Network of Steel: Neural Font Style Transfer from Heavy Metal to Corporate Logos

Aram Ter-Sarkisov

2020

Abstract

We introduce a method for transferring style from the logos of heavy metal bands onto corporate logos using a VGG16 network. We establish the contribution of different layers and loss coefficients to the learning of style, minimization of artefacts and maintenance of readability of corporate logos. We find layers and loss coefficients that produce a good tradeoff between heavy metal style and corporate logo readability. This is the first step both towards sparse font style transfer and corporate logo decoration using generative networks. Heavy metal and corporate logos are very different artistically, in the way they emphasize emotions and readability, therefore training a model to fuse the two is an interesting problem.

Paper Citation

in Harvard Style

Ter-Sarkisov A. (2020). Network of Steel: Neural Font Style Transfer from Heavy Metal to Corporate Logos. In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 621-629. DOI: 10.5220/0009343906210629

in Bibtex Style

@conference{icpram20,
author={Aram Ter-Sarkisov},
title={Network of Steel: Neural Font Style Transfer from Heavy Metal to Corporate Logos},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={621-629},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009343906210629},
isbn={978-989-758-397-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Network of Steel: Neural Font Style Transfer from Heavy Metal to Corporate Logos
SN - 978-989-758-397-1
AU - Ter-Sarkisov A.
PY - 2020
SP - 621
EP - 629
DO - 10.5220/0009343906210629