Small Patterns Detection in Historical Digitised Manuscripts Using Very Few Annotated Examples

Hussein Mohammed, Mahdi Jampour

2024

Abstract

Historical manuscripts can be challenging for computer vision tasks such as writer identification, style classification and layout analysis due to the degradation of the artefacts themselves and the poor quality of digitization, thereby limiting the scope of analysis. However, recent advances in machine learning have shown promising results in enabling the analysis of vast amounts of data from digitised manuscripts. Nevertheless, the task of detecting patterns in these manuscripts is further complicated by the lack of annotations and the small size of many patterns, which can be smaller than 0.1% of the image size. In this study, we propose to explore the possibility of detecting small patterns in digitised manuscripts using only a few annotated examples. We also propose three detection datasets featuring three types of patterns commonly found in manuscripts: words, seals, and drawings. Furthermore, we employed two state-of-the-art deep learning models on these novel datasets: the FASTER ResNet and the EfficientDet, along with our general approach for standard evaluations as a baseline for these datasets.

Paper Citation

in Harvard Style

Mohammed H. and Jampour M. (2024). Small Patterns Detection in Historical Digitised Manuscripts Using Very Few Annotated Examples. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 605-612. DOI: 10.5220/0012269500003654

in Bibtex Style

@conference{icpram24,
author={Hussein Mohammed and Mahdi Jampour},
title={Small Patterns Detection in Historical Digitised Manuscripts Using Very Few Annotated Examples},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={605-612},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012269500003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Small Patterns Detection in Historical Digitised Manuscripts Using Very Few Annotated Examples
SN - 978-989-758-684-2
AU - Mohammed H.
AU - Jampour M.
PY - 2024
SP - 605
EP - 612
DO - 10.5220/0012269500003654
PB - SciTePress