Brno Mobile OCR Dataset

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU135406" target="_blank" >RIV/00216305:26230/20:PU135406 - isvavai.cz</a>

Výsledek na webu

<a href="https://pero.fit.vutbr.cz/publications" target="_blank" >https://pero.fit.vutbr.cz/publications</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICDAR.2019.00218" target="_blank" >10.1109/ICDAR.2019.00218</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Brno Mobile OCR Dataset

Popis výsledku v původním jazyce

We introduce the Brno Mobile OCR Dataset (B-MOD) for document Optical Character Recognition from low-quality images captured by handheld mobile devices. While OCR of high-quality scanned documents is a mature field where many commercial tools are available, and large datasets of text in the wild exist, no existing datasets can be used to develop and test document OCR methods robust to non-uniform lighting, image blur, strong noise, built-in denoising, sharpening, compression and other artifacts present in many photographs from mobile devices. This dataset contains 2 113 unique pages from random scientific papers, which were photographed by multiple people using 23 different mobile devices. The resulting 19 728 photographs of various visual quality are accompanied by precise positions and text annotations of 500k text lines. We further provide an evaluation methodology, including an evaluation server and a testset with non-public annotations. We provide a state-of-the-art text recognition baseline build on convolutional and recurrent neural networks trained with Connectionist Temporal Classification loss. This baseline achieves 2 %, 23 % and 73 % word error rates on easy, medium and hard parts of the dataset, respectively, confirming that the dataset is challenging. The presented dataset will enable future development and evaluation of document analysis for low-quality images. It is primarily intended for line-level text recognition, and can be further used for line localization, layout analysis, image restoration and text binarization.

Název v anglickém jazyce

Brno Mobile OCR Dataset

Popis výsledku anglicky

We introduce the Brno Mobile OCR Dataset (B-MOD) for document Optical Character Recognition from low-quality images captured by handheld mobile devices. While OCR of high-quality scanned documents is a mature field where many commercial tools are available, and large datasets of text in the wild exist, no existing datasets can be used to develop and test document OCR methods robust to non-uniform lighting, image blur, strong noise, built-in denoising, sharpening, compression and other artifacts present in many photographs from mobile devices. This dataset contains 2 113 unique pages from random scientific papers, which were photographed by multiple people using 23 different mobile devices. The resulting 19 728 photographs of various visual quality are accompanied by precise positions and text annotations of 500k text lines. We further provide an evaluation methodology, including an evaluation server and a testset with non-public annotations. We provide a state-of-the-art text recognition baseline build on convolutional and recurrent neural networks trained with Connectionist Temporal Classification loss. This baseline achieves 2 %, 23 % and 73 % word error rates on easy, medium and hard parts of the dataset, respectively, confirming that the dataset is challenging. The presented dataset will enable future development and evaluation of document analysis for low-quality images. It is primarily intended for line-level text recognition, and can be further used for line localization, layout analysis, image restoration and text binarization.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/DG18P02OVV055" target="_blank" >DG18P02OVV055: Pokročilá extrakce a rozpoznávání obsahu tištěných a rukou psaných digitalizátů pro zvýšení jejich přístupnosti a využitelnosti</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

ISBN

978-1-7281-3014-9

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

1352-1357

Název nakladatele

Institute of Electrical and Electronics Engineers

Místo vydání

Sydney

Místo konání akce

Sydney, Australia

Datum konání akce

20. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—