Enhancing Road Safety Education Using an AI-Driven Mobile Traffic Sign Recognition System

Road safety education plays a crucial role in reducing traffic accidents, particularly among novice drivers who often struggle to recognize and recall traffic signs in real-world situations. Conventional learning methods such as manuals and classroom instruction lack interactivity and contextual visualization. To address this limitation, this study proposes an AI-powered mobile application for traffic sign recognition using a TensorFlow Lite model. The system enables real-time detection of Malaysian traffic signs through a smartphone camera or image selection, providing instant sign identification and explanatory information. In addition to detection, the application incorporates learning mode, scan history tracking, and quiz-based assessments to enhance user engagement and knowledge retention. The system was developed using Flutter for the mobile interface, a PHP-based backend, and a MySQL database for content management. Experimental evaluation demonstrates that the proposed system achieves accurate traffic sign recognition while offering significant educational value through its interactive features. The findings indicate that integrating lightweight AI models with mobile learning applications can effectively support traffic sign education and promote road safety awareness.

Traffic Sign Recognition, TensorFlow Lite, Mobile Learning, Artificial Intelligence

1. Gangoso, E. P. J., Aca-ac, R. J. R., & Sarabia, P. Z. G. (2025). Real-time mobile app traffic sign recognition with YOLOv10 and CNN for driving education. The International Journal of Computational Science, Information Technology and Control Engineering, 12(2). https://doi.org/10.5121/ijcsitce.2025.12201 [Google Scholar] [Crossref]

2. Benhamida, A., Varkonyi-Koczy, A. R., & Kozlovszky, M. (2020). Traffic Signs Recognition in a mobile-based application using TensorFlow and Transfer Learning technics. IEEE, 000537–000542. https://doi.org/10.1109/sose50414.2020.9130519 [Google Scholar] [Crossref]

3. Loghashankar, H., & Nguyen, H. (2023). Real-Time traffic sign detection: a case study in a Santa Clara suburban neighborhood. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2310.09630 [Google Scholar] [Crossref]

4. Vázquez-Cano, E., & Castañeda, L. F. (2022). Mobile learning and its effect on learning outcomes and critical thinking. Applied Sciences, 14(19), 9105. https://doi.org/10.3390/app14199105 [Google Scholar] [Crossref]

5. Arinova, B., Pyatkina, D., Latysheva, V., & Stroiteleva, N. (2022). Mobile applications in education: Implementation aspects and impact on student competencies development. International Journal of Web-Based Learning and Teaching Technologies, 17(1), 1–17. https://doi.org/10.4018/IJWLTT.305805 [Google Scholar] [Crossref]

6. Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., & Hu, S. (2016). Traffic-sign detection and classification in the wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2110–2118. https://doi.org/10.1109/CVPR.2016.232 [Google Scholar] [Crossref]

7. A. Howard et al., "Searching for MobileNetV3," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 1314-1324. https://doi.org/10.1109/ICCV.2019.00140 [Google Scholar] [Crossref]

8. Naveed, Q. N., Choudhary, H., Ahmad, N., Alqahtani, J., & Qahmash, A. I. (2023). Mobile Learning in Higher Education: A Systematic Literature review. Sustainability, 15(18), 13566. https://doi.org/10.3390/su151813566 [Google Scholar] [Crossref]

9. Shinar, D., & Vogelzang, M. (2013). Comprehension of traffic signs with symbolic versus text displays. Transportation Research Part F Traffic Psychology and Behaviour, 18, 72–82. https://doi.org/10.1016/j.trf.2012.12.012 [Google Scholar] [Crossref]

10. Kumar, R., & Sharma, P. (2025). Leveraging interactive mobile Technologies for Enhanced learning Outcomes A Systematic review. Journal Mobile Technologies (JMS), 3(1), 1–8. https://doi.org/10.59431/jms.v3i1.540 [Google Scholar] [Crossref]

11. Stallkamp, J., Schlipsing, M., Salmen, J., & Igel, C. (2012). Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Networks, 32, 323–332. https://doi.org/10.1016/j.neunet.2012.02.016 [Google Scholar] [Crossref]

12. Cireşan, D. C., Meier, U., Masci, J., & Schmidhuber, J. (2012). Multi-column deep neural network for traffic sign classification. Neural Networks, 32, 333–338. https://doi.org/10.1016/j.neunet.2012.02.023 [Google Scholar] [Crossref]

13. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). SSD: Single shot multibox detector. European Conference on Computer Vision (ECCV), 21–37. https://doi.org/10.1007/978-3-319-46448-0_2 [Google Scholar] [Crossref]

14. Maldonado-Bascón, S., Lafuente-Arroyo, S., Gil-Jiménez, P., Gómez-Moreno, H., & López-Ferreras, F. (2007). Road-sign detection and recognition based on support vector machines. IEEE Transactions on Intelligent Transportation Systems, 8(2), 264–278. https://doi.org/10.1109/TITS.2007.895311 [Google Scholar] [Crossref]

15. Chen, L., Chen, P., & Lin, Z. (2020). Artificial intelligence in education: A review. IEEE Access, 8, 75264–75278. https://doi.org/10.1109/ACCESS.2020.2988510 [Google Scholar] [Crossref]

• Smart Iot Device for Weather And Health
• Merlarchive: A Web-Based Academic Hub for UDM With AI-Powered Natural Language Processing
• Enhanced Social Network Security System: Integrating Biometric Authentication for Improved User Verification and Privacy Protection
• Smart Budget Allocation in Public Policy: A Data-Driven Approach for Equitable Resource Distribution
• Decision Support System for Faculty Selection, Promotion, and Reclassification Using Predictive Analytics