Defect Detection in Printed Circuit Boards: A Comparative Analysis of Object Detection Models with Depthwise Convolution Adaptation

Authors

Keywords:

Objects Detection, Printed Circuit Boards Surface Defects, You Only Look Once, Depthwise Convolution, Deep Learning

Abstract

Printed circuit boards (PCBs) are key components in the electronics industry, and ensuring their integrity is essential for reliable manufacturing. Automated inspection systems based on computer vision, although efficient, face challenges. In this scenario, deep learning techniques have become effective solutions for detecting defects in more modern and complex PCBs. This article presents a comparative study between the YOLOv8n, YOLOv11n and RT-DETRv2 models for identifying defects in PCBs. The experiments were conducted using the PKU-Market-PCB dataset, which includes Missing Hole, Mouse Bite, Open Circuit, Short Circuit, Spur and Spurious Copper defects. To reduce the computational cost, modified versions of YOLOv8n and YOLOv11n with Depthwise convolution blocks (YOLOv8-DWConv and YOLOv11-DWConv). The analysis includes quantitative and qualitative comparisons. In addition, the robustness of the models is evaluated under challenging conditions with blur and illumination gradient noise. The results indicate that YOLOv11n achieves the best overall performance, while YOLOv11n-DWConv offers a competitive balance between precision and computational efficiency.

Downloads

Download data is not yet available.

Author Biographies

Julio Martins, University of Acre

Julio Martins (Member, IEEE) is currently pursuing a Bachelor's degree in Electrical Engineering at the Federal University of Acre (UFAC), Brazil. He is actively involved as a researcher in the PD project Applied Research in Computer Vision and Intelligence (PAVIC-Lab), a collaborative initiative between UFAC, Motorola, Flextronics and FUNDAPE. His research interests include object detection models.

Josue Lopez-Cabrejos, University of Acre

Josue Lopez (Member, IEEE) received the Bachelor's degree in Electronic Engineering and Telecommunications (2024) from the National Technological University of Lima Sur (UNTELS), Peru. He is currently pursuing a Master's degree in Computer Science at the Federal University of Acre (UFAC). His research interests include computer vision with a focus on Vision Transformer-based models. He is currently participating as a researcher in the PD Project Applied Research in Computer Vision and Intelligence (PAVIC-Lab), a partnership between UFAC, Motorola, Flextronics and FUNDAPE.

Quefren Leher, University of Acre

Quefren Leher (Member, IEEE) received the B.S. degree in Electrical Engineering from the Federal University of Acre, Brazil, in 2024. Currently pursuing an M.S. in Computer Science at the same institution, with a focus on intelligent computational systems. His research interests include computer vision, with a focus on generative models, and the application of Python in engineering and artificial intelligence. He is currently participating as a researcher in the PD Project Applied Research in Vision and Computational Intelligence (PAVIC-Lab) of the partnership between UFAC, Motorola, Flextronics, and FUNDAPE.

Thuanne Paixão, University of Acre

Thuanne Paixao (Member, IEEE) received the Bachelor's degree in Information Systems from the Federal University of Acre (2019), a specialization in Information Security from the Estacio University Center in Ribeirao Preto (2021), and a Master's degree in Computer Science from the Federal University of Acre (2023). She has experience in areas related to artificial intelligence, robotics, and information security. She is currently participating as a researcher in the PD Project Applied Research in Vision and Computational Intelligence (PAVIC-Lab) of the partnership between UFAC, Motorola, Flextronics, and FUNDAPE.

Ana Beatriz Alvarez, University of Acre

Ana Alvarez (Senior Member, IEEE) received a degree in electronic engineering from the Universidad Nacional del Altiplano, Puno-Peru, in 2000, and M.Sc. and Ph.D. degrees in electrical engineering from the University of Campinas (UNICAMP), Campinas-SP, Brazil, in 2005 and 2011, respectively. In 2012, she was a postdoctoral researcher in the Department of Computer Engineering and Automation (DCA-FEEC), UNICAMP, Brazil. Since 2013, it has been an effective research professor at the Center for Exact and Technological Sciences of the University of Acre (UFAC) Brazil, and since 2022 coordinates the Center for Applied Research in Computer Vision and Intelligence (PAVIC-Lab) of the CCET-UFAC, Rio Branco-AC, Brazil. She is the author of three book chapters and, several full scientific articles, and holds a software registration. My research interests include computational intelligence, machine learning, and computer vision. Specifically, my focus is on image restoration and synthesis, image enhancement, and analysis.

