End-to-End License Plate Detection and Recognition in Iraq Using a Detection Transformer and OCR
Article Sidebar
Main Article Content
Abstract
Automatic license plate recognition (ALPR) is essential for intelligent transportation systems, traffic monitoring, and law enforcement. Although deep learning has significantly progressed ALPR, the adaptation of these techniques to the specific characteristics of Iraqi plates presents challenges due to the variety of fonts, differing plate dimensions, and intricate real-world driving conditions. This paper presents an end-to-end Automatic License Plate Recognition (ALPR) framework specifically designed for Iraqi license plates. This system integrates a Detection Transformer (DETR) for the identification of plates alongside a Convolutional Recurrent Neural Network (CRNN)-based Optical Character Recognition (OCR) module for the purpose of character recognition. The system is trained and evaluated on a newly developed dataset of 1,000 annotated images representing diverse driving scenarios in Iraq. It achieves a mean Average Precision (mAP@[.5:.95]) of 0.91 for detection and a full-plate OCR accuracy of 93%. The accuracy of DETR surpasses that of YOLOv5, Faster R-CNN, and SSD, as demonstrated by comparative experiments. Conversely, a lightweight transformer (DeiT-Tiny-Det) approaches DETR's performance at faster inference velocities, illustrating a practical trade-off between speed and precision. Ablation studies confirm the importance of robust detection for end-to-end accuracy, while error analysis shows that low-light and character-level confusions remain the main challenges. The results indicate that transformer-based detectors, in conjunction with specialised OCR models, yield dependable region-specific ALPR appropriate for real-world application.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
References
[1] J. Shashirangana, H. Padmasiri, D. Meedeniya, and C. Perera, “Automated license plate recognition: A survey on methods and techniques,” IEEE Access, vol. 9, pp. 11203–11225, Dec. 2020. https://doi.org/10.1109/ACCESS.2020.3047929.
[2] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 779–788. https://doi.org/10.1109/CVPR.2016.91
[3] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, Jun. 2017. https://doi.org/10.1109/TPAMI.2016.2577031
[4] Y. Al-Arbo and A. Alqassab, “Emerging challenges in adversarial deep learning for computer vision and cybersecurity,” Baghdad Science Journal, vol. 22, no. 8, art. 27, 2025.https://doi.org/10.21123/2411-7986.5038.
[5] N. R. Soora, V. K. Kotte, K. Dorthi, S. Vodithala, and N. C. Kumar, “A comprehensive literature review of vehicle license plate detection methods,” Traitement du Signal, vol. 41, no. 3, pp. 1129, 2024. https://doi.org/10.18280/ts.410304
[6] W. Liu et al., “SSD: Single Shot MultiBox Detector,” in Proc. ECCV, 2016, pp. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2
[7] Y. Al-Arbo and K. I. Alsaif, “Cars tracking based on YOLO for feature extraction,” in AIP Conference Proceedings, vol. 2475, no. 1, p. 070013, Mar. 2023. https://doi.org/10.1063/5.0104361
[8] W. Wang and J. Tu, “Research on license plate recognition algorithms based on deep learning in complex environment,” IEEE Access, vol. PP, pp. 1–1, 2020. https://doi.org/ 10.1109/ACCESS.2020.2994287
[9] S. Z. Masood, G. Shu, A. Dehghan, and E. G. Ortiz, “License plate detection and recognition using deeply learned convolutional neural networks,” arXiv preprint, Mar. 2017. [Online]. Available: https://arxiv.org/abs/1703.07330
[10] S. Vig, A. Arora, and G. Arya, “Automated license plate detection and recognition using deep learning,” in Advancements in Interdisciplinary Research, Communications in Computer and Information Science, vol. 1724, pp. 419–431, Springer, 2023.https://doi.org/10.1007/978-3-031-23724-9_39
[11] A. S. Abdali, A. H. Ali, and A. Al-Azawi, “Automatic license plate recognition: A comprehensive review on methods and techniques,” Array, vol. 10, p. 100085, Dec. 2021..https://doi.org/10.1109/ACCESS.2020.3047929
[12] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-End Object Detection with Transformers,” in Proc. ECCV, 2020, pp. 213–229. https://doi.org/10.1007/978-3-030-58452-8_13
[13] K. Wang, L. Lin, X. Wang, W. Zuo, and L. Zhang, “Scene Text Detection and Recognition: The Deep Learning Era,” Int. J. Computer Vision, vol. 129, no. 6, pp. 1619–1640, 2021.https://doi.org/10.1007/s11263-020-01369-0
[14] S. Zherzdev and A. Gruzdev, “Lprnet: License plate recognition via deep neural networks,” arXiv preprint arXiv:1806.10447, 2018. [Online]. Available: https://arxiv.org/abs/1806.10447
[15] Z. Chen et al., “Transformer-Based End-to-End Text Spotting with Explicit Alignment,” in Proc. CVPR, 2022.
