The Effects of Character-Level Data Augmentation on Style-Based Dating of Historical Manuscripts

Lisa Koopmans, Maruf A. Dhali, Lambert Schomaker

2023

Abstract

Identifying the production dates of historical manuscripts is one of the main goals for paleographers when studying ancient documents. Automatized methods can provide paleographers with objective tools to estimate dates more accurately. Previously, statistical features have been used to date digitized historical manuscripts based on the hypothesis that handwriting styles change over periods. However, the sparse availability of such documents poses a challenge in obtaining robust systems. Hence, the research of this article explores the influence of data augmentation on the dating of historical manuscripts. Linear Support Vector Machines were trained with k-fold cross-validation on textural and grapheme-based features extracted from historical manuscripts of different collections, including the Medieval Paleographical Scale, early Aramaic manuscripts, and the Dead Sea Scrolls. Results show that training models with augmented data improve the performance of historical manuscripts dating by 1% - 3% in cumulative scores. Additionally, this indicates further enhancement possibilities by considering models specific to the features and the documents’ scripts.

Paper Citation

in Harvard Style

Koopmans L., A. Dhali M. and Schomaker L. (2023). The Effects of Character-Level Data Augmentation on Style-Based Dating of Historical Manuscripts. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 124-135. DOI: 10.5220/0011699500003411

in Bibtex Style

@conference{icpram23,
author={Lisa Koopmans and Maruf A. Dhali and Lambert Schomaker},
title={The Effects of Character-Level Data Augmentation on Style-Based Dating of Historical Manuscripts},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={124-135},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011699500003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - The Effects of Character-Level Data Augmentation on Style-Based Dating of Historical Manuscripts
SN - 978-989-758-626-2
AU - Koopmans L.
AU - A. Dhali M.
AU - Schomaker L.
PY - 2023
SP - 124
EP - 135
DO - 10.5220/0011699500003411