Welcome to the InfoSci Platform
Reference Hub1
Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures

Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures

Utkarsh Dubey, Rahul Kumar Chaurasiya
Copyright: © 2021 |Volume: 15 |Issue: 4 |Pages: 19
ISSN: 1557-3958|EISSN: 1557-3966|EISBN13: 9781799859857|DOI: 10.4018/IJCINI.295811
Cite Article Cite Article

MLA

Dubey, Utkarsh, and Rahul Kumar Chaurasiya. "Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures." IJCINI vol.15, no.4 2021: pp.1-19. http://doi.org/10.4018/IJCINI.295811

APA

Dubey, U. & Chaurasiya, R. K. (2021). Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 15(4), 1-19. http://doi.org/10.4018/IJCINI.295811

Chicago

Dubey, Utkarsh, and Rahul Kumar Chaurasiya. "Efficient Traffic Sign Recognition Using CLAHE-Based Image Enhancement and ResNet CNN Architectures," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 15, no.4: 1-19. http://doi.org/10.4018/IJCINI.295811

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Recognition and classification of traffic signs and other numerous displays on the road are very crucial for autonomous driving, navigation, and safety systems on roads. Machine learning or deep learning methods are generally employed to develop a traffic sign recognition (TSR) system. This paper proposes a novel two-step TSR approach consisting of contrast limited adaptive histogram equalization (CLAHE)-based image enhancement and convolutional neural network (CNN) as multiclass classifier. Three CNN architectures viz. LeNet, VggNet, and ResNet were employed for classification. All the methods were tested for classification of German traffic sign recognition benchmark (GTSRB) dataset. The experimental results presented in the paper endorse the capability of the proposed work. Based on experimental results, it has also been illustrated that the proposed novel architecture consisting of CLAHE-based image enhancement & ResNet-based classifier has helped to obtain better classification accuracy as compared to other similar approaches.