https://doi.org/10.1007/978-3-031-19815-1_21
[16] B. Shi, X. Bai, and C. Yao, “An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 11, pp. 2298–2304, 2017. https://doi.org/10.1109/TPAMI.2016.2646371
[17] M. Baek, B. Lee, D. Han, S. Yun, H. Lee, and H. Lee, “Character Region Awareness for Text Detection,” in Proc. CVPR, 2019, pp. 9365–9374. [Online]. Available: https://openaccess.thecvf.com/
[18] L. S. Fernandes, F. H. S. Silva, E. Ohata, and A. G. Medeiros, “A robust automatic license plate recognition system for embedded devices,” in Proc. 9th Brazilian Conf. on Intelligent Systems (BRACIS), Rio Grande, Brazil, Oct. 2020, Lecture Notes in Computer Science, vol. 12469, pp. 226–239. https://doi.org/10.1007/978-3-030-61377-8_16
[19] W. Russell et al., “LabelMe: A Database and Web-Based Tool for Image Annotation,” International Journal of Computer Vision, vol. 77, no. 1-3, pp. 157–173, 2008. https://doi.org/10.1007/s11263-007-0090-8
[20] T.-Y. Lin et al., “Microsoft COCO: Common Objects in Context,” in Proc. ECCV, 2014, pp. 740–755. https://doi.org/10.1007/978-3-319-10602-1_48.
[21] E. Gonçalves et al., “Benchmark for License Plate Character Segmentation,” Journal of Electronic Imaging, vol. 29, no. 1, 2020. https://doi.org/10.1117/1.JEI.25.5.053034
[22] M. N. Kadhim, A. H. Mutlag, and D. A. Hammood, “Multi-models based on Yolov8 for identification of vehicle type and license plate recognition,” in New Trends in Information and Communications Technology Applications. NTICT 2023, A. M. Al-Bakry et al., Eds., Communications in Computer and Information Science, vol. 2096. Cham: Springer, 2024, pp. 118–135. https://doi.org/10.1007/978-3-031-62814-6_9.
[23] W. G. Yass and M. Faris, “A comprehensive review of deep learning and machine learning techniques for real-time car detection and wrong-way vehicle tracking,” Babylonian Journal of Machine Learning, 2023, pp. 78–90, Nov. 2023
https://doi.org/10.58496/BJML/2023/013.
[24] H. Li, P. Wang, and C. Shen, “Toward End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline,” in Proc. ICPR, 2018, pp. 3576–3581. [Online]. Available: https://openaccess.thecvf.com
[25] F. H. Faraj, “Modelling an automatic recognition system for Iraq vehicle license plates by MATLAB,” J. Millimeterwave Commun., Optim. Model., vol. 1, no. 1, pp. 1–5, Nov. 2021. [Online]. Available: https://www.jomcom.org/index.php/1/article/view/13/3