Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69142
Volume:
10 |
11 |
Nov 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Computer Engineering
SVPM's College of Engineering, Malegaon (Bk), Baramati

Department of Computer Engineering
SVPM's College of Engineering, Malegaon (Bk), Baramati

Department of Computer Engineering
SVPM's College of Engineering, Malegaon (Bk), Baramati
Department of Computer Engineering
SVPM's College of Engineering, Malegaon (Bk), Baramati
Traffic signs communicate mandatory regulations, hazard warnings, and directional guidance essential for safe road navigation. However, manual sign recognition by human drivers can be degraded by distraction, fatigue, high vehicle speeds, poor illumination, adverse weather, and partial occlusion. This paper presents the design and implementation framework of an automated Traffic Sign Recognition System based on a Convolutional Neural Network (CNN). The system utilizes the German Traffic Sign Recognition Benchmark (GTSRB), comprising more than 50,000 labelled images distributed across 43 traffic-sign categories. The proposed processing pipeline accepts an input image via camera capture or file upload, applies standardized image preprocessing (resizing, normalization, and noise filtering), extracts hierarchical spatial features through convolutional and pooling layers, and predicts the traffic-sign class alongside a softmax confidence score. Furthermore, this manuscript establishes a rigorous evaluation protocol encompassing overall accuracy, macro-averaged precision, macro-averaged recall, F1-score, inference latency, and a 43 × 43 confusion matrix. Because completed training logs and held-out experimental metrics are pending final execution, placeholders are explicitly reserved for empirical validation prior to final publication.
KEYWORDS
This paper presented the system architecture, preprocessing pipeline, CNN feature-extraction design, and quantitative evaluation protocol for a Traffic Sign Recognition System trained on the 43-class GTSRB dataset. By combining standardized image preprocessing with deep convolutional feature learning and softmax confidence estimation, the framework establishes a structured foundation for driver-assistance applications. Populating the reserved experimental evaluation tables with held-out test metrics and confusion-matrix diagnostics will complete the empirical validation required for journal publication.
[1] J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, “The German Traffic Sign Recognition Benchmark: A Multi-Class Classification Competition,” In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), pp. 1453–1460, 2011, doi: 10.1109/IJCNN.2011.6033395. [2] J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, “Man vs. Computer: Benchmarking Machine Learning Algorithms for Traffic Sign Recognition,” Neural Networks, vol. 32, pp. 323–332, 2012, doi: 10.1016/j.neunet.2012.02.016. [3] P. Sermanet and Y. LeCun, “Traffic Sign Recognition with Multi-Scale Convolutional Networks,” In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), pp. 2809–2813, 2011, doi: 10.1109/IJCNN.2011.6033589. [4] X. R. Lim, C. P. Lee, K. M. Lim, and T. S. Ong, “Enhanced Traffic Sign Recognition with Ensemble Learning,” Journal of Sensor and Actuator Networks, vol. 12, no. 2, Art. no. 33, 2023, doi: 10.3390/jsan12020033. [5] A. M. Al-Khafaji et al., “The Implications of Weather and Reflectivity Variations on Automatic Traffic Sign Recognition Performance,” Advances in Civil Engineering, vol. 2021, Art. ID 5513552, 2021, doi: 10.1155/2021/5513552.
Publication Date
11/18/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
0
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...