Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Comparative visualization of defect detection versus conventional object detection.

More »

Fig 1 Expand

Fig 2.

The structure of YOLOv11.

More »

Fig 2 Expand

Fig 3.

The structure of YOLOv11-WBD.

More »

Fig 3 Expand

Fig 4.

Wavelet-Attentive Multiband Fusion (WAMF) module.

More »

Fig 4 Expand

Fig 5.

Bottleneck-Enhanced Dilated U-Conv (BEDU) module.

More »

Fig 5 Expand

Fig 6.

Bidirectional Depthwise Cross-Attention (BDCA) module.

More »

Fig 6 Expand

Fig 7.

An example of the NEU-DET steel strip surface defect dataset.

More »

Fig 7 Expand

Fig 8.

An example of the GC10-DET steel strip surface defect dataset.

More »

Fig 8 Expand

Table 1.

Experimental basic environment configuration.

More »

Table 1 Expand

Fig 9.

Training and validation losses and metric progression on NEU-DET dataset.

More »

Fig 9 Expand

Fig 10.

Training and validation losses and metric progression on GC10-DET dataset.

More »

Fig 10 Expand

Fig 11.

Precision-recall curve.

More »

Fig 11 Expand

Fig 12.

Heatmap comparison on NEU-DET datasets.

More »

Fig 12 Expand

Fig 13.

Heatmap comparison on GC10-DET dataset.

More »

Fig 13 Expand

Table 2.

Results of comparison experiments on dataset NEU-DET.

More »

Table 2 Expand

Table 3.

Results of comparison experiments on dataset GC10-DET.

More »

Table 3 Expand

Fig 14.

Comparative Analysis of Noisy Image Predictions on the NEU-DET dataset.

More »

Fig 14 Expand

Fig 15.

Comparative Analysis of Noisy Image Predictions on the GC10-DET dataset.

More »

Fig 15 Expand

Table 4.

The comparison of model missed detection rates under different noise intensities.

More »

Table 4 Expand

Table 5.

Results of ablation experiments on dataset NEU-DET.

More »

Table 5 Expand

Table 6.

Results of ablation experiments on dataset GC10-DET.

More »

Table 6 Expand