An Optimized Deep Learning Approach for Automatic License Plate Detection and Recognition

DOI

10.2991/978-94-6239-664-7_45How to use a DOI?

Keywords

Automated License Plate Recognition (ALPR); Traffic Law Enforcement; Optical Character Recognition (OCR); Real time Object Detection; Cloud Computing; You Only Look Once; Image Processing

Abstract

The rapid increase of vehicles and the growth of smart transportation systems have created a strong demand for accurate and efficient Automated License Plate Recognition (ALPR) systems. This research presents an end-to-end ALPR framework optimized for Bangladeshi license plates, addressing challenges such as non-standardized designs, two-line formats, and bilingual text (Bengali and English). The proposed system integrates state-of-the-art object detection models—YOLOv5x, YOLOv8x, and YOLOv11—for precise and real-time license plate localization, while EasyOCR is employed for robust character recognition. A custom dataset of 3,500 annotated images was developed, covering diverse environmental conditions, vehicle types, lighting variations, and plate styles. To improve model robustness, extensive data augmentation was applied, including geometric transformations, photometric adjustments, and simulated weather effects such as fog and rain. Experimental results demonstrate that the system achieves high detection and recognition accuracy, with YOLOv11S providing the best trade-off between speed and performance. The proposed framework is suitable for practical applications such as digital toll collection, automated parking, vehicle identification, and traffic law enforcement, offering a reliable and real-time solution tailored for Bangladeshi roads.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nusrat Jahan Bristy
AU  - Rakib Rizan
AU  - Abu Kausar
AU  - Amir Hossen
AU  - Arjun Sutradhar
AU  - Md. Humaun Kabir
PY  - 2026
DA  - 2026/06/08
TI  - An Optimized Deep Learning Approach for Automatic License Plate Detection and Recognition
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 648
EP  - 663
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_45
DO  - 10.2991/978-94-6239-664-7_45
ID  - Bristy2026
ER  -