Convolutional Neural Networks for Croatian Traffic Signs Recognition

Abstract

We present an approach to recognition of Croatian traffic signs based on convolutional neural networks (CNNs). A library for quick prototyping of CNNs, with an educational scope, is first developed1. An architecture similar to LeNet-5 is then created and tested on the MNIST dataset of handwritten digits where comparable results were obtained. We analyze the FERMASTIF TS2010 dataset and propose a CNN architecture for traffic sign recognition. The presented experiments confirm the feasibility of CNNs for the defined task and suggest improvements to be made in order to improve recognition of Croatian traffic signs.

Files

Full Paper as PDF

BibTeX Citation

DOI

10.20532/ccvw.2014.0016

https://doi.org/10.20532/ccvw.2014.0016

BibTeX

@InProceedings{10.20532/ccvw.2014.0016,
  author =       {Vedran Vukoti{\' c} and Josip Krapac and Sini{\v s}a
                  {\v S}egvi{\' c}},
  title =        {Convolutional Neural Networks for Croatian Traffic
                  Signs Recognition},
  booktitle =    {Proceedings of the Croatian Compter Vision Workshop,
                  Year 2},
  pages =        {15-20},
  year =         2014,
  editor =       {Lon{\v c}ari{\' c}, Sven and Suba{\v s}i{\' c},
                  Marko},
  address =      {Zagreb},
  month =        {September},
  organization = {Center of Excellence for Computer Vision},
  publisher =    {University of Zagreb},
  abstract =     {We present an approach to recognition of Croatian
                  traffic signs based on convolutional neural networks
                  (CNNs). A library for quick prototyping of CNNs is
                  first developed. An architecture similar to LeNet-5
                  is then created and tested on the MNIST dataset of
                  handwritten digits where comparable results were
                  obtained. We analyze the FER-MASTIF TS2010 dataset
                  and propose a CNN architecture for traffic sign
                  recognition. The presented experiments confirm the
                  feasibility of CNNs for the defined task and suggest
                  improvements to be made in order to improve
                  recognition of Croatian traffic signs.},
  doi =          {10.20532/ccvw.2014.0016},
  url =          {https://doi.org/10.20532/ccvw.2014.0016}
}