Welcome to Francis Academic Press

International Journal of Frontiers in Engineering Technology, 2022, 4(10); doi: 10.25236/IJFET.2022.041005.

Defect Detection Method of PCB Based on Improved YOLOv5

Author(s)

Jianfei Yuan, Yongkang Peng

Corresponding Author:
Yongkang Peng
Affiliation(s)

Jingdezhen Ceramic University, Jingdezhen, Jiangxi, 333403, China

Abstract

Stimulated by the increasing demand for electronic equipment, the global PCB market is expanding rapidly, and the detection of PCB defects is becoming more and more important. However, the small target, dense and other problems that are difficult to detect pose a great challenge to the accuracy and real-time performance of PCB defect detection. In this paper, YOLOv5 algorithm is applied to the field of PCB defect detection, and the corresponding YOLOv5-SlimNeck lightweight network is adopted. The experiment shows that YOLOv5l6 can detect all kinds of small and dense defects of PCB, with mAP.5 reaching 95.4%. On the other hand, YOLOv5-SlimNeck reduced the parameters by 89.6% and mAP.5 reached 94%. Compared with the lightweight network yolov5s6 in the official library, YOLOv5s6, YOLOv5-SlimNeck has only 64.5% parameters, and mAP.5 is 2.4% higher than YOLOv5s6.

Keywords

PCB; defect detection; YOLO

Cite This Paper

Jianfei Yuan, Yongkang Peng. Defect Detection Method of PCB Based on Improved YOLOv5. International Journal of Frontiers in Engineering Technology (2022), Vol. 4, Issue 10: 28-33. https://doi.org/10.25236/IJFET.2022.041005.

References

[1] Xiang Sen. Practical application of defect detection of printed circuit boards [J]. Electronic Testing, 2021 (06): 125-126. doi: 10.16520/j.cnki.1000-8519.2021.06.056.

[2] Girshick, R.B., Donahue, J., Darrell, T., & Malik, J. (2014). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 580-587.

[3] Ren, S., He, K., Girshick, R.B., & Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149.

[4] Redmon, J., Divvala, S.K., Girshick, R.B., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779-788.

[5] Lin, T., Goyal, P., Girshick, R.B., He, K., & Dollár, P. (2017). Focal Loss for Dense Object Detection. 2017 IEEE International Conference on Computer Vision (ICCV), 2999-3007.

[6] Shao Yanhua, Zhang Duo, Chu Hongyu, Zhang Xiaoqiang, Rao Yunbo. Overview of YOLO target detection based on deep learning [J]. Journal of Electronics and Information, 2022,44(10):3697-3708.

[7] Zhang Yue, Wang Zhiyuan, Zhao Lishan, Zhu Shisong, Lu Bibo. Intelligent safety helmet detection based on YOLOv5 [J]. Northeast Electric Power Technology, 2022,43(08):50-52+56.

[8] Mathew, Midhun P.,Mahesh, Therese Yamuna. Leaf-based disease detection in bell pepper plant using YOLO v5[J]. Signal, Image and Video Processing,2021(prepublish).

[9] Glenn Jocher, Ayush Chaurasia, Alex Stoken, Jirka Borovec, NanoCode012, Yonghye Kwon, TaoXie, Kalen Michael, Jiacong Fang, imyhxy, Lorna, Colin Wong, Zeng Yifu, Abhiram V, Diego Montes, Zhiqiang Wang, Cristifati, Jebastin Nadar, Laughing, … xylieong. (2022). ultralytics/yolov5: v6.2 - YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations (v6.2). Zenodo. https://doi.org/10.5281/zenodo.7002879

[10] Li, H., Li, J., Wei, H., Liu, Z., Zhan, Z., & Ren, Q. (2022). Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles. ArXiv, abs/2206.02424.

[11] Huang, W., & Wei, P. (2019). A PCB Dataset for Defects Detection and Classification. ArXiv, abs/1901.08204.