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..

The metallized ceramic ring and the pinhole defects on the surface of its metal layer.

More »

Fig 1. Expand

Table 1..

Model and parameters of each device in the acquisition device.

More »

Table 1. Expand

Fig 2.

Schematic diagram of the pinhole defect detection module of the metallized ceramic ring.

More »

Fig 2 Expand

Fig 3.

Sample image preprocessing and image segmentation process.

More »

Fig 3 Expand

Table 2.

Numbers of pinhole defects before and after data augmentation.

More »

Table 2 Expand

Fig 4.

Basic framework of data augmentation.

More »

Fig 4 Expand

Fig 5.

Improved DETR Network Model.

More »

Fig 5 Expand

Fig 6.

Principles of SimAM attention mechanism.

More »

Fig 6 Expand

Fig 7.

MBconv structure with SimAM.

More »

Fig 7 Expand

Fig 8.

Pinhole defect detection procedure based on deep learning.

More »

Fig 8 Expand

Fig 9.

The morphology-based pinhole defect detection module flow.

More »

Fig 9 Expand

Fig 10.

Verification flow of detection results of the two pinhole defect detection modules.

More »

Fig 10 Expand

Fig 11.

Fusion process of detection results of the two pinhole defect detection modules.

More »

Fig 11 Expand

Fig 12.

Implementation process chart of proposed method.

More »

Fig 12 Expand

Table 3.

Training parameters of the improved DETR network model.

More »

Table 3 Expand

Table 4.

mAP of the model before and after data augmentation.

More »

Table 4 Expand

Table 5.

Settings of different models and comparison of detection results.

More »

Table 5 Expand

Table 6.

Pinhole Detection Results of Different Methods.

More »

Table 6 Expand

Table 7.

Comparison of performances of different detection methods.

More »

Table 7 Expand

Table 8.

Single-frame image inference time of different detection methods.

More »

Table 8 Expand