Recognition and Information Extraction in Historical Handwritten Tables : Toward Understanding Early 20th Century Paris Census - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2022

Recognition and Information Extraction in Historical Handwritten Tables : Toward Understanding Early 20th Century Paris Census

Résumé

We aim to build a vast database (up to 9 million individuals) from the handwritten tabular nominal census of Paris of 1926, 1931 and 1936, each composed of about 100,000 handwritten simple pages in a tabular format. We created a complete pipeline that goes from the scan of double pages to text prediction while minimizing the need for segmentation labels. We describe how weighted finite state transducers, writer specialization and self-training further improved our results. We also introduce through this communication two annotated datasets for handwriting recognition that are now publicly available, and an open-source toolkit to apply WFST on CTC lattices.
Fichier principal
Vignette du fichier
DAS_2022_paper_54 (1).pdf (4.9 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03675614 , version 1 (13-09-2023)

Identifiants

Citer

Thomas Constum, Nicolas Kempf, Thierry Paquet, Pierrick Tranouez, Clément Chatelain, et al.. Recognition and Information Extraction in Historical Handwritten Tables : Toward Understanding Early 20th Century Paris Census. Document Analysis Systems 2022 proceedings, 13237, Springer International Publishing, pp.143-157, 2022, Lecture Notes in Computer Science, ⟨10.1007/978-3-031-06555-2_10⟩. ⟨hal-03675614⟩
72 Consultations
20 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More