EHDI: Enhancement of Historical Document Images via Generative Adversarial Network

Abir Fathallah, Abir Fathallah, Mounim El-Yacoubi, Najoua Ben Amara

2023

Abstract

Images of historical documents are sensitive to the significant degradation over time. Due to this degradation, exploiting information contained in these documents has become a challenging task. Consequently, it is important to develop an efficient tool for the quality enhancement of such documents. To address this issue, we present in this paper a new modelknown as EHDI (Enhancement of Historical Document Images) which is based on generative adversarial networks. The task is considered as an image-to-image conversion process where our GAN model involves establishing a clean version of a degraded historical document. EHDI implies a global loss function that associates content, adversarial, perceptual and total variation losses to recover global image information and generate realistic local textures. Both quantitative and qualitative experiments demonstrate that our proposed EHDI outperforms significantly the state-of-the-art methods applied to the widespread DIBCO 2013, DIBCO 2017, and H-DIBCO 2018 datasets. Our suggested model is adaptable to other document enhancement problems, following the results across a wide range of degradations. Our code is available at https://github.com/Abir1803/EHDI.git.

Paper Citation

in Harvard Style

Fathallah A., El-Yacoubi M. and Ben Amara N. (2023). EHDI: Enhancement of Historical Document Images via Generative Adversarial Network. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 238-245. DOI: 10.5220/0011662700003417

in Bibtex Style

@conference{visapp23,
author={Abir Fathallah and Mounim El-Yacoubi and Najoua Ben Amara},
title={EHDI: Enhancement of Historical Document Images via Generative Adversarial Network},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={238-245},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011662700003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - EHDI: Enhancement of Historical Document Images via Generative Adversarial Network
SN - 978-989-758-634-7
AU - Fathallah A.
AU - El-Yacoubi M.
AU - Ben Amara N.
PY - 2023
SP - 238
EP - 245
DO - 10.5220/0011662700003417
PB - SciTePress