A tailored Handwritten-Text-Recognition System for Medieval Latin
Abstract
The Bavarian Academy of Sciences and Humanities aims to digitize its Medieval Latin Dictionary. This dictionary entails record cards referring to lemmas in medieval Latin, a low-resource language. A crucial step of the digitization process is the Handwritten Text Recognition (HTR) of the handwritten lemmas found on these record cards. In our work, we introduce an end-to-end pipeline, tailored to the medieval Latin dictionary, for locating, extracting, and transcribing the lemmas. We employ two state-of-the-art (SOTA) image segmentation models to prepare the initial data set for the HTR task. Furthermore, we experiment with different transformer-based models and conduct a set of experiments to explore the capabilities of different combinations of vision encoders with a GPT-2 decoder. Additionally, we also apply extensive data augmentation resulting in a highly competitive model. The best-performing setup achieved a Character Error Rate (CER) of 0.015, which is even superior to the commercial Google Cloud Vision model, and shows more stable performance.
Cite
@article{arxiv.2308.09368,
title = {A tailored Handwritten-Text-Recognition System for Medieval Latin},
author = {Philipp Koch and Gilary Vera Nuñez and Esteban Garces Arias and Christian Heumann and Matthias Schöffel and Alexander Häberlin and Matthias Aßenmacher},
journal= {arXiv preprint arXiv:2308.09368},
year = {2023}
}
Comments
This paper has been accepted at the First Workshop on Ancient Language Processing, co-located with RANLP 2023. This is the author's version of the work. The definite version of record will be published in the proceedings