Transfer and Extraction of the Style of Handwritten Letters using Deep Learning

Omar Mohammed, Gérard Bailly, Damien Pellier

2019

Abstract

How can we learn, transfer and extract handwriting styles using deep neural networks? This paper explores these questions using a deep conditioned autoencoder on the IRON-OFF handwriting data-set. We perform three experiments that systematically explore the quality of our style extraction procedure. First, We compare our model to handwriting benchmarks using multidimensional performance metrics. Second, we explore the quality of style transfer, i.e. how the model performs on new, unseen writers. In both experiments, we improve the metrics of state of the art methods by a large margin. Lastly, we analyze the latent space of our model, and we show that it separates consistently writing styles.

Paper Citation

in Harvard Style

Mohammed O., Bailly G. and Pellier D. (2019). Transfer and Extraction of the Style of Handwritten Letters using Deep Learning.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 677-684. DOI: 10.5220/0007388606770684

in Bibtex Style

@conference{icaart19,
author={Omar Mohammed and Gérard Bailly and Damien Pellier},
title={Transfer and Extraction of the Style of Handwritten Letters using Deep Learning},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={677-684},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007388606770684},
isbn={978-989-758-350-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Transfer and Extraction of the Style of Handwritten Letters using Deep Learning
SN - 978-989-758-350-6
AU - Mohammed O.
AU - Bailly G.
AU - Pellier D.
PY - 2019
SP - 677
EP - 684
DO - 10.5220/0007388606770684