Е-Публикации
Технически университет - София

Abstract: The process of designing electronic circuits is supported by graphic editors in specialized CAD tools. Although this software is characterized by rich functionality, it can be enriched with the ability to recognize hand-drawn electronic circuits. In this way, an electronic circuit design idea drawn by hand will be converted into the corresponding schematic solution in CAD software. This will contribute to speeding up the design process and significantly reduce the efforts of the designer, who will not need to draw the electronic circuit twice - once on paper and then in the CAD software editor. The paper presents an analysis aimed at recognizing hand-drawn electronic analog circuits using the YOLOv8 object recognition algorithm. An image dataset of hand-drawn schematics is created. The accuracy of the model is evaluated and a high recognition rate of the circuit elements is obtained as a result.

References

1. J. Redmon, S. Divvala, R. Girshick, A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, 779-788. doi: 10.1109/CVPR.2016.91.
2. T. Diwan, G. Anirudh, J. V. Tembhurne, "Object detection using YOLO: Challenges, architectural successors, datasets and applications," Multimedia Tools and Applications 82, 2023, 9243-9275. https://doi.org/10.1007/s11042-022-13644-y.
3. J. Terven, D.-M. Cordova-Esparza, J.-A. Romero-Gonzalez, "A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS," Machine Learning and Knowledge Extraction, 5(4), 2023, 1680-1716. https://doi.org/10.3390/make5040083.
4. Ultralytics, https://github.com/ultralytics/ultralytics.
5. C. Dong, G. Du, "An enhanced real-time human pose estimation method based on modified YOLOv8 framework," Scientific Reports 14, 8012, 2024. https://doi.org/10.1038/s41598-024-58146-z.
6. C. Gao, Q. Zhang, Z. Tan et al., "Applying optimized YOLOv8 for heritage conservation: Enhanced object detection in Jiangnan traditional private gardens," Heritage Science 12, 31, 2024. https://doi.org/10.1186/s40494-024-01144-1.
7. S. Sun, B. Mo, J. Xu, D. Li, J. Zhao, S. Han, Neurocomputing, vol. 588, 2024, 1-24. https://doi.org/10.1016/j.neucom.2024.127685.
8. CVAT Computer Vision Annotation Tool, https://www.cvat.ai/.
9. M. Glucina, N. Andelic, I. Lorencin, Z. Car, "Detection and Classification of Printed Circuit Boards Using YOLO Algorithm," Electronics 12, 667, 2023. https://doi.org/10.3390/electronics12030667.
10. R. Huang, G. Jinan, S. Xiaohong, H. Yongtao, U. Saad, "A Rapid Recognition Method for Electronic Components Based on the Improved YOLO-V3 Network, Electronics 8, no. 8: 825, 2019. https://doi.org/10.3390/electronics8080825.
11. Li J, Gu J, Huang Z, Wen J. Application Research of Improved YOLO V3 Algorithm in PCB Electronic Component Detection. Applied Sciences, 2019; 9(18):3750. https://doi.org/10.3390/app9183750.
12. T. S. Naga Venkata Satya Sirisha, N. Venkata Sai Mada, S. Haritha, P. Tumuluru, V. Rachapudi, "Evaluating the Performance of YOLO V5 for Electronic Device Classification," 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS), Coimbatore, India, 2023, 992-997. doi: 10.1109/ICAIS56108.2023.10073671.
13. S. P. Chhetri, S. Bhat, P. Timalsina, B. Thapa Magar, "Detection of Missing Component in PCB Using YOLO," International Journal on Engineering Technology (InJET), 1(1), Nov 2023, 62-71. ISSN: 3021-940X (print).
14. PyCharm: The Python IDE, https://www.jetbrains.com/pycharm/.
15. Ultralytics model, https://docs.ultralytics.com/.
16. Ultralytics model at Object Detection: https://docs.ultralytics.com/tasks/detect/.
17. Performance metrics Deep Dive, https://docs.ultralytics.com/guides/yolo-performance-metrics/#classwise-metrics.

Issue

Copyright Institute of Electrical and Electronics Engineers Inc.