Full-Page Text Recognition: Learning Where to Start and When to Stop - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Full-Page Text Recognition: Learning Where to Start and When to Stop

Résumé

Text line detection and localization is a crucial step for full page document analysis, but still suffers from heterogeneity of real life documents. In this paper, we present a new approach for full page text recognition. Localization of the text lines is based on regressions with Fully Convolutional Neural Networks and Multidimensional Long Short-Term Memory as contextual layers. In order to increase the efficiency of this localization method, only the position of the left side of the text lines are predicted. The text recognizer is then in charge of predicting the end of the text to recognize. This method has shown good results for full page text recognition on the highly heterogeneous Maurdor dataset.
Fichier non déposé

Dates et versions

hal-01563124 , version 1 (17-07-2017)

Identifiants

  • HAL Id : hal-01563124 , version 1

Citer

Bastien Moysset, Christopher Kermorvant, Christian Wolf. Full-Page Text Recognition: Learning Where to Start and When to Stop. International Conference on Document Analysis and Recognition, Nov 2017, Kyoto, Japan. ⟨hal-01563124⟩
199 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More