A lightweight detection algorithm of PCB surface defects based on YOLO.
Aiming at the problems of low accuracy and large computation in the task of PCB defect detection. This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model li...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0320344 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849715270636011520 |
|---|---|
| author | Shiwei Yu Feng Pan Xiaoqiang Zhang Linhua Zhou Liang Zhang Jikui Wang |
| author_facet | Shiwei Yu Feng Pan Xiaoqiang Zhang Linhua Zhou Liang Zhang Jikui Wang |
| author_sort | Shiwei Yu |
| collection | DOAJ |
| description | Aiming at the problems of low accuracy and large computation in the task of PCB defect detection. This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. Second, the ordinary convolution of the neck network is improved by depthwise separable convolution, resulting in a reduction of redundant parameters within the neck network. Afterwards, the Swin-Transformer is integrated with the C3 module in the Neck to build the C3STR module, which aims to address the issue of cluttered background in defective images and the confusion caused by simple defect types. Finally, the PANet network structure is replaced with the bidirectional feature pyramid network (BIFPN) structure to enhance the fusion of multi-scale features in the network. The results indicated that when comparing our model with the original model, there was a 47.2% reduction in the model's parameter count, a 48.5% reduction in GFLOPs, a 42.4% reduction in Weight, a 2.0% reduction in FPS, and a 2.4% rise in mAP. The model is better suited for use on low-arithmetic platforms as a result. |
| format | Article |
| id | doaj-art-a86592ccff4040098d25bc0800a2d4a3 |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-a86592ccff4040098d25bc0800a2d4a32025-08-20T03:13:27ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01204e032034410.1371/journal.pone.0320344A lightweight detection algorithm of PCB surface defects based on YOLO.Shiwei YuFeng PanXiaoqiang ZhangLinhua ZhouLiang ZhangJikui WangAiming at the problems of low accuracy and large computation in the task of PCB defect detection. This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. Second, the ordinary convolution of the neck network is improved by depthwise separable convolution, resulting in a reduction of redundant parameters within the neck network. Afterwards, the Swin-Transformer is integrated with the C3 module in the Neck to build the C3STR module, which aims to address the issue of cluttered background in defective images and the confusion caused by simple defect types. Finally, the PANet network structure is replaced with the bidirectional feature pyramid network (BIFPN) structure to enhance the fusion of multi-scale features in the network. The results indicated that when comparing our model with the original model, there was a 47.2% reduction in the model's parameter count, a 48.5% reduction in GFLOPs, a 42.4% reduction in Weight, a 2.0% reduction in FPS, and a 2.4% rise in mAP. The model is better suited for use on low-arithmetic platforms as a result.https://doi.org/10.1371/journal.pone.0320344 |
| spellingShingle | Shiwei Yu Feng Pan Xiaoqiang Zhang Linhua Zhou Liang Zhang Jikui Wang A lightweight detection algorithm of PCB surface defects based on YOLO. PLoS ONE |
| title | A lightweight detection algorithm of PCB surface defects based on YOLO. |
| title_full | A lightweight detection algorithm of PCB surface defects based on YOLO. |
| title_fullStr | A lightweight detection algorithm of PCB surface defects based on YOLO. |
| title_full_unstemmed | A lightweight detection algorithm of PCB surface defects based on YOLO. |
| title_short | A lightweight detection algorithm of PCB surface defects based on YOLO. |
| title_sort | lightweight detection algorithm of pcb surface defects based on yolo |
| url | https://doi.org/10.1371/journal.pone.0320344 |
| work_keys_str_mv | AT shiweiyu alightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT fengpan alightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT xiaoqiangzhang alightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT linhuazhou alightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT liangzhang alightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT jikuiwang alightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT shiweiyu lightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT fengpan lightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT xiaoqiangzhang lightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT linhuazhou lightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT liangzhang lightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo AT jikuiwang lightweightdetectionalgorithmofpcbsurfacedefectsbasedonyolo |