Handwritten Text Recognition from Crowdsourced Annotations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Handwritten Text Recognition from Crowdsourced Annotations

Solène Tarride
  • Fonction : Auteur
Tristan Faine
  • Fonction : Auteur
Mélodie Boillet
Christopher Kermorvant

Résumé

In this paper, we explore different ways of training a model for handwritten text recognition when multiple imperfect or noisy transcriptions are available. We consider various training configurations, such as selecting a single transcription, retaining all transcriptions, or computing an aggregated transcription from all available annotations. In addition, we evaluate the impact of quality-based data selection, where samples with low agreement are removed from the training set. Our experiments are carried out on municipal registers of the city of Belfort (France) written between 1790 and 1946. % results The results show that computing a consensus transcription or training on multiple transcriptions are good alternatives. However, selecting training samples based on the degree of agreement between annotators introduces a bias in the training data and does not improve the results. Our dataset is publicly available on Zenodo: https://zenodo.org/record/8041668.

Dates et versions

hal-04264668 , version 1 (30-10-2023)

Identifiants

Citer

Solène Tarride, Tristan Faine, Mélodie Boillet, Harold Mouchère, Christopher Kermorvant. Handwritten Text Recognition from Crowdsourced Annotations. HIP '23: 7th International Workshop on Historical Document Imaging and Processing, Aug 2023, San Jose CA USA, France. pp.1-6, ⟨10.1145/3604951.3605517⟩. ⟨hal-04264668⟩
15 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More