Traffic Sign Recognition with Convolutional Neural Network
Authors:
- 3 August 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 48-53
Abstract
Traffic sign recognition is a computer vision technique to recognize the traffic signs put on the road. In this paper, a traffic sign dataset with approximately 5000 images is collected. This paper presents an ablation analysis of Multilayer Perceptron and Convolutional Neural Networks in traffic sign recognition. The ablation analysis studies the effects of different architectures of Multilayer Perceptron and Convolutional Neural Networks, batch normalization, and dropout. A total of 8 different models are reviewed and their performance is studied. The experimental results demonstrate that Convolutional Neural Networks outperform Multilayer Perceptron in general. Leveraging dropout layer and batch normalization is effective in improving the stability of the model and achieved 98.62% accuracy in traffic sign recognition.Keywords
Funding Information
- Ministry of Higher Education
This publication has 7 references indexed in Scilit:
- Hand gesture recognition via enhanced densely connected convolutional neural networkExpert Systems with Applications, 2021
- Convolutional neural network with spatial pyramid pooling for hand gesture recognitionNeural Computing and Applications, 2020
- A four dukkha state-space model for hand trackingNeurocomputing, 2017
- Gait recognition using binarized statistical image features and histograms of oriented gradients2017
- Robust classification of traffic signs using multi-view cues2012
- Statistical and entropy based multi purpose human motion analysis2010
- Road-Sign Detection and Recognition Based on Support Vector MachinesIEEE Transactions on Intelligent Transportation Systems, 2007