Text Line Detection in Historical Index Tables: Evaluations on a New French PArish REcord Survey Dataset (PARES) - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Text Line Detection in Historical Index Tables: Evaluations on a New French PArish REcord Survey Dataset (PARES)

Résumé

In this paper, we address the challenge of document image analysis for historical index table documents with handwritten records. Demographic studies can gain insight from the use of automatic document analysis in such documents through the study of population movements. To evaluate the efficacy of automatic layout analysis tools, we release the PARES dataset, which contains 250 labeled index table images originating from French archives. Also, we run state-of-the-art algorithms (U-FCN, R-CNN and Transformers) in order to detect the lines within index tables, a common prerequisite for handwritten text recognition (HTR). Our results indicate that text line extraction works well with the U-FCN model, while also indicating that Transformer architectures show promise for accurate text line detection in such historical documents with great efficiency. This is a encouraging step towards a Transformer-based architecture for both layout and content detection. This process and dataset represent a first step to automatically analyze handwritten and historical index tables. In addition to this paper and the PARES dataset of historical index tables of 250 images, we release segmentation masks, the code we used to train and test the models, and the models themselves.
Fichier principal
Vignette du fichier
ICADL___Long_Paper___A_Historical_Census_Tables_Dataset.pdf (3.82 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY NC SA - Paternité - Pas d'utilisation commerciale - Partage selon les Conditions Initiales

Dates et versions

hal-04207205 , version 1 (14-09-2023)
hal-04207205 , version 2 (23-10-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04207205 , version 2

Citer

Guillaume Bernard, Casey Wall, Mélodie Boillet, Mickaël Coustaty, Christopher Kermorvant, et al.. Text Line Detection in Historical Index Tables: Evaluations on a New French PArish REcord Survey Dataset (PARES). The 25th International Conference on Asia-Pacific Digital Libraries, Hao-Ren KE (National Taiwan Normal University, Taiwan), Dec 2023, Taipei, Taiwan. ⟨hal-04207205v2⟩

Collections

UNIV-ROCHELLE
54 Consultations
88 Téléchargements

Partager

Gmail Facebook X LinkedIn More