• Journal of Applied Optics
  • Vol. 44, Issue 3, 677 (2023)
Jinyao HOU1, Weiguo LIU1,*, Shun ZHOU1, Aihua GAO1..., Shaobo GE1 and Xiangguo XIAO2|Show fewer author(s)
Author Affiliations
  • 1College of Photoelectric Engineering, Xi'an Technological University, Xi'an 710021, China
  • 2Xi'an Institute of Applied Optics, Xi'an 710065, China
  • show less
    DOI: 10.5768/JAO202344.0305003 Cite this Article
    Jinyao HOU, Weiguo LIU, Shun ZHOU, Aihua GAO, Shaobo GE, Xiangguo XIAO. Image classification of optical element surface defects based on convolutional neural network[J]. Journal of Applied Optics, 2023, 44(3): 677 Copy Citation Text show less
    Surface defect images
    Fig. 1. Surface defect images
    MER model of surface defects
    Fig. 2. MER model of surface defects
    Classification flow chart of surface defect images of optical elements
    Fig. 3. Classification flow chart of surface defect images of optical elements
    Establishment of dataset for surface defect images
    Fig. 4. Establishment of dataset for surface defect images
    AlexNet network model
    Fig. 5. AlexNet network model
    Asymmetric convolution process
    Fig. 6. Asymmetric convolution process
    Proposed network structure
    Fig. 7. Proposed network structure
    表面缺陷长轴/pixel短轴/pixel面积/pixel2外接矩形面积/pixel2长宽比矩形度P
    1114114
    2114114
    11318332.67
    12228412
    13321061.51.67
    168648501.330.96
    179856721.130.78
    1811.267.736987.071.460.79
    1910.299.8478101.201.050.77
    2032.6531.7588104.281.030.84
    2687.7428.8713762 532.953.10.54
    Table 1. Feature extraction of surface defects
    模型模型总参数
    Alexnet58 271 811
    Alexnet+AC54 405 027
    Table 2. Comparison of network model parameters before and after improvement
    表面缺陷ScratchDigNoisy
    准确率10099.7597.4
    Table 3. Identification results of proposed network%
    Model灵敏度/%特异性/%精确性/%运行时间/s
    VGG1669.3991.2096.4081.1
    InceptionV371.7492.2997.1279.35
    ResNet5073.8794.1797.3278.56
    AlexNet77.2092.3497.2018.54
    Ours89.9796.7399.0518.46
    Table 4. Model comparison experiments
    Jinyao HOU, Weiguo LIU, Shun ZHOU, Aihua GAO, Shaobo GE, Xiangguo XIAO. Image classification of optical element surface defects based on convolutional neural network[J]. Journal of Applied Optics, 2023, 44(3): 677
    Download Citation