Jian QIAO, Nengda CHEN, Yanxiong WU, Yang WU, Jingwei YANG. Defect detection of cylindrical surface of metal pot combining attention mechanism[J]. Optics and Precision Engineering, 2023, 31(3): 404

Search by keywords or author
- Optics and Precision Engineering
- Vol. 31, Issue 3, 404 (2023)

Fig. 1. Structure of BiYOLOX network

Fig. 2. Multiscale feature learning based on attention mechanism

Fig. 3. SAM module based on dilated convolution

Fig. 4. Variation curves of sinusoidal attenuation factor

Fig. 5. Example of classification loss function curves

Fig. 6. Image acquisition and detection system

Fig. 7. Samples of various defects on cylindrical surface of metal pot

Fig. 8. Target quantity distribution of various labels

Fig. 9. Statistics of defect recall rate of each category under different θ settings

Fig. 10. Detection results of cylindrical surface defects of highlight reflective metal pot
|
Table 1. Model super parameter setting
|
Table 2. Performance comparison of feature fusion network
|
Table 3. Comparison of detection effect of regression loss functions
|
Table 4. Comparison of detection effect of classification loss functions
|
Table 5. Performance comparison of feature fusion networks with Di_CBAM introduced at different locations
|
Table 6. Comparison of impact of improvement strategies on model performance
|
Table 7. Performance comparison of lightweight improved models

Set citation alerts for the article
Please enter your email address