Volume 22, Issue 4 (JIAEEE Vol.22 No.4 2025)
Journal of Iranian Association of Electrical and Electronics Engineers 2025, 22(4): 44-56 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Hosseini H, Mavaddati S. Application and Evaluation of Deep Learning Models for Defect Detection in Printed Circuit Boards. Journal of Iranian Association of Electrical and Electronics Engineers 2025; 22 (4) :44-56
URL: http://jiaeee.com/article-1-1765-en.html
URL: http://jiaeee.com/article-1-1765-en.html
Electronic Department, Faculty of Engineering and Technology, University of Mazandaran, Babolsar
Abstract: (707 Views)
Here’s the translation for your abstract title and keywords:
Title:
Application and Evaluation of Deep Learning Models for Defect Detection in Printed Circuit Boards
Abstract:
In this paper, the effectiveness of deep learning models for the automatic detection of defects in printed circuit boards is investigated. Defects in printed circuit boards can lead to serious disruptions in the performance of electronic devices, and accurate and rapid identification of these defects is essential for ensuring production quality. To this end, the Inception-v3, VGG16, ResNet18, ResNet50, ResNet101, and YOLOv5 models were selected as representatives of various deep neural network architectures, and trained and evaluated on datasets of images containing PCB defects. These models, due to their capabilities in extracting complex and deep features from images, facilitate precise detection of both surface and structural defects. The results from evaluating these models indicate that deep learning can accurately and automatically identify defects in printed circuit boards, thereby improving the inspection process. This research emphasizes the importance of utilizing advanced deep learning models in the electronics industry and demonstrates that the choice of appropriate architecture significantly impacts the accuracy and speed of defect detection.
Keywords: Image processing, Printed Circuit Board, Defect detection, Data redundancy, Deep learning.
Type of Article: Research |
Subject:
Electronic
Received: 2024/10/1 | Accepted: 2025/07/13 | Published: 2026/01/22
Received: 2024/10/1 | Accepted: 2025/07/13 | Published: 2026/01/22
References
1. [1] G. Lakshmi, V. U. Sankar, and Y. S. Sankar, "A survey of PCB defect detection algorithms", J. Electron. Test., vol. 39, pp. 541-554, 2023, doi: 10.1007/s10836-023-06091-6. [DOI:10.1007/s10836-023-06091-6]
2. [2] Q. Ling and N. A. M. Isa, "Printed circuit board defect detection methods based on image processing, machine learning and deep learning: A survey", IEEE Access, vol. 11, pp. 15921-15944, 2023, doi: 10.1109/ACCESS.2023.3245093. [DOI:10.1109/ACCESS.2023.3245093]
3. [3] X. Wu, Y. Ge, Q. Zhang, and D. Zhang, "PCB defect detection using deep learning methods", in IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD), 2021, pp. 873-876, doi: 10.1109/CSCWD49262.2021.9437846. [DOI:10.1109/CSCWD49262.2021.9437846]
4. [4] J. Zheng, X. Sun, H. Zhou, C. Tian, and H. Qiang, "Printed circuit boards defect detection method based on improved fully convolutional networks", IEEE Access, vol. 10, pp. 109908-109918, 2022, doi: 10.1109/ACCESS.2022.3214306. [DOI:10.1109/ACCESS.2022.3214306]
5. [5] Y. D. Austria and A. C. Fajardo, "Defect detection in printed circuit boards using convolutional neural networks", in 2023 2nd International Conference on Edge Computing and Applications (ICECAA), 2023, pp. 1498-1504, doi: 10.1109/ICECAA58104.2023.10212195. [DOI:10.1109/ICECAA58104.2023.10212195]
6. [6] V. Mankad, N. Bhanvadia, M. I. Patel, and R. Gajjar, "PCB classification using convolutional neural network", in 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021, pp. 986-990, doi: 10.1109/ICAC3N53548.2021.9725695. [DOI:10.1109/ICAC3N53548.2021.9725695]
7. [7] J. Yu, L. Zhao, Y. Wang, and Y. Ge, "Defect detection of printed circuit board based on adaptive key-points localization network", Comput. Ind. Eng., vol. 193, p. 110258, 2024. [DOI:10.1016/j.cie.2024.110258]
8. [8] G. J. Brindha, S. Athiban, J. Gurumoorthi, and P. Sanjaykrishna, "Printed circuit board defect detection using machine learning", J. Electron Int. Res. J. Educ. Technol., pp. 76-82, 2023, doi: 10.1234/abcd.efghi.
9. [9] A. Bhattacharya and S. G. Cloutier, "End-to-end deep learning framework for printed circuit board manufacturing defect classification", Sci. Rep., vol. 12, p. 12559, 2022, doi: 10.1038/s41598-022-16302-3. [DOI:10.1038/s41598-022-16302-3]
10. [10] V. A. Adibhatla, H. C. Chih, C. C. Hsu, J. Cheng, M. F. Abbod, and J. S. Shieh, "Defect detection in printed circuit boards using you-only-look-once convolutional neural networks", Electronics, vol. 9, no. 9, p. 1547, 2020, doi: 10.3390/electronics9091547. [DOI:10.3390/electronics9091547]
11. [11] J. Shen, N. Liu, and H. Sun, "Defect detection of printed circuit board based on lightweight deep convolution network", IET Image Process., vol. 14, pp. 3932-3940, 2020. [DOI:10.1049/iet-ipr.2020.0841]
12. [12] M. A. Alghassab, "Defect detection in printed circuit boards with pre-trained feature extraction methodology with convolution neural networks", Comput. Mater. Contin., vol. 70, no. 1, pp. 637-652, 2022, doi: 10.32604/cmc.2022.019527. [DOI:10.32604/cmc.2022.019527]
13. [13] Q. Yang and F. Yu, "Deep learning-based defect detection research on printed circuit boards", Int. J. Adv. Netw. Monit. Control., vol. 9, no. 2, pp. 51-58, 2024, doi: 10.2478/ijanmc-2024-0015. [DOI:10.2478/ijanmc-2024-0015]
14. [14] V. T. Nguyen and H. A. Bui, "A real-time defect detection in printed circuit boards applying deep learning", EUREKA: Phys. Eng., no. 2, pp. 143-153, 2022, doi: 10.21303/2461-4262.2022.002127. [DOI:10.21303/2461-4262.2022.002127]
15. [15] Kaggle, "PCB defects dataset", [Online]. Available: https://www.kaggle.com/datasets/akhatova/pcb-defects.
