SavedAdd your journal

Journals / International Advanced Researches and Engineering Journal / 2026 / Volume: 10 Issue: 2

Middle-East Traffic Sign (METS) recognition: databases and models

Elena Battini Sonmez(İSTANBUL BİLGİ ÜNİVERSİTESİ)0000-0003-0090-984X
Hamza Arnaout(ISTANBUL BILGI UNIVERSITY)0009-0002-7350-902X
Albano Younes(ISTANBUL BILGI UNIVERSITY)0009-0009-9113-6985
Pages
—
Publication Date
2026-08-25
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The same architecture is also very successful when tested on the newly introduced picture collection.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Automatic Traffic Sign Recognition is a crucial sub-task for autonomous driving, playing a key role in reducing accidents and enabling safer, more intelligent navigation on the roads.
📊
Key Findings & Data:This paper reviews the current state-of-the-art in automatic Arabic road-signs recognition; it proposes a new model, which improves the best performance of existing databases; it merges the Arabic Traffic Signs collection with the Jordanian dataset, and it uses several data augmentation techniques to create the largest publicly available database in the Arabic world to date.
💡
Conclusion & Impact:The same architecture is also very successful when tested on the newly introduced picture collection.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:Arabic traffic sign recognition · Computer vision · Convolutional neural networks

Abstract

Automatic Traffic Sign Recognition is a crucial sub-task for autonomous driving, playing a key role in reducing accidents and enabling safer, more intelligent navigation on the roads. This challenge remains largely unresolved in the Arabic world, unlike other regions. This paper reviews the current state-of-the-art in automatic Arabic road-signs recognition; it proposes a new model, which improves the best performance of existing databases; it merges the Arabic Traffic Signs collection with the Jordanian dataset, and it uses several data augmentation techniques to create the largest publicly available database in the Arabic world to date. Finally, it gives a benchmark algorithm for the newly introduced collection. The proposed model is a variation of the lightweight Residual Net architecture, which has been improved by a significant reduction in the number of parameters, minimization of down-sampling to maintain as much spatial detail as possible, and the incorporation of both Dropout and Batch Normalization to ensure better regularization and overfitting prevention. The performance of the introduced model on the Arabic Traffic Sign database surpasses the current state of the art in both accuracy and training time. The same architecture is also very successful when tested on the newly introduced picture collection.

🔖

Cite This Article

Sonmez, E. B., Arnaout, H., Younes, A. (2026). Middle-East Traffic Sign (METS) recognition: databases and models. International Advanced Researches and Engineering Journal, Volume: 10 Issue: 2. https://doi.org/10.35860/iarej.1841529

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (25)

