Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203320,
        author = {Gobinath and Rajarajeshwari and Dhanush and Gopinath},
        title = {AI BASED TRAFFIC SIGN RECOGNITION FOR SMART VEHICLES},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10616-10627},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203320},
        abstract = {Traffic signs play a crucial role in maintaining road safety and guiding drivers by providing important information regarding speed limits, warnings, and traffic regulations. However, drivers may fail to notice or correctly interpret traffic signs due to fatigue, distractions, poor weather conditions, or low visibility, which can lead to serious road accidents. To address this issue, this project presents an AI-Based Traffic Sign Recognition System for Smart Vehicles that automatically detects and classifies traffic signs in real time using deep learning and computer vision techniques.
The proposed system utilizes a vehicle-mounted camera to capture road images continuously. The captured images undergo preprocessing operations such as resizing, normalization, and data augmentation to improve image quality and enhance model robustness. A Convolutional Neural Network (CNN) and YOLO-based object detection approach are employed to identify and classify different categories of traffic signs accurately. The model is trained using a standard traffic sign dataset containing multiple classes of road signs. The system is designed to provide fast and reliable recognition suitable for real-time smart vehicle applications.
Performance evaluation is carried out using metrics such as accuracy, precision, recall, F1-score, and processing speed. Experimental results demonstrate that the proposed system achieves high recognition accuracy with low latency, making it effective for 
practical intelligent transportation systems and Advanced Driver Assistance Systems (ADAS). The optimized architecture balances computational efficiency and detection performance, enabling deployment in embedded smart vehicle environments.
The developed system contributes to improving road safety, reducing driver errors, and supporting autonomous driving technologies. Future enhancements may include multilingual sign recognition, weather-adaptive models, and integration with fully autonomous vehicle control systems for enhanced intelligent transportation capabilities.},
        keywords = {Artificial Intelligence (AI), Traffic Sign Recognition, Deep Learning, Convolutional Neural Network (CNN), YOLO, Computer Vision, Smart Vehicles.},
        month = {May},
        }