16. [16] C. Wang, G. Huang, Z. Huang, and W. He, "Conditional TransGAN-based data augmentation for PCB electronic component inspection", Comput. Intell. Neurosci., vol. 2023, p. 2024237, Jan. 2023, doi: 10.1155/2023/2024237. [DOI:10.1155/2023/2024237]
17. [17] H. Kang and Y. Yang, "An enhanced detection method of PCB defect based on D-DenseNet (PCBDD-DDNet)", Electronics, vol. 12, p. 4737, 2023, doi: 10.3390/electronics12234737. [DOI:10.3390/electronics12234737]
18. [18] X. Yu and Y. He, "PCB defect detection based on GAN data generation with self-attentive mechanism", in 2022 2nd International Conference on Frontiers of Electronics, Information and Computation Technologies (ICFEICT), Wuhan, China, 2022, pp. 55-60, doi: 10.1109/ICFEICT57213.2022.00018. [DOI:10.1109/ICFEICT57213.2022.00018]
19. [19] B. Ghosh, M. K. Bhuyan, P. Sasmal, Y. Iwahori, and P. Gadde, "Defect classification of printed circuit boards based on transfer learning", in Proc. 2018 IEEE Applied Signal Process. Conf. (ASPCON), Kolkata, India, 2018, pp. 245-248, doi: 10.1109/ASPCON.2018.8748670. [DOI:10.1109/ASPCON.2018.8748670]
20. [20] X. Chen, Y. Wu, X. He, and W. Ming, "A comprehensive review of deep learning-based PCB defect detection", IEEE Access, vol. 11, pp. 139017-139038, 2023, doi: 10.1109/ACCESS.2023.3339561. [DOI:10.1109/ACCESS.2023.3339561]
21. [21] A. Legon, M. Deo, S. Albin, and M. Audette, "Detection and classification of PCB defects using deep learning methods", in Proc. 2022 IEEE 31st Microelectron. Design Test Symp. (MDTS), Albany, NY, USA, 2022, pp. 1-6, doi: 10.1109/MDTS54894.2022.9826925. [DOI:10.1109/MDTS54894.2022.9826925]
22. [22] T. T. A. Pham, D. K. T. Thoi, H. Choi, and S. Park, "Defect detection in printed circuit boards using semi-supervised learning", Sensors, vol. 23, no. 6, p. 3246, Mar. 2023, doi: 10.3390/s23063246. [DOI:10.3390/s23063246]
23. [23] S. Szabó, I. J. Holb, V. É. Abriha-Molnár, G. Szatmári, S. K. Singh, and D. Abriha, "Classification Assessment Tool: A program to measure the uncertainty of classification models in terms of class-level metrics", Applied Soft Computing, vol. 155, p. 111468, 2024, doi: 10.1016/j.asoc.2024.111468. [DOI:10.1016/j.asoc.2024.111468]
24. [24] M. Krzywicka and A. Wosiak, "Sensitivity of Standard Evaluation Metrics for Disease Classification and Progression Assessment Based on Whole-Body Imaging", Procedia Computer Science, vol. 225, pp. 4314-4323, 2023, doi: 10.1016/j.procs.2023.10.428. [DOI:10.1016/j.procs.2023.10.428]
25. [25] Z. Dorrani, H. Farsi, and S. Mohamadzadeh, "Deep learning in vehicle detection using ResUNet-a architecture", Jordan Journal of Electrical Engineering, vol. 8, no. 2, pp. 165-178, 2022. [DOI:10.5455/jjee.204-1638861465]
26. [26] Z. Dorrani, H. Farsi, and S. Mohamadzadeh, "Shadow removal in vehicle detection using ResUNet-a", Iranian Journal of Energy and Environment, vol. 14, no. 1, pp. 87-95, 2023. [DOI:10.5829/IJEE.2023.14.01.11]
27. [27] N. Aghayan Mashhady and A. Amirkhani, "Improving the Accuracy of Road Damage Detectors Using Traditional Augmentations and Object Bounding Box Augmentation", Journal of Iranian Association of Electrical and Electronics Engineers, vol. 21, no. 3, pp. 139-154, 2024. [DOI:10.61186/jiaeee.21.3.139]
28. [28] N. Aghaei, G. Akbarizadeh, and A. Kosarian, "Using ShuffleNet to design a deep semantic segmentation model for oil spill detection in synthetic aperture radar images", Journal of Iranian Association of Electrical and Electronics Engineers, vol. 19, no. 3, pp. 131-144, 2022. [DOI:10.52547/jiaeee.19.3.131]
Send email to the article author
| Rights and permissions | |
 |
This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0) |
