Brazilian Automatic License Plate Recognition: On the Importance to Add Vehicle Detection Phase in a Deep Learning Approach

• Lucas Mity Kamado IFSP
• Murilo Varges da Silva IFSP

DOI: https://doi.org/10.5753/wvc.2023.27529

Resumo

In recent years, surveillance cameras have found wide-ranging applications, particularly in automatic vehicle license plate recognition to enhance security. One of the major problems of performing vehicle license plate recognition is the wide variety of existing license plate standards around the world, only in Brazil there are two standards, in addition, automatic license plate recognition depends directly on the quality of the input image. The objective of this paper is to evaluate whether adding the vehicle detection step improves license plate recognition rates in a deep learning approach. The method was implemented using the YOLOv8s model in all stages, however, two different approaches were proposed, one with and the other without the vehicle detection stage, the database used was the UFPR-ALPR, which only presents plates of the old Brazilian standard of 3 letters and 4 numbers.

Palavras-chave: ALPR, Deep Learning, YOLOv8s

Referências

P. Agarwal, K. Chopra, M. Kashif, and V. Kumari, “Implementing alpr for detection of traffic violations: a step towards sustainability,” Procedia Computer Science, vol. 132, pp. 738–743, 2018.

G. L. Corneto, F. A. da Silva, D. R. Pereira, L. L. de Almeida, A. O. Artero, J. P. Papa, V. H. C. de Albuquerque, and H. M. Sapia, “A new method for automatic vehicle license plate detection,” IEEE Latin America Transactions, vol. 15, no. 1, pp. 75–80, 2017.

C. Henry, S. Y. Ahn, and S.-W. Lee, “Multinational license plate recognition using generalized character sequence detection,” IEEE Access, vol. 8, pp. 35 185–35 199, 2020.

CONTRAN, “Resolução contran nº 231 de 15/03/2007,” [link], 3 2007.

——, “Resolução contran nº 510 de 27/11/2014,” [link], 12 2014.

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.

J. Shashirangana, H. Padmasiri, D. Meedeniya, and C. Perera, “Automated license plate recognition: a survey on methods and techniques,” IEEE Access, vol. 9, pp. 11 203–11 225, 2020.

R. Laroca, E. Severo, L. A. Zanlorensi, L. S. Oliveira, G. R. Gonçalves, W. R. Schwartz, and D. Menotti, “A robust real-time automatic license plate recognition based on the yolo detector,” in 2018 international joint conference on neural networks (ijcnn). IEEE, 2018, pp. 1–10.

J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.

G. Jocher, A. Chaurasia, and J. Qiu, “YOLO by Ultralytics,” 1 2023. [Online]. Available: [link]