Email this article Traffic Sign Classification with a Convolutional Network
- Authors: Staravoitau A.1
-
Affiliations:
- Belarusian State University
- Issue: Vol 28, No 1 (2018)
- Pages: 155-162
- Section: Applied Problems
- URL: https://journals.rcsi.science/1054-6618/article/view/195320
- DOI: https://doi.org/10.1134/S1054661818010182
- ID: 195320
Cite item
Open Access
Access granted
Subscription Access
Abstract
I approach the traffic signs classification problem with a convolutional neural network implemented in TensorFlow reaching 99.33% accuracy. The highlights of this solution would be data pre-processing, data augmentation pipeline, pre-training and skipping connections in the network. I am using Python as programming language and TensorFlow as a fairly low-level machine learning framework.
About the authors
A. Staravoitau
Belarusian State University
Author for correspondence.
Email: alex.staravoitau@gmail.com
Belarus, Minsk
Supplementary files
