Handwritten Text Recognition for Documentary Medieval Manuscripts

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 quotabl...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of data mining and digital humanities Jg. Historical Documents and...
Hauptverfasser: Torres Aguilar, Sergio, Jolivet, Vincent
Format: Journal Article
Sprache:Englisch
Veröffentlicht: INRIA 22.12.2023
Nicolas Turenne
Schlagworte:
[info.info-ai]computer science [cs]/artificial intelligence [cs.ai]
[shs.hist]humanities and social sciences/history
Artificial Intelligence
Computer Science
digital diplomatics
History
htr for historical documents
htr for medieval french manuscripts
htr for medieval latin manuscripts
Humanities and Social Sciences
medieval charters
medieval digital studies
digital diplomatics
medieval digital studies
HTR for historical documents
HTR for medieval Latin manuscripts
medieval charters
HTR for medieval French manuscripts
ISSN:2416-5999, 2416-5999
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:2416-5999
2416-5999
DOI:10.46298/jdmdh.10484