Assessing Detection and Classification Performance for Vehicle License Plate Colors Using YOLOv5, YOLOv7, YOLOv8, and YOLOv9
Article Sidebar
Main Article Content
Abstract
This study assesses the detection and classification performance of YOLOv5, YOLOv7, YOLOv8, and YOLOv9 for vehicle license plate colors in Indonesia, supporting the electronic ticketing system (e-tilang). The dataset consisted of 1,214 images from video footage captured in Bandar Lampung, comprising five color categories: black, white, yellow, red, and non-plate. The models were trained using transfer learning with COCO pre-trained weights, evaluated using precision, recall, F1-score, mAP50, and mAP50-95, and tested under real-world moderate and crowded traffic conditions. The results show that YOLOv9 consistently outperformed all other models, achieving the highest precision (97.20%), recall (96.50%), F1-score (96.85%), mAP50 (98.10%), and mAP50-95 (80.50%), with the fastest inference time of 6.8 ms per image (approximately 147 FPS). YOLOv8 ranked second, followed by YOLOv7 and YOLOv5. Across all models, the non-plate category remained the most challenging, while white and yellow plates were occasionally misclassified under low-light conditions. In conclusion, YOLOv9 is recommended for deployment in Indonesia's e-tilang system due to its best balance of accuracy and speed. Future work should expand the dataset to more diverse geographical locations, evaluate model performance under extreme weather conditions, and deploy the model on edge devices to validate real-world performance.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
M. Ashkanani, A. AlAjmi, A. Alhayyan, Z. Esmael, M. AlBedaiwi, and M. Nadeem, “A Self-Adaptive Traffic Signal System Integrating Real-Time Vehicle Detection and License Plate Recognition for Enhanced Traffic Management,” Inventions, vol. 10, no. 1, 14, 2025, doi: https://doi.org/10.3390/inventions10010014.
R. Sholehurrohman, K. Muludi, and J. Triloka, “Optimizing transportation surveillance with YOLOv7: Detection and classification of vehicle license plate colors,” Jurnal Ilmu Teknologi dan Komputer (JITK), vol. 10, no. 4, pp. 812–820, May 2025, doi: https://doi.org/10.33480/jitk.v10i4.6260.
Kepolisian Negara Republik Indonesia, “Peraturan Kepolisian Negara Republik Indonesia Nomor 7 Tahun 2021 tentang Registrasi dan Identifikasi Kendaraan Bermotor,” 2021. [Online]. Available: https://peraturan.bpk.go.id/Details/225016/perpol-no-7-tahun-2021.
Kepolisian Negara Republik Indonesia, “Peraturan Kepala Kepolisian Negara Republik Indonesia Nomor 5 Tahun 2012 tentang Registrasi dan Identifikasi Kendaraan Bermotor,” 2012. [Online]. Available: https://www.peraturanpolri.com/2015/12/peraturan-kapolri-nomor-05-tahun2012.html.
R. Sholehurrohman, “Pengembangan YOLOv3 dengan Fitur Ekstraktor MobileNetV2 untuk Deteksi dan Klasifikasi Kendaraan Bergerak”, Master’s thesis, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia, 2021.
R. Sholehurrohman and B. Setiyono, “Detection and classification of moving vehicle based on YOLOv3 model,” AIP Conference Proceedings, vol. 2540, p. 080017, 2023, doi: https://doi.org/10.1063/5.0105877.
E. S. dos Santos Júnior, T. Paixão, and A. B. Alvarez, “Comparative performance of YOLOv8, YOLOv9, YOLOv10, and YOLOv11 for layout analysis of historical documents images,” Applied Sciences, vol. 15, no. 6, p. 3164, 2025, doi: https://doi.org/10.3390/app15063164.
S. Dolhopolov, T. Honcharenko, D. Chernyshev, and O. Panina, “Advancing automated quality control in automotive manufacturing: A comparative analysis of YOLOv8, YOLOv9, and YOLOv10 for vehicle damage detection,” in Proc. 9th Int. Conf. Digital Technologies in Education, Science and Industry (DTESI), Oct. 2024. CEUR-WS.org/vol-3966/W3Paper10.pdf
L. T. Ramos and A. D. Sappa, “A decade of you only look once (YOLO) for object detection,” arXiv preprint arXiv:2504.18586, 2025, doi: https://doi.org/10.1109/ACCESS.2025.3630988.
J. E. Gallagher and E. J. Oughton, “Surveying you only look once (YOLO) multispectral object detection advancements, applications, and challenges,” IEEE Access, vol. 13, pp. 7366–7395, 2025, doi: https://doi.org/10.1109/ACCESS.2025.3526458.
