Text Localization in Real-World Images Using Efficiently Pruned Exhaustive Search

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F11%3A00187378" target="_blank" >RIV/68407700:21230/11:00187378 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICDAR.2011.144" target="_blank" >http://dx.doi.org/10.1109/ICDAR.2011.144</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICDAR.2011.144" target="_blank" >10.1109/ICDAR.2011.144</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Text Localization in Real-World Images Using Efficiently Pruned Exhaustive Search

Popis výsledku v původním jazyce

An efficient method for text localization and recognition in real-world images is proposed. Thanks to effective pruning, it is able to exhaustively search the space of all character sequences in real time (200ms on a 640x480 image). The method exploits higher-order properties of text such as word text lines. We demonstrate that the grouping stage plays a key role in the text localization performance and that a robust and precise grouping stage is able to compensate errors of the character detector. Themethod includes a novel selector of Maximally Stable Extremal Regions (MSER) which exploits region topology. Experimental validation shows that 95.7% characters in the ICDAR dataset are detected using the novel selector of MSERs with a low sensitivity threshold. The proposed method was evaluated on the standard ICDAR 2003 dataset where it achieved state-of-the-art results in both text localization and recognition.

Název v anglickém jazyce

Text Localization in Real-World Images Using Efficiently Pruned Exhaustive Search

Popis výsledku anglicky

An efficient method for text localization and recognition in real-world images is proposed. Thanks to effective pruning, it is able to exhaustively search the space of all character sequences in real time (200ms on a 640x480 image). The method exploits higher-order properties of text such as word text lines. We demonstrate that the grouping stage plays a key role in the