A lightweight detection algorithm of PCB surface defects based on YOLO.
Saved in:
| Title: | A lightweight detection algorithm of PCB surface defects based on YOLO. |
|---|---|
| Authors: | Yu S; CGN Digital Technology Co., Ltd., Shanghai, China., Pan F; CGN Digital Technology Co., Ltd., Shanghai, China., Zhang X; CGN Digital Technology Co., Ltd., Shanghai, China., Zhou L; CGN Digital Technology Co., Ltd., Shanghai, China., Zhang L; CGN Digital Technology Co., Ltd., Shanghai, China., Wang J; CGN Digital Technology Co., Ltd., Shanghai, China. |
| Source: | PloS one [PLoS One] 2025 Apr 18; Vol. 20 (4), pp. e0320344. Date of Electronic Publication: 2025 Apr 18 (Print Publication: 2025). |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: San Francisco, CA : Public Library of Science |
| MeSH Terms: | Detection Algorithms* , Image Processing, Computer-Assisted*/methods , Polychlorinated Biphenyls*/analysis , Polychlorinated Biphenyls*/chemistry, Algorithms ; Neural Networks, Computer |
| Abstract: | Competing Interests: The authors have declared that no competing interests exist. 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. (Copyright: © 2025 Yu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.) |
| References: | Waste Manag. 2020 May 15;109:1-9. (PMID: 32361385) Waste Manag. 2021 May 1;126:247-257. (PMID: 33780704) Neural Netw. 2023 Oct;167:787-797. (PMID: 37729792) |
| Substance Nomenclature: | DFC2HB4I0K (Polychlorinated Biphenyls) |
| Entry Date(s): | Date Created: 20250418 Date Completed: 20250418 Latest Revision: 20250422 |
| Update Code: | 20250422 |
| PubMed Central ID: | PMC12007705 |
| DOI: | 10.1371/journal.pone.0320344 |
| PMID: | 40249746 |
| Database: | MEDLINE |
Full Text 
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Competing Interests: The authors have declared that no competing interests exist.<br />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.<br /> (Copyright: © 2025 Yu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.) |
|---|---|
| ISSN: | 1932-6203 |
| DOI: | 10.1371/journal.pone.0320344 |