S. Farhadpour, T. A. Warner, and A. E. Maxwell, “Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices,” Remote Sens, vol. 16, no. 3, 533, 2024, doi: https://doi.org/10.3390/rs16030533.
A. Panda, D. Panigrahi, S. Mitra, S. Mittal, and S. Rahimi, “Transfer Learning App to Computer Vision Problems: Survey on Current Progress, Limitations, and Opportunities,” arXiv:2409.07736, 2024, doi: https://doi.org/10.48550/arXiv.2409.07736.
A. A. Quraishi, F. Feyzi, A. Shahbahrami, “Detection and recognition of vehicle licence plates using deep learning in challenging conditions: A systematic review,” Int. J. Intell. Syst. Technol. Appl., vol. 22, no. 2, pp.105-150, 2024, doi: https://doi.org/10.1504/IJISTA.2024.139736.
A. Alekseev, L. Kozhemyakin, V. Nikitin, and J. Bolshakova, “Data Preprocessing and Neural Network Architecture Selection Algorithms in Cases of Limited Training Sets—On an Example of Diagnosing Alzheimer’s Disease,” Algorithms, vol. 16, no. 5, 219, 2023, doi: https://doi.org/10.3390/a16050219.
S. Dolhopolov, T. Honcharenko, V. Hots, and P. Kruk, “YOLOv8, YOLOv9, and YOLOv10: A study in automated vehicle damage detection,” in Proc. 4th Int. Workshop on Information Technologies: Theoretical and Applied Problems (ITTAP), Ternopil, Ukraine, Oct. 2024.
R. Sholehurrohman, K. Sari, and A. Junaidi, “Color-based spot detection using automatic leaf segmentation in potato plants,” Integra: Journal of Integrated Mathematics and Computer Science, vol. 2, no. 3, pp. 75–80, 2025, doi: https://doi.org/10.26554/integrajimcs.20252339.
R. Khanam and M. Hussain, “What is yolov5: A deep look into the internal features of the popular object detector,” arXiv preprint arXiv:2407.20892, 2024, doi: https://doi.org/10.48550/arXiv.2407.20892.
Z. Yang, R. Xie, L. Liu, and N. Li, “Dense-YOLOv7: improved real-time insulator detection framework based on YOLOv7”, International Journal of Low-Carbon Technologies, vol. 19, pp. 157–170, 2024, doi: https://doi.org/10.1093/ijlct/ctad122.
A. Thakuria and C. Erkinbaev, “Improving the network architecture of YOLOv7 to achieve real-time grading of canola based on kernel health,” Smart Agricultural Technology, vol. 5, p. 100300, Oct. 2023, doi: https://doi.org/10.1016/j.atech.2023.100300.
V. Afifah and S. Erniwati, “Yolov8 for object detection: A comprehensive review of advances, techniques, and applications,” IJACI: International Journal of Advanced Computing and Informatics, vol. 2, no. 1, pp. 53–61, 2026, doi: https://doi.org/10.71129/ijaci.v2i1.pp53-61.
C. Y. Wang, I. H. Yeh, and H. Y. M. Liao, “Yolov9: Learning what you want to learn using programmable gradient information,” arXiv preprint arXiv:2402.13616, 2024, doi: https://doi.org/10.48550/arXiv.2410.17725.
M. Barr, “Coupling the Power of YOLOv9 with Transformer for Small Object Detection in Remote-Sensing Images,” Computer Modeling in Engineering & Sciences, vol. 143, no. 1, pp. 593–616, 2025, doi: https://doi.org/10.32604/cmes.2025.062264.
Z. Wang and J. Yang, “RE-YOLO: a lightweight small object detection method for UAV remote sensing imagery,” Annals of GIS, vol. 32, no. 1, pp. 65-84, 2026, doi: https://doi.org/10.1080/19475683.2026.2617202.
E. Pandilova, M. Petrov, V. Spasev, I. Dimitrovski, and I. Kitanovski, “Transfer Learning with Yolo for Object Detection in Remote Sensin,” in ICT Innovations 2024. TechConvergence: AI, Business, and Startup Synergy; Risteska Stojkoska, B., Janeska Sarkanjac, S., Eds.; Communications in Computer and Information Science; Springer Nature: Cham, Switzerland, 2025; vol. 2436, pp. 121–135, doi: https://doi.org/10.1007/978-3-031-86162-8_9.
S. Al-Saddik, M. E. Philip, and A. Haidar, “YOLO for Knowledge Extraction from Vehicle Images: A Baseline Study,” arXiv preprint arXiv:2507.18966, 2025 Jul 25, doi: https://doi.org/10.48550/arXiv.2507.18966.