  1. Hwei, K., Jordanian (Arabic) traffic signs in yolo format. https://www.kaggle.com/datasets/khaledhweij/Jordanian-traffic-signs. (Last access: 15.08.2026).
  2. Latif, G., J. Alghazo, D.A. Alghmgham and L. Alzubaidi, ArTS: Arabic traffic sign dataset. Mendeley Data. 2020. (Last access: 15.08.2026).
  3. Vincent, M. A., K.R. Vidya and P.M. Santhosh, Traffic Sign Classification using Deep Neural Network. IEEE Recent Advances in Intelligent Computational Systems (RAICS). 2020. India: p. 13–17.
  4. Stallkamp, J., M. Schlipsing, J. Salmen and C. Igel, The German Traffic Sign Recognition Benchmark: A Multi-Class Classification Competition. International Joint Conference on Neural Networks. 2021. CA, USA: p. 1453–1460.
  5. Jonah, S. and S. Orike, Traffic Sign Classification Comparison Between Various Convolution Neural Network Models. International Journal of Scientific and Engineering Research, 2021. 12: p. 165–171.
  6. Kerim, A. and M. Efe, Recognition of Traffic Signs with Artificial Neural Networks: A Novel Dataset and Algorithm. International Conference on Artificial Intelligence in Information and Communication (ICAIIC). 2021. Korea (South): p. 171–176.
  7. Zaibi, A., A. Ladgham and A. Sakly, Lightweight Model for Traffic Sign Classification Based on Enhanced LeNet-5 Network. Journal of Sensors, 2021. 1: p. 8870529.
  8. Timofte, R., K. Zimmermann and L. van Gool, Multi-View Traffic Sign Detection, Recognition, and 3D Localization. Ninth IEEE Computer Society Workshop on Application of Computer Vision. 2009. Utah, USA: p. 1–8.
  9. Lecun, Y., L. Bottou, Y. Bengio and P. Haffner, Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998. 86 (11): p. 2278–2324.
  10. Syed Abudhagir, U. and N. Ashok, Highly Sensitive Deep Learning Model for Road Traffic Sign Identification. Mathematical Statistician and Engineering Applications, 2022. 71 (4).
  11. Bhatt, N., P. Laldas and V.B. Lobo, A Real-Time Traffic Sign Detection and Recognition System on Hybrid Dataset Using CNN. 7th International Conference on Communication and Electronics Systems (ICCES). 2022. India: p. 1354–1358.
  12. Ay, G., A. Durdu and B. Nesimioglu, Accuracy Comparison of CNN Networks on GTSRB Dataset. Journal of Artificial Intelligence and Data Science, 2022. 2: p. 63–68.
  13. Zheng, Y. and W. Jiang, Evaluation of Vision Transformers for Traffic Sign Classification. Wireless Communications and Mobile Computing, 2022. 1: p. 3041117.
  14. Lim, X., C. Lee, K. Lim, T. Ong, A. Alqahtani and A. Ali, Recent Advances in Traffic Sign Recognition: Approaches and Datasets. Sensors (Basel) 2023. 23(10): p. 46–74.
  15. Qu, S., X. Yang, H. Zhou and Y. Xie, Improved Yolov5-Based for Small Traffic Sign Detection Under Complex Weather. Scientific Reports 2023. 13: p. 16219.
  16. Wang, J., Y. Chen, Z. Dong and M.Gao, Improved YoloV5 Network for Real- Time Multi-Scale Traffic Sign Detection. Neural Computing and Applications, 2023. 35(10): p. 7853–7865.
  17. Lu, Z., Z. Zhu, G. Li and J. Chen, Enhancing Small Target Traffic Sign Detection with ML_SAP in YoloV5s. Scientific Reports, 2024. 14(1): p. 25904.
  18. Luo, Y., Y. Ci, S. Jiang and X. Wei, A Novel Lightweight Real-Time Traffic Sign Detection Method Based on an Embedded Device and YoloV8. Real-Time Image Proc, 2024. 21(2).
  19. Han, Y., F. Wang, W. Wang, X. Zhang and X. Li, End-Yolo: Multi-Scale Traffic Sign Detection Method in Complex Scenes. Digital Signal Processing, 2024. 153: p. 104615.
  20. Tran, H., N. Nguyen, N. Le, T. Le and A.D. Nguyen, Grounding Dino and Distillation-Enhanced Model for Advanced Traffic Sign Detection and Classification. International Journal of Autonomous Vehicles, Engineering Science and Technology, 2025. 64: p. 102028.
  21. Guo, Z., Y. Wang and N. Chen, LAR-TSDETR: a lightweight adaptive robust traffic sign detection transformer with multi-scale fusion for real-time recognition under challenging conditions. Measurement Science and Technology, 2025. 36: p.096129.
  22. Latif, G., D.A. Alghmgham, R. Maheswar, J. Alghazo, F. Sibai and M.H. Aly, Deep Learning in Transportation: Optimized Driven Deep Residual Networks for Arabic Traffic Sign Recognition. Alexandria Engineering Journal, 2023. 80: p. 134–143.
  23. Alqahtani, A., E. Alqaysi, W. Alsarhani, C. Lee, A. Alsharafi, M. Alzahrani and A. Almosa, MobileVITv2-MLP: Arabic Traffic Sign Recognition with Enhanced Lightweight Vision Transformers. In Proc. SPIE 13517, 17th International Conference on Machine Vision (ICMV). 2024. Edinburg, UK.
  24. Alqahtani, A. and M. Naseer, Enhancing Arabic traffic sign recognition through synthetic data generation using diffusion models. In Proc. SPIE 14114, 18th International Conference on Machine Vision (ICMV). 2026. Paris, FR.
  25. He K., X. Zhang, S. Ren and J. Sun, Deep Residual Learning for Image Recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016.