YOLO-RSH: A PCB Surface Component Detection Model
DOI:
https://doi.org/10.6919/ICJE.202603_12(3).0013Keywords:
PCB; YOLOv11; Small Object Detection; Feature Extraction; Feature Fusion.Abstract
Printed Circuit Boards (PCBs) are an essential component of modern electronic products. The surface components of PCBs exhibit characteristics such as multi-scale, dense distribution, high similarity, and small size, which can lead to missed or false detections during inspection. This paper proposes a novel YOLO-RSH detection model based on YOLOv11. First, a new C2SCSA attention module is introduced to replace the C2PSA module in the backbone network, which enhances the network's feature extraction ability. Next, the newly proposed C3k2 convolution module in YOLOv11 is augmented with the RepVGG mechanism, forming the C3k2-RepVGG convolution, which improves the backbone's focus on important features. Finally, a hierarchical feature fusion block (HFFB) is added before the detection head, which better integrates multi-scale target features. Experimental results show that compared to the baseline model, the YOLO-RSH model achieves an average precision improvement of 1.8 percentage points.
Downloads
References
[1] Y .Shi, Z. Xin, P. C. Loh, and F. Blaabjerg, ‘‘A review of traditional helical to recent miniaturized printed circuit board Rogowski coils for powerelectronic applications,’’ IEEE Trans. Power Electron., vol. 35, no. 11, pp. 12207–12222, Nov. 2020.
[2] F. R. Leta and F. F. Feliciano, ‘‘Computational system to detect defects in mounted and bare PCB based on connectivity and image correlation,’’ in Proc. 15th Int. Conf. Syst., Signals Image Process., Jun. 2008, pp. 331–334.
[3] Xu Mingming. Detection and Recognition of PCB Components [D]. Dalian University of Technology, 2006.
[4] Crispin, A.J., Rankov, V. Automated inspection of PCB components using a genetic algorithm template-matching approach. Int J Adv Manuf Technol 35, 293–300 (2007). https://doi.org/10.1007/s00170-006-0730-0
[5] YIN H M. A template-matching-based fast algorithm for PCB components detection[J]. Advanced materials research, 2013, 690/691/692/693:3205-3208.
[6] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016
[7] Joseph Redmon and Ali Farhadi. Yolo9000: Better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.
[8] Joseph Redmon and Ali Farhadi. Yolov3: An incremental improvement, 2018.
[9] Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. Yolov4: Optimal speed and accuracy of object detection, 2020.
[10] Jocher Glenn. Yolov5 release v7.0. https: // github. com/ ultralytics/ yolov5/ tree/ v7. 0 , 2022.
[11] Chien-Yao Wang, Hong-Yuan Mark Liao, Yueh-Hua Wu, Ping-Yang Chen, Jun-Wei Hsieh, and I-Hau Yeh. Cspnet: A new backbone that can enhance learning capability of cnn. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 390–391, 2020.
[12] Joseph Redmon. Darknet: Open source neural networks in c. http://pjreddie.com/ darknet/, 2013–2016.
[13] Chuyi Li, Lulu Li, Yifei Geng, Hongliang Jiang, Meng Cheng, Bo Zhang, Zaidan Ke, Xiaoming Xu, and Xiangxiang Chu. Yolov6 v3.0: A full-scale reloading. arXiv preprint arXiv:2301.05586, 2023.
[14] Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. Yolov7: Trainable bag-offreebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7464–7475, 2023.
[15] Jocher Glenn. Yolov8. https: // github. com/ ultralytics/ ultralytics/ tree/ main , 2023.
[16] Chien-Yao Wang, I-Hau Yeh, and Hong-Yuan Mark Liao. Yolov9: Learning what you want to learn using programmable gradient information. arXiv preprint arXiv:2402.13616, 2024.
[17] Wang, A.; Chen, H.; Liu, L.; Chen, K.; Lin, Z.; Han, J.; Ding, G. Yolov10: Real-time end-to-end object detection. arXiv 2024, arXiv:2405.14458.
[18] Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.Y.; Berg, A.C. SSD: Single shot multibox detector. In Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016; pp. 21–37.
[19] RENS,HEK, GIRSHICKR,etal. Faster r_cnn: Towards real-time object detection with regionproposal networks[J].Advances in neural information process-ing systems,2015,28.
[20] Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 1137–1149.
[21] Si, Yunzhong et al. “SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention.” Neurocomputing 634 (2024): 129866.
[22] Xiangzuo Huo, Gang Sun, Shengwei Tian, Yan Wang, Long Yu, Jun Long, Wendong Zhang, Aolun Li,HiFuse: Hierarchical multi-scale feature fusion network for medical image classification,Biomedical Signal Processing and Control,Volume 87, Part A,2024,105534,ISSN 1746-8094,https://doi.org/10.1016/j.bspc.2023.105534.
[23] Ding, Xiaohan et al. “RepVGG: Making VGG-style ConvNets Great Again.” 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021): 13728-13737.
[24] C. Pramerdorfer and M. Kampel, “A dataset for computer-vision-based pcb analysis,” in 2015 14th IAPR International Conference on Machine Vision Applications (MVA), pp. 378–381, May 2015.
[25] G. Mahalingam, K. M. Gay, and K. Ricanek, “Pcb-metal: A pcb image dataset for advanced computer vision machine learning component analysis,” in 2019 16th International Conference on Machine Vision Applications (MVA), pp. 1–5, 2019.
[26] Hangwei Lu, Dhwani Mehta, Olivia Paradis, Navid Asadizanjani, Mark Tehranipoor, Damon L. Woodard. FICS-PCB: A Multi-Modal Image Dataset for Automated Printed Circuit Board Visual Inspection. Cryptology ePrint Archive, Paper 2020/366, 2020. [Online]. Available: https://eprint.iacr.org/2020/366.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Core Journal of Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