Facundo Palomino-Quispe, University of Acre

Facundo Palomino (Senior Member, IEEE) was born in Peru. He received his degree in Electronic Engineering from the Universidad Privada de Tacna, Peru. Master of Science in Electronic Engineering with mention in Automation and Instrumentation and Doctor of Science: Mechatronics Engineering from Universidad Nacional San Agustín de Arequipa (UNSA), Peru. He is a professor at the Universidad Nacional de San Antonio Abad del Cusco (UNSAAC), Cusco, Peru. Director of the Institutional Laboratory for Research, Entrepreneurship and Innovation in Automatic Control Systems, Automation and Robotics - LIECAR. Research Professor RENACYT: P0049773 Level V. His main areas of interest are Mobile Robotics, Control, Automation, Artificial Intelligence and Embedded Systems.

References

J. Niu, H. Li, X. Chen, and K. Qian, “An improved yolov5 network for detection of printed circuit board defects,” Journal of Sensors, vol.

, no. 1, p. 7270093, 2023. doi: 10.1155/2023/7270093 .

Y.-S. Deng, A.-C. Luo, and M.-J. Dai, “Building an automatic defect verification system using deep neural network for pcb defect classification,” in 2018 4th International Conference on Frontiers of Signal Processing (ICFSP). IEEE, 2018, pp. 145–149. doi: 10.1109/ICFSP.2018.8552045 .

J. P. Nayak and B. Parameshachari, “Effective pcb defect detection using stacked autoencoder with bi-lstm network.” International Journal of Intelligent Engineering & Systems, vol. 15, no. 5, 2022. doi: 10.22266/ijies2022.1031.05 .

Z. Xiao, Z. Wang, D. Liu, and H. Wang, “A path planning algorithm for pcb surface quality automatic inspection,” Journal of Intelligent Manufacturing, vol. 33, no. 6, pp. 1829–1841, 2022. doi: 10.1007/s10845-021-01766-3 .

W.-C. Wang, S.-L. Chen, L.-B. Chen, and W.-J. Chang, “A machine vision based automatic optical inspection system for measuring drilling quality of printed circuit boards,” IEEE access, vol. 5, pp. 10 817–10 833, 2016. doi: 10.1109/ACCESS.2016.2631658 .

Y. Yang and H. Kang, “An enhanced detection method of pcb defect based on improved yolov7,” Electronics, vol. 12, no. 9, p. 2120, 2023. doi: 10.3390/electronics12092120 .

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, 2019. doi: 10.1049/trit.2019.0019 .

W.-Y. Wu, M.-J. J. Wang, and C.-M. Liu, “Automated inspection of printed circuit boards through machine vision,” Computers in industry,

vol. 28, no. 2, pp. 103–111, 1996. doi: 10.1016/0166-3615(95)00063-1.

T. Zhang, J. Zhang, P. Pan, and X. Zhang, “Yolo-rrl: A lightweight algorithm for pcb surface defect detection,” Applied Sciences, vol. 14,

no. 17, p. 7460, 2024. doi: 10.3390/app14177460 .

W. Lv, Y. Zhao, Q. Chang, K. Huang, G. Wang, and Y. Liu, “Rt-detrv2: Improved baseline with bag-of-freebies for real-time detection

transformer,” 07 2024. doi: 10.48550/arXiv.2407.17140 .

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE

conference on computer vision and pattern recognition, 2016, pp. 779–788. doi: 10.1109/CVPR.2016.91 .

T. Yuan, Z. Jiao, and N. Diao, “Yolo-ssw: An improved detection method for printed circuit board surface defects,” Mathematics,

vol. 13, no. 3, 2025. doi: 10.3390/math13030435 . [Online]. Available: https://www.mdpi.com/2227-7390/13/3/435

H. Wang, S. Shen, and M. Li, “Pcb defect detection algorithm based on improved yolov8,” in 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI). IEEE, 2024, pp. 323–327. doi: 10.1109/ICECAI62591.2024.10675028 .

Y. Zhao, W. Lv, S. Xu, J. Wei, G. Wang, Q. Dang, Y. Liu, and J. Chen, “Detrs beat yolos on real-time object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp. 16 965–16 974. doi: 10.1109/CVPR52733.2024.01605 .

P. Malge and R. Nadaf, “Pcb defect detection, classification and localization using mathematical morphology and image processing tools,” International journal of computer applications, vol. 87, no. 9, 2014. doi: 10.5120/15240-3782 .

Y. Chang, Y. Xue, Y. Zhang, J. Sun, Z. Ji, H. Li, T. Wang, and J. Zuo, “Pcb defect detection based on pso-optimized threshold segmentation and surf features,” Signal, Image and Video Processing, vol. 18, no. 5, pp. 4327–4336, 2024. doi: 10.1007/s11760-024-03075-7 .

W. Huang and P. Wei, “A pcb dataset for defects detection and classification,” arXiv preprint arXiv:1901.08204, 2019. doi:

48550/arXiv.1901.08204 .

