Generation of Synthetic Images of Full-Text Documents

Kód výsledku v IS VaVaI

RIV/49777513:23520/18:43952605 - isvavai.cz

Výsledek na webu

https://link.springer.com/chapter/10.1007%2F978-3-319-99579-3_8

DOI - Digital Object Identifier

10.1007/978-3-319-99579-3_8

Jazyk výsledku

angličtina

Název v původním jazyce

Generation of Synthetic Images of Full-Text Documents

Popis výsledku v původním jazyce

In this paper, we present an algorithm for generating images of full-text documents. Such images can be used to train and evaluate models of optical character recognition. The algorithm is modular, individual parts can be changed and tweaked to generate desired images. We describe a method for obtaining background images of paper from already digitalized documents.We use a Variational Autoencoder to train a generative model of these backgrounds enabling the generation of similar background images as the training ones on the fly. The module for printing the text uses large text corpora, font, and suitable positional and brightness noise to obtain believable results. We use Tesseract OCR to compare the real world and generated images and observe that the recognition rate is very similar indicating the proper appearance of the synthetic images. Furthermore, the mistakes made by the OCR system in both cases are alike. Finally, the system generates detailed, structured annotation of the synthesized image.

Název v anglickém jazyce

Generation of Synthetic Images of Full-Text Documents

Popis výsledku anglicky

In this paper, we present an algorithm for generating images of full-text documents. Such images can be used to train and evaluate models of optical character recognition. The algorithm is modular, individual parts can be changed and tweaked to generate desired images. We describe a method for obtaining background images of paper from already digitalized documents.We use a Variational Autoencoder to train a generative model of these backgrounds enabling the generation of similar background images as the training ones on the fly. The module for printing the text uses large text corpora, font, and suitable positional and brightness noise to obtain believable results. We use Tesseract OCR to compare the real world and generated images and observe that the recognition rate is very similar indicating the proper appearance of the synthetic images. Furthermore, the mistakes made by the OCR system in both cases are alike. Finally, the system generates detailed, structured annotation of the synthesized image.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Speech and Computer 20th International Conference, SPECOM 2018 Leipzig, Germany, September 18–22, 2018, Proceedings

ISBN

978-3-319-99578-6

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

8

Strana od-do

68-75

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Cham

Místo konání akce

Leipzig, Germany

Datum konání akce

18. 9. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—