Sergio Torres Aguilar ; Vincent Jolivet - Handwritten Text Recognition for Documentary Medieval Manuscripts

jdmdh:10484 - Journal of Data Mining & Digital Humanities, December 22, 2023, Historical Documents and automatic text recognition - https://doi.org/10.46298/jdmdh.10484
Handwritten Text Recognition for Documentary Medieval ManuscriptsArticle

Authors: Sergio Torres Aguilar ORCID1,2; Vincent Jolivet ORCID3,4

Handwritten Text Recognition (HTR) techniques aim to accurately recognize sequences of characters in input manuscript images by training artificial intelligence models to capture historical writing features. Efficient HTR models can transform digitized manuscript collections into indexed and quotable corpora, providing valuable research insight for various historical inquiries. However, several challenges must be addressed, including the scarcity of relevant training corpora, the consequential variability introduced by different scribal hands and writing scripts, and the complexity of page layouts. This paper presents two models and one cross-model approach for automatic transcription of Latin and French medieval documentary manuscripts, particularly charters and registers, written between the 12th and 15th centuries and classified into two major writing scripts: Textualis (from the late-11th to 13th century) and Cursiva (from the 13th to the 15th century). The architecture of the models is based on a Convolutional Recurrent Neural Network (CRNN) coupled with a Connectionist Temporal Classification (CTC) loss. The training and evaluation of the models, involving 120k lines of text and almost 1M tokens, were conducted using three available ground-truth corpora : The e-NDP corpus, the Alcar-HOME database and the Himanis project. This paper describes the training architecture and corpora used, while discussing the main training challenges, results, and potential applications of HTR techniques on medieval documentary manuscripts.


Volume: Historical Documents and automatic text recognition
Published on: December 22, 2023
Accepted on: October 16, 2023
Submitted on: December 14, 2022
Keywords: HTR for historical documents,HTR for medieval Latin manuscripts,digital diplomatics,medieval digital studies,HTR for medieval French manuscripts,medieval charters,[SHS.HIST]Humanities and Social Sciences/History,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]

Publications

Consultation statistics

This page has been seen 287 times.
This article's PDF has been downloaded 102 times.