Traffic sign recognition using convolutional neural networks
Open Access
- 5 March 2021
- journal article
- Published by Institute of Research and Community Services Diponegoro University (LPPM UNDIP) in Jurnal Teknologi dan Sistem Komputer
- Vol. 9 (2), 120-125
- https://doi.org/10.14710/jtsiskom.2021.13959
Abstract
Traffic sign recognition (TSR) can be used to recognize traffic signs by utilizing image processing. This paper presents traffic sign recognition in Indonesia using convolutional neural networks (CNN). The overall image dataset used is 2050 images of traffic signs, consisting of 10 kinds of signs. The CNN layer used in this study consists of one convolution layer, one pooling layer using maxpool operation, and one fully connected layer. The training algorithm used is stochastic gradient descent (SGD). At the training stage, using 1750 training images, 48 filters, and a learning rate of 0.005, the recognition results in 0.005 of loss and 100 % of accuracy. At the testing stage using 300 test images, the system recognizes the signs with 0.107 of loss and 97.33 % of accuracy.Keywords
Funding Information
- Universitas Mercu Buana Yogyakarta
This publication has 9 references indexed in Scilit:
- A survey of the recent architectures of deep convolutional neural networksArtificial Intelligence Review, 2020
- An Overview of Overfitting and its SolutionsJournal of Physics: Conference Series, 2019
- A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Advanced Driver-Assistance Systems: A Path Toward Autonomous VehiclesIEEE Consumer Electronics Magazine, 2018
- Review of advanced driver assistance systems (ADAS)AIP Conference Proceedings, 2017
- Three Decades of Driver Assistance Systems: Review and Future PerspectivesIEEE Intelligent Transportation Systems Magazine, 2014
- Towards fully autonomous driving: Systems and algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Evaluation of Pooling Operations in Convolutional Architectures for Object RecognitionLecture Notes in Computer Science, 2010
- Handwritten Digit Recognition: Applications of Neural Net Chips and Automatic LearningPublished by Springer Science and Business Media LLC ,1990