) Background image by 13×13 median filter; (b) background image by morphological median filter; (c) background difference image by morphological median filter; (d) segmentation image of scratch binarization
    Schematic of scratch region growing
    Fig. 5. Schematic of scratch region growing
    Result of scratch region growing
    Fig. 6. Result of scratch region growing
    Flow chart of scratch detection based on weighted fusion of multi-features
    Fig. 7. Flow chart of scratch detection based on weighted fusion of multi-features
    Scratch images extracted by different algorithms. (a) Gaussian filter; (b) median filter; (c) low-pass filter; (d) morphological median filter
    Fig. 8. Scratch images extracted by different algorithms. (a) Gaussian filter; (b) median filter; (c) low-pass filter; (d) morphological median filter
    Scratch extraction error images obtained by different algorithms. (a) Gaussian filter; (b) median filter; (c) low-pass filter; (d) morphological median filter
    Fig. 9. Scratch extraction error images obtained by different algorithms. (a) Gaussian filter; (b) median filter; (c) low-pass filter; (d) morphological median filter
    Experimental results of scratch detection
    Fig. 10. Experimental results of scratch detection
    Characteristic parameterNumber of false inspectionsNumber of missed inspectionsCorrect rate
    Area92273.5%
    Perimeter71382.9%
    Aspect ratio3593.2%
    Circularity4592.3%
    Rectangularity61284.6%
    Table 1. Scratch detection accuracy based on single feature
    Experimental algorithmImage size /(pixel×pixel)We/pixelEr
    Gaussian filter350×250112790.1289
    Median filter350×25047340.0541
    Low-pass filter350×250151730.1734
    Morphology median filter350×25012770.0146
    Table 2. Scratch extraction errors under different algorithms
    Detection methodNumber of false inspectionsNumber of missed inspectionsCorrect rateDetection time /s
    Top-hat6887.3%0.94
    Dual-threshold frequency domain differential3590.8%1.61
    Proposed method2595.7%1.21
    Table 3. Scratch detection results under different methods
    Kebin Li, Houyun Yu, Shenjiang Zhou. Surface Scratch Detection of Mechanical Parts Based on Morphological Features[J]. Acta Optica Sinica, 2018, 38(8): 0815027
    Download Citation