This paper presents a hybrid approach to traffic sign recognition that combines classical preprocessing techniques (color segmentation, contour detection, Haar Cascade, and HOG) with a lightweight Convolutional Neural Network (CNN) for classification. The proposed method reduces the amount of processed image data by a factor of 10–20, as only preselected regions of interest are passed to the neural network. The CNN, trained on the GTSRB dataset with data augmentation, achieved 100% accuracy on the test set, with precision and recall values ranging from 0.97 to 1.00 across individual classes. Compared to direct full-image classification using CNN alone, the hybrid pipeline ensured over 5× faster inference, making it suitable for real-time deployment on embedded platforms such as Raspberry Pi or mobile robotic systems. The practical significance of this work lies in its applicability to low-cost ADAS solutions and autonomous transport platforms. Future research directions include integration with real-time video streams and expansion to a wider range of traffic sign categories.
[1] 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, https://doi.org/10.1016/j.neunet.2012.02.016.
[2] P. Sermanet and Y. LeCun, "Traffic Sign Recognition with Multi-Scale Convolutional Networks," International Joint Conference on Neural Networks (IJCNN), Barcelona, Spain, 2011, pp. 2809-2813, https://doi.org/10.1109/IJCNN.2011.6033589.
[3] S. Houben, J. Stallkamp, J. Salmen, M. Schlipsing and C. Igel, "Detection of Traffic Signs in Real-World Images: The German Traffic Sign Detection Benchmark," International Joint Conference on Neural Networks (IJCNN), Dallas, TX, USA, 2013, pp. 1-8, https://doi.org/10.1109/IJCNN.2013.6706807.
[4] K. Simonyan, A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition”, arXiv preprint arXiv:1409.1556, 2014 https://arxiv.org/abs/1409.1556
[5] A. Youssef, D. Albani, D. Nardi and D. D. Bloisi, "Fast Traffic Sign Recognition Using Color Segmentation and Deep Convolutional Networks," Lecture Notes in Computer Science, vol. 10016, pp. 221-230, Oct. 2016, https://doi.org/10.1007/978-3-319-48680-2_19.
[6] X. Qiao, "Research on Traffic Sign Recognition Based on CNN Deep Learning Network," ScienceDirect, 2023, https://www.sciencedirect.com/science/article/pii/S1877050923019336.
[7] M. Abadi, A. Agarwal, P. Barham et al., "TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems," arXiv preprint arXiv:1603.04467, 2016, https://doi.org/10.48550/arXiv.1603.04467.
[8] H.B. Fredj, "An Efficient Implementation of Traffic Signs Recognition Using CNN for Unconstrained Environments," ScienceDirect, 2023, https://doi.org/10.1016/j.micpro.2023.104791.