Abstract
Consumer electronic devices such as smartphones, TV sets, etc. are designed around printed circuit boards (PCBs) with a large number of surface mounted components. The pick and place machine soldering these components on the PCB may pick the wrong component, may solder the component in the wrong position or fail to solder it at all. Therefore, Automated Optical Inspection (AOI) is essential to detect the above defects even prior to electric tests by comparing populated PCBs with the schematics. In this context, we leverage YOLO, a deep convolutional architecture designed for one-shot object detection, for AOI of PCBs. This architecture enables real-time processing of large images and can be trained end-to-end. In this work we also exploit a modified architecture of YOLOv5 designed to detect small components of which boards are often highly populated. Moreover, we proposed a strategy to transfer weights from the original pre-trained model to this improved one. We report here our experimental setup and some performance measures.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
This work is the result of the collaboration with SPEA, a worldwide leader in electronic component testing solutions that made available the images sued in this work.
References
Adibhatla, V.A., Chih, H.C., Hsu, C.C., Cheng, J., Abbod, M.F., Shieh, J.S.: Defect detection in printed circuit boards using you-only-look-once convolutional neural networks. Electronics 9(9), 1547 (2020). https://doi.org/10.3390/electronics9091547, https://www.mdpi.com/2079-9292/9/9/1547
Benjumea, A., Teeti, I., Cuzzolin, F., Bradley, A.: YOLO-Z: improving small object detection in yolov5 for autonomous vehicles. CoRR abs/2112.11798 (2021). https://arxiv.org/abs/2112.11798
Bochkovskiy, A., Wang, C., Liao, H.M.: YOLOv4: Optimal speed and accuracy of object detection. CoRR abs/2004.10934 (2020). https://arxiv.org/abs/2004.10934
Girshick, R.B.: Fast R-CNN. CoRR abs/1504.08083 (2015). https://arxiv.org/abs/1504.08083
Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR abs/1311.2524 (2013). https://arxiv.org/abs/1311.2524
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. CoRR abs/1406.4729 (2014). https://arxiv.org/abs/1406.4729
Jocher, G.: YOLOv5 by Ultralytics (2020). https://doi.org/10.5281/zenodo.3908559, https://github.com/ultralytics/yolov5
Li, J., Gu, J., Huang, Z., Wen, J.: Application research of improved YOLO V3 algorithm in PCB electronic component detection. Appl. Sci. 9(18), 3750 (2019). https://doi.org/10.3390/app9183750, https://www.mdpi.com/2076-3417/9/18/3750
Liao, X., Lv, S., Li, D., Luo, Y., Zhu, Z., Jiang, C.: YOLOv4-MN3 for PCB surface defect detection. Appl. Sci. 11(24), 11701 (2021). https://doi.org/10.3390/app112411701, https://www.mdpi.com/2076-3417/11/24/11701
Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: Unified, real-time object detection. CoRR abs/1506.02640 (2015). https://arxiv.org/abs/1506.02640
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. CoRR abs/1612.08242 (2016). https://arxiv.org/abs/1612.08242
Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. CoRR abs/1804.02767 (2018). https://arxiv.org/abs/1804.02767
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR abs/1506.01497 (2015). https://arxiv.org/abs/1506.01497
Tang, J., Liu, S., Zhao, D., Tang, L., Zou, W., Zheng, B.: PCB-YOLO: an improved detection algorithm of PCB surface defects based on YOLOv5. Sustainability 15(7), 5963 (2023). https://doi.org/10.3390/su15075963, https://www.mdpi.com/2071-1050/15/7/5963
Wang, C., Liao, H.M., Yeh, I., Wu, Y., Chen, P., Hsieh, J.: CSPNet: A new backbone that can enhance learning capability of CNN. CoRR abs/1911.11929 (2019). https://arxiv.org/abs/1911.11929
Zhan, W., et al.: An improved YOLOv5 real-time detection method for small objects captured by UAV. Soft Comput. 26, 1â13 (2022). https://doi.org/10.1007/s00500-021-06407-8
Zou, Z., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: A survey. CoRR abs/1905.05055 (2019). https://arxiv.org/abs/1905.05055
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Âİ 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Spadaro, G., Vetrano, G., Penna, B., Serena, A., Fiandrotti, A. (2024). Towards One-Shot PCB Component Detection with YOLO. In: Foresti, G.L., Fusiello, A., Hancock, E. (eds) Image Analysis and Processing - ICIAP 2023 Workshops. ICIAP 2023. Lecture Notes in Computer Science, vol 14365. Springer, Cham. https://doi.org/10.1007/978-3-031-51023-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-51023-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-51022-9
Online ISBN: 978-3-031-51023-6
eBook Packages: Computer ScienceComputer Science (R0)