Evaluation of Lightweight Object Detection and Instance Segmentation Techniques for Industrial Printed Circuit Board Solder Quality Assessment

Abstract

The rapid progress of deep learning has transformed the detection of soldering defects in printed circuit boards (PCBs), outperforming traditional manual inspections and rule-based machine vision systems.This study evaluates the performance of state-of-the-art YOLO models—specifically YOLOv11 and YOLOv12—for both object detection and instance segmentation of solder defects in aerospace PCBs using the open-source SolDef_AI dataset. We compare multiple variants (nano, small, and medium) to assess their accuracy, efficiency, and suitability for industrial quality control. Our experiments reveal that YOLO-v11s-seg achieves the highest mean average precision (mAP50-95: 0.853 for detection, 0.822 for segmentation), demonstrating superior defect localization capabilities, particularly for challenging classes such as "poor_solder" and "spike." While YOLOv12 models exhibit competitive detection performance, they show slightly lower segmentation accuracy, indicating potential areas for architectural refinement. Smaller models (YOLO-v11n, YOLO-v12n) offer a favorable balance between speed and precision, making them viable for real-time applications. The findings highlight the effectiveness of YOLO-based deep learning in automating solder defect inspection, with implications for improving manufacturing quality assurance in electronics production.

Keywords

• Image Processing
• Object Detection
• Quality Control
• Soldering Defect Detection

References

1. [1]. W. Dai, A. Mujeeb, M. Erdt, and A. Sourin, “Soldering defect detection in automatic optical inspection,” Adv. Eng. Informatics, vol. 43, p. 101004, 2020.
2. [2]. Q. Ling, N. A. M. Isa, and M. S. M. Asaari, “SDD-Net: Soldering defect detection network for printed circuit boards,” Neurocomputing, vol. 610, p. 128575, 2024.
3. [3]. A. Sezer and A. Altan, “Detection of solder paste defects with an optimization-based deep learning model using image processing techniques,” Solder. \& Surf. Mt. Technol., vol. 33, no. 5, pp. 291–298, 2021.
4. [4]. A. Bhattacharya and S. G. Cloutier, “End-to-End Deep Learning Framework for Printed Circuit Board Manufacturing Defect Classification,” Sci. Rep., 2022.
5. [5]. Y. Wang et al., “Surface Defect Detection of Printed Circuit Board With Large Kernel Convolutional Networks,” 2024.
6. [6]. E. Vakili, G. Karimian, M. Shoaran, R. Yadipour, and J. Sobhi, “Valid-IoU: An Improved IoU-based Loss Function and Its Application to Detection of Defects on Printed Circuit Boards,” Multimed. Tools Appl., 2024.
7. [7]. W. Chen, H. Zhao, and Z. Wang, “Defect Detection Model of Printed Circuit Board Components Based on the Fusion of Multi-Scale Features and Efficient Channel Attention Mechanism,” Ieee Access, 2024.
8. [8]. Y. Liu, H. Wu, Y. Xu, X. Liu, and X. Yu, “Automatic PCB Sample Generation and Defect Detection Based on ControlNet and Swin Transformer,” Sensors, 2024.

