Training Strategies for OCR Systems for Historical Documents - Artificial Intelligence Applications and Innovations
Conference Papers Year : 2019

Training Strategies for OCR Systems for Historical Documents

Abstract

This paper presents an overview of training strategies for optical character recognition of historical documents. The main issue is the lack of the annotated data and its quality. We summarize several ways of synthetic data preparation. The main goal of this paper is to show and compare possibilities how to train a convolutional recurrent neural network classifier using the synthetic data and its combination with a real annotated dataset.
Fichier principal
Vignette du fichier
483292_1_En_30_Chapter.pdf (968.48 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02331288 , version 1 (24-10-2019)

Licence

Identifiers

Cite

Jiří Martínek, Ladislav Lenc, Pavel Král. Training Strategies for OCR Systems for Historical Documents. 15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.362-373, ⟨10.1007/978-3-030-19823-7_30⟩. ⟨hal-02331288⟩
53 View
82 Download

Altmetric

Share

More