Email this article EVALUATION OF PRINTED CIRCUIT BOARD DEFECT DETECTION ALGORITHMS BASED ON FASTER R-CNN AND YOLOV8
About this article
Received: 24/01/25 Revised: 19/03/25 Published: 19/03/25Authors
1. Pham Thu Ha, Le Quy Don University2. Luong Van Bang, Le Quy Don University
3. Le Hoang Phuc, Le Quy Don University
4. Ta Chi Hieu, Le Quy Don University
5. Dao Thi Nga
, Le Quy Don University
Abstract
Detecting printed circuit board defects is one of the critical tasks to ensure the quality of electronic devices, especially as printed circuit board sizes become increasingly compact, leading to higher demands for accuracy and speed in defect detection in industrial manufacturing. However, traditional inspection methods are time-consuming and inefficient for modern printed circuit boards. In recent years, deep learning techniques have demonstrated superior capabilities in detecting and classifying printed circuit board defects, providing a robust alternative to conventional methods. This paper presents an enhancement to the baseline model by incorporating modern techniques to analyze data in object detection tasks. By separately approaching the two models, Faster R-CNN and YOLOv8, we experimented with and compared their performance. Experimental results indicate that both models achieve promising performance; However, Faster R-CNN excels in accuracy, while YOLOv8 stands out for its speed.
Keywords
Full Text:
PDFReferences
[1] Q. Zhang and H. Liu, “Multi-scale defect detection of printed circuit board based on feature pyramid network,” in IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), 2021, pp. 911-914.
[2] H. Suzuki, “Printed Circuit Board,” Official Gazette of the United States Patent and Trademark Office, U.S. Patent 4,640,866, Mar. 16, 1987.
[3] H. S. Cho, “Printed Circuit Board,” Samsung Electro Mechanics Co., Ltd. Official Gazette of the United States Patent and Trademark, U.S. Patent 8,159,824, Mar. 16, 2012.
[4] M. X. Zhao, Z. Wang, and Y. Wu, "A Dataset for Deep Learning Based Detection of Printed Circuit Board Defects," Sci. Data, vol. 11, no. 1, pp. 1–8, 2024, doi: 10.1038/s41597-024-03656-8.
[5] D. B. Anitha and M. Rao, “A survey on defect detection in bare PCB and assembled PCB using image processing techniques,” in Proc. Int. Conf. Wireless Commun., Signal Process. Netw. (WiSPNET), Mar. 2017, pp. 39–43.
[6] V. A. Adibhatla, “Applying deep learning to defect detection in printed circuit boards via a newest model of you-only-look-once,” Mathematical Biosciences and Engineering, vol. 18, no. 4, pp. 4411-4428, 2021.
[7] W. Chen, Z. Huang, Q. Mu, and Y. Sun, "PCB defect detection method based on transformer-YOLO," IEEE Access, vol. 10, pp. 129480–129489, 2022, doi: 10.1109/ACCESS.2022.3228206.
[8] W. Liu and Y. Zhang, "Real-time PCB defect detection using SSD for industrial applications," J. Electron. Imaging, vol. 29, no. 2, 2020, Art. no. 023005, doi: 10.1117/1.JEI.29.2.023005.
[9] B. Hu and J. Wang, "Detection of PCB Surface Defects with Improved Faster-RCNN and Feature Pyramid Networks,” in IEEE Access, vol. 8, pp. 108335-108345, 2020.
[10] F. Fan, B. Wang, G. Zhu, and J. Wu, "Efficient Faster R-CNN: Used in PCB solder joint defects and components detection," in Proc. IEEE 4th Int. Conf. Comput. Commun. Eng. Technol. (CCET), Beijing, China, 2021, pp. 1–5, doi: 10.1109/CCET52649.2021.9544356.
[11] H. Xu and W. Wang, "Defect detection in PCB manufacturing using R-FCN-based deep learning model," IEEE Access, vol. 9, pp. 123567-123577, 2021, doi: 10.1109/ACCESS.2021.3112345.
[12] Y. Long, Z. Li, Y. Cai, R. Zhang, and K. Shen, “PCB defect detection algorithm based on improved YOLOv8,” Academ. J. Sci. Technol., vol. 7, no. 3, pp. 297–304, 2023, doi: 10.54097/ajst.v7i3.13420.
[13] RangeKing, "Brief summary of YOLOv8 model structure," GitHub, Jan. 10, 2023. [Online]. Available: https://github.com/ultralytics/ultralytics/issues/189. [Accessed Jan. 17, 2025].
[14] TigerZ, "Target detection algorithm - YOLOV8 - algorithm details," CSDN, March. 2, 2023.
[15] Z. Xiong, "A Design of Bare Printed Circuit Board Defect Detection System Based on YOLOv8," Highlights in Science, Engineering and Technology, vol. 57, pp. 203-209, Jul. 2023.
[16] P. Huang and P. Wei, “A PCB dataset for defects detection and classification,” arXiv preprint arXiv:1901.08204, 2019.
[17] R. Ding, L. Dai, G. Li, and H. Liu, "TDD-net: a tiny defect detection network for printed circuit boards," CAAI Transactions on Intelligence Technology, vol. 4, no. 2, pp. 110-116, Jun. 2019, doi: 10.1049/trit.2019.0019.
[18] P. V. Viet, "A combination of Faster R-CNN and YOLOv2 for drone detection in images," TNU Journal of Science and Technology, vol. 226, no. 06, pp. 90–96, May 2021.
DOI: https://doi.org/10.34238/tnu-jst.11949
Refbacks
- There are currently no refbacks.