Training Strategies for OCR Systems for Historical Documents

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F19%3A43955252" target="_blank" >RIV/49777513:23520/19:43955252 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-030-19823-7_30" target="_blank" >http://dx.doi.org/10.1007/978-3-030-19823-7_30</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-19823-7_30" target="_blank" >10.1007/978-3-030-19823-7_30</a>

Result language

angličtina

Original language name

Training Strategies for OCR Systems for Historical Documents

Original language description

This paper presents an overview of training strategies for optical character recognition of historical documents.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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Artificial Intelligence Applications and Innovation

ISBN

978-3-030-19822-0

ISSN

1868-4238

e-ISSN

—

Number of pages

12

Pages from-to

362-373

Publisher name

Springer

Place of publication

Cham

Event location

Crete

Event date

May 24, 2019

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—