Towards a general open dataset and model for late medieval Castilian text recognition (HTR/OCR) - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Data Mining and Digital Humanities Année : 2023

Towards a general open dataset and model for late medieval Castilian text recognition (HTR/OCR)

Résumé

This paper introduces a first HTR/OCR open access gold corpus for spanish late medieval sources, based on the allographetic transcription of more than 300 pages of several manuscripts of the Regimiento de los Prínçipes, as well as a first set of general transcription and regions/lines segmentation models trained with Kraken. These models are evaluated with in-domain and out-of-domain data.

Dates et versions

hal-04327119 , version 1 (06-12-2023)

Identifiants

Citer

Matthias Gille Levenson. Towards a general open dataset and model for late medieval Castilian text recognition (HTR/OCR). Journal of Data Mining and Digital Humanities, 2023, Historical Documents and.., ⟨10.46298/jdmdh.10416⟩. ⟨hal-04327119⟩
20 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More