Z. Qu, J. Shen, R. Li, J. Liu, and Q. Guan, “Partsnet: A unified deep network for automotive engine precision parts defect detection,”

in Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence, 2018, pp. 594–599. doi:

1145/3297156.3297190 .

J. Kim, J. Ko, H. Choi, and H. Kim, “Printed circuit board defect detection using deep learning via a skip-connected convolutional autoencoder,” Sensors, vol. 21, no. 15, p. 4968, 2021. doi: 10.3390/s21154968 .

S. Ray and J. Mukherjee, “A hybrid approach for detection and classification of the defects on printed circuit board,” International Journal of Computer Applications, vol. 121, no. 12, 2015. doi: 10.5120/21595-4691 .

J. Huang, F. Zhao, and L. Chen, “Defect detection network in pcb circuit devices based on gan enhanced yolov11,” arXiv preprint

arXiv:2501.06879, 2025. doi: 10.48550/arXiv.2501.06879 .

J. Wang, X. Xie, G. Liu, and L. Wu, “A lightweight pcb defect detection algorithm based on improved yolov8-pcb,” Symmetry,

vol. 17, no. 2, 2025. doi: 10.3390/sym17020309 . [Online]. Available: https://www.mdpi.com/2073-8994/17/2/309

S. Xu, Y. Li, and Q. Liang, “Bare pcb defect detection based on improved yolov5 algorithm,” Packaging Engineering, vol. 43, no. 15,

pp. 33–41, 2022. doi: 10.1109/safepress58597.2023.10295682 .

M. Yuan, Y. Zhou, X. Ren, H. Zhi, J. Zhang, and H. Chen, “Yolo-hmc: An improved method for pcb surface defect detection,” IEEE

Transactions on Instrumentation and Measurement, vol. 73, pp. 1–11, 2024. doi: 10.1109/TIM.2024.3351241 .

M. Sohan, T. Sai Ram, R. Reddy, and C. Venkata, “A review on yolov8 and its advancements,” in International Conference on Data

Intelligence and Cognitive Informatics. Springer, 2024, pp. 529–545. doi: 10.1007/978-981-99-7962-239 .

M. Hussain, “Yolov5, yolov8 and yolov10: The go-to detectors for real-time vision,” arXiv preprint arXiv:2407.02988, 2024. doi:

48550/arXiv.2407.02988 .

R. Khanam and M. Hussain, “Yolov11: An overview of the key architectural enhancements,” arXiv preprint arXiv:2410.17725, 2024. doi:

48550/arXiv.2410.17725 .

Y. Guo, Y. Li, L. Wang, and T. Rosing, “Depthwise convolution is all you need for learning multiple visual domains,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, 2019, pp. 8368–8375. doi: 10.1609/aaai.v33i01.33018368 .

N. Jegham, C. Y. Koh, M. Abdelatti, and A. Hendawi, “Evaluating the evolution of yolo (you only look once) models: A comprehen-

sive benchmark study of yolo11 and its predecessors,” arXiv preprint arXiv:2411.00201, 2024. doi: 10.48550/arXiv.2411.00201 .

Y. Gong, Z. Chen, W. Deng, J. Tan, and Y. Li, “Real-time long-distance ship detection architecture based on yolov8,” IEEE Access, 2024. doi: 10.1109/ACCESS.2024.3445154 .

D. Wang, J. Tan, H. Wang, L. Kong, C. Zhang, D. Pan, T. Li, and J. Liu, “Sds-yolo: An improved vibratory position detection algorithm

based on yolov11,” Measurement, vol. 244, p. 116518, 2025. doi: 10.1016/j.measurement.2024.116518 .

J. Bento, T. Paix˜ao, and A. B. Alvarez, “Performance evaluation of yolov8, yolov9, yolov10, and yolov11 for stamp detection in

scanned documents,” Applied Sciences, vol. 15, no. 6, 2025. doi: 10.3390/app15063154 . [Online]. Available: https://www.mdpi.com/

-3417/15/6/3154

H. Yan, H. Zhang, F. Gao, H. Wu, and S. Tang, “Research on deep learning model enhancements for pcb surface defect detection,” Electronics, vol. 13, no. 23, p. 4626, 2024. doi: 10.3390/electronics13234626.

Downloads

Published

2025-10-01

How to Cite

Martins, J., Lopez-Cabrejos, J., Leher, Q., Paixão, T., Alvarez, A. B., & Palomino-Quispe, F. (2025). Defect Detection in Printed Circuit Boards: A Comparative Analysis of Object Detection Models with Depthwise Convolution Adaptation. IEEE Latin America Transactions, 23(11), 1001–1010. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/9899

Issue

Vol. 23 No. 11 (2025): Ordinary Issue

Section

Computing