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.

Common electronic panel surface defects.

More »

Fig 1 Expand

Fig 2.

A kind of supervised target detector applied to the detection of surface defects in electronic panels.

It includes Backbone, Neck, and Double T-head with features extracted by T-deformable convolution module, which will be described in detail in Chapter 3.

More »

Fig 2 Expand

Fig 3.

A more detailed network structure.

More »

Fig 3 Expand

Fig 4.

The deformable convolution module of the fusion convolution self-attention module.

The left side is the feature extraction branch, and the right side is the offset learning branch. The offset is learned by the CBAM module.

More »

Fig 4 Expand

Fig 5.

The difference between Standard convolution, deformable convolution, and T-deformable convolution.

The left, middle, and right sides represent standard convolution, deformable convolution, and T-deformable convolution respectively. The upper, middle, and lower sides represent the activation unit on the feature map, 3 ×3 filter, sampling position.

More »

Fig 5 Expand

Fig 6.

Double T-head structure, in addition to head1, head2 is also designed to enhance the detection of small target defects.

More »

Fig 6 Expand

Fig 7.

SE module structure.

More »

Fig 7 Expand

Fig 8.

Training results of our designed network.

More »

Fig 8 Expand

Fig 9.

Test results of each trained network on the four categories of TNDSR1, TNDDR0, TNPLR0, TNNPE0.

More »

Fig 9 Expand

Table 1.

Comparison of the proposed method with Faster- RCNN, Retinanet, SSD, YOLOV3, YOLOV5, and YOLOX on the same dataset for each metric.

More »

Table 1 Expand

Fig 10.

Training results of our network on the MSD dataset.

More »

Fig 10 Expand

Table 2.

Comparison experiments between the proposed method and each comparison method on the MSD data set.

More »

Table 2 Expand

Table 3.

Map metrics and recall metrics for each network in the ablation experiment.

More »

Table 3 Expand