Traffic Sign Recognition Using CNN
Authors:
- 23 April 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Nowadays, technology is growing very fast with automation in all aspects and still research is going on to introduce more and more algorithms to reduce human work. In this regard, Artificial intelligence is playing a major role. One of the greatest inventions using artificial intelligence is automated vehicles. In which there is no need for human interaction to drive the vehicle. Utmost care should be taken for the safe driving of autonomous vehicles. For autonomous cars or vehicles, recognition of the traffic signs is the major consideration for safe driving. So, to recognize and classify the traffic signs on the road, in this paper proposed method is Traffic sign recognition using CNN and Keras frameworks using a deep learning algorithm. CNN is the best algorithm used in so many image analysis tasks like image recognition and object detection. Not only may this strategy be used to minimize accidents caused by human error, but it can also be used to reduce accidents caused by human error. An accuracy of 96.8% was achieved using this method.Keywords
This publication has 12 references indexed in Scilit:
- Indian Traffic Sign Board Recognition and Driver Alert System Using CNN2020
- Traffic signs recognition with deep learning2018
- Traffic sign detection — A new approach and recognition using convolution neural network2017
- Traffic sign recognition using convolutional neural networks2017
- Automatic traffic sign detection and recognition in video sequences2017
- CNN Design for Real-Time Traffic Sign RecognitionProcedia Engineering, 2017
- Tracking traffic signs in video sequences based on a vehicle velocityComputer Optics, 2015
- Detection and classification of speed limit traffic signs2014
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012
- The German Traffic Sign Recognition Benchmark: A multi-class classification competition2011