9. [9]. S. Liang et al., “Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles,” Ieee Trans. Intell. Transp. Syst., 2022.
10. [10]. G. Lavanya and S. D. Pande, “Enhancing Real-Time Object Detection With YOLO Algorithm,” Eai Endorsed Trans. Internet Things, 2023.
11. [11]. M. J. Shaifee, B. Chywl, F. Li, and A. Wong, “Fast YOLO: A Fast You Only Look Once System for Real-Time Embedded Object Detection in Video,” J. Comput. Vis. Imaging Syst., 2017.
12. [12]. Z. Guo, C. Wang, G. Yang, Z. Huang, and G. Li, “MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface,” Sensors, 2022.
13. [13]. W. Tao, “Analysis the Improvements of YOLOv5 Algorithms: NRT-YOLO, MR-YOLO and YPH-YOLOv5,” Appl. Comput. Eng., 2024.
14. [14]. X. Lang, Z. Ren, D. Wan, Y. Zhang, and S. Shu, “MR-YOLO: An Improved YOLOv5 Network for Detecting Magnetic Ring Surface Defects,” Sensors, 2022.
15. [15]. J. Terven, D. Córdova‐Esparza, and J.-A. Romero-González, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Mach. Learn. Knowl. Extr., 2023.
16. [16]. M. Hussain, “YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature Toward Digital Manufacturing and Industrial Defect Detection,” Machines, 2023.
17. [17]. L. Lü, X. Li, Y. Wu, and B. Chen, “Enhanced RT-DETR for Traffic Sign Detection:Small Object Precision and Lightweight Design,” 2024.
18. [18]. Z. Li et al., “RT-DETR-SoilCuc: Detection Method for Cucumber Germinationinsoil Based Environment,” Front. Plant Sci., 2024.
19. [19]. S. Tang, “Improvement of RT-DETR Model for Ground Glass Pulmonary Nodule Detection,” PLoS One, 2025.
20. [20]. C. Tang, Y. Li, L. Wang, and W. Li, “Real-Time Traffic Light Detection Based on Lightweight Improved RT-DETR,” 2024.
21. [21]. G. Fontana, M. Calabrese, L. Agnusdei, G. Papadia, and A. Del Prete, “SolDef_AI: An Open Source PCB Dataset for Mask R-CNN Defect Detection in Soldering Processes of Electronic Components,” J. Manuf. Mater. Process., vol. 8, no. 3, p. 117, 2024.
22. [22]. K. Zhang and H. Shen, “Solder Joint Defect Detection in the Connectors Using Improved Faster-RCNN Algorithm,” Appl. Sci., 2021.
23. [23]. J. P. R Nayak and B. D. Parameshachari, “Effective PCB Defect Detection Using Stacked Autoencoder With Bi-LSTM Network,” Int. J. Intell. Eng. Syst., 2022.
24. [24]. X. Liao, S. Lv, D. Li, Y. Luo, Z. Zhu, and C. Jiang, “YOLOv4-MN3 for PCB Surface Defect Detection,” Appl. Sci., 2021.
25. [25]. W. Huang and P. Wei, “A PCB dataset for defects detection and classification,” arXiv Prepr. arXiv1901.08204, 2019.
26. [26]. “SolDef_AI: PCB dataset for defect detection.” [Online]. Available: https://kaggle.com/datasets/f899d21ce26435a9aa74da20a1409641fcafee386bdaf980e451cdbd4d744e0c.
27. [27]. R. Khanam and M. Hussain, “Yolov11: An overview of the key architectural enhancements,” arXiv Prepr. arXiv2410.17725, 2024.
28. [28]. Y. Tian, Q. Ye, and D. Doermann, “Yolov12: Attention-centric real-time object detectors,” arXiv Prepr. arXiv2502.12524, 2025.
29. [29]. R. Padilla, S. L. Netto, and E. A. B. Da Silva, “A survey on performance metrics for object-detection algorithms,” in 2020 international conference on systems, signals and image processing (IWSSIP), 2020, pp. 237–242.
30. [30]. S. Raschka, “An overview of general performance metrics of binary classifier systems,” arXiv Prepr. arXiv1410.5330, 2014.
31. [31]. J. P. R. Nayak and B. D. Parameshachari, “Effective PCB Defect Detection Using Stacked Autoencoder With Bi-LSTM Network,” Int. J. Intell. Eng. Syst., vol. 15, no. 2, pp. 285–294, 2022.
32. [32]. Y. Xu and others, “Lightweight PCB Solder Joint Defect Detection with YOLO11n Enhanced by RetBlock, SAF, and AAF,” J. Intell. Manuf., vol., 2025.
33. [33]. H. Li, others, I. Mendizabal-Arrieta, and others, “SCF-YOLO: A Lightweight Real-Time Model for PCB Surface Defect Detection,” Comput. Ind., vol., p. , 2025.
34. [34]. Q. Zhu and others, “VR-YOLO: Viewpoint-Robust PCB Defect Detection Based on YOLOv8 with CBAM,” IEEE Access, vol., p. , 2025.