Copyright © 2025 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{178767,
        author = {Jeevitha.P and Thiyanadurai C and Ariharan V and Selvakumar K and Vijayaragavan S},
        title = {Traffic Sign Recognition system using CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4990-4996},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178767},
        abstract = {A dynamic component of intelligent transportation systems, traffic sign recognition is essential to sophisticated driver-assistance systems and driverless cars. This study proposes a CNN-based TSR system that integrates preprocessing, segmentation, feature extraction, and classification to accurately detect and recognize traffic signs in real-world environments. In the preprocessing phase, techniques such as Gaussian filtering for noise reduction, histogram equalization for contrast enhancement, and grayscale conversion are applied to improve image quality. The segmentation process utilizes Otsu’s thresholding to isolate traffic signs from the background. For feature extraction a Gray Level Co-occurrence Matrix, deep learning-based methods using convolutional layers capture essential features like shape, texture, and color patterns. Finally, in the classification stage, a Convolutional Neural Network to accurately categorize traffic signs. To evaluate system performance, various performance metrics such as accuracy 95.5%, precision 94.8%, recall 95.9%, F1-score 96.2%, and Specificity 96.8% are utilized. The combination of image processing and deep learning techniques enhances the system's efficiency and reliability, making it suitable for real-time traffic sign recognition in autonomous vehicles and smart traffic management systems.},
        keywords = {Traffic Sign Recognition, Gaussian filtering, Gray Level Co-occurrence Matrix, Convolutional Neural Network, Otsu’s thresholding.},
        month = {May},
        }