Abstract
With the revolutionary advancements in technologies such as machine learning and artificial intelligence, many big companies such as Google, Tesla, and Uber are working on creating autonomous vehicles or self-driving cars. Traffic sign recognition (TSR) plays a really important role in this as it is essential for vehicles to understand and follow all traffic rules to assure the safety of the passengers as well as other drivers and pedestrians on the road. In this paper, we study how traffic signs recognition can be done using machine learning. The dataset that we have used is taken from Kaggle and will contain around 50,000 images divided into various different classes. This dataset will be used for testing as well as training our model. We will be trying out two major approaches used in traffic sign recognition. Our approach is based on convolution neural network (CNN) in which we vary some parameters and prepare a comparative study of how these factors affect the accuracy of our model. After comparing the accuracy of our models, we have implemented the best performing model in a web application using Flask. Also, we have included the text-to-speech feature which speaks the result to the user and makes our project more accessible.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
P. Pacl´ık, J. Novoviˇcov´a, R.P.W. Duin, Building roadsign classifiers using a trainable similarity measure. IEEE Trans. Intell. Transp. Syst. 7(3), 309–321 (2006)
A. Bouti, M.A. Mahraz, J. Riffi, H. Tairi, A robust system for road sign detection and classification using LeNet architecture based on convolutional neural network. Soft Comput. 1–13 (2019)
J. Greenhalgh, M. Mirmehdi, in Traffic Sign Recognition Using MSER and Random Forests, Proceedings of the 20th European Signal Processing Conference (EUSIPCO’12), pp. 1935–1939, Aug 2012
J. Jin, K. Fu, C. Zhang, Traffic sign recognition with hinge loss trained convolutional neural networks. IEEE Trans. Intell. Transp. Syst. 15(5), 1991–2000 (2014)
G. Overett, L. Petersson, in Large Scale Sign Detection Using HOG Feature Variants. Proceedings of the IEEE Intelligent Vehicles Symposium (IV ’11), pp. 326–331, Baden-Baden, Germany, June 2011
M.M. Møgelmose, M. Trivedi, T.B. Moeslund, Visionbased traffic sign detection and analysis for intelligent driver assistance systems: perspectives and survey. IEEE Trans. Intell. Transp. Syst. 13(4), 1484–1497 (2012)
S. Vitabile, G. Pollaccia, G. Pilato, E. Sorbello, in Road Signs Recognition Using a Dynamic Pixel Aggregation Technique in the HSV Color Space. Proceedings of the 11th International Conference on Image Analysis and Processing (ICIAP ’01), pp. 572–577, Palermo, Italy, Sept 2001
D.M. Gavrila, in Traffic Sign Recognition Revisited. Mustererkennung 1999: 21. DAGM-Symposium Bonn, 15–17. September 1999, pp. 86–93, Springer, Berlin, Germany (1999)
B. H¨o4ferlin, K. Zimmermann, in Towards Reliable Traffic Sign Recognition. Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 324–329, Xi’an, China, June 2009
R. Mandal et al., in City Traffic Speed Characterization Based on City Road Surface Quality, ed. by J.M.R.S. Tavares, S. Dutta, S. Dutta, D. Samanta, Cyber Intelligence and Information Retrieval. Lecture Notes in Networks and Systems, vol. 291 (Springer, Singapore). https://doi.org/10.1007/978-981-16-4284-5_45
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sheoran, K., Chirag, Chhabra, K., Sagar, A.K. (2023). Traffic Sign Recognition Using CNN. In: Dutta, P., Bhattacharya, A., Dutta, S., Lai, WC. (eds) Emerging Technologies in Data Mining and Information Security. Advances in Intelligent Systems and Computing, vol 1348. Springer, Singapore. https://doi.org/10.1007/978-981-19-4676-9_40
Download citation
DOI: https://doi.org/10.1007/978-981-19-4676-9_40
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-4675-2
Online ISBN: 978-981-19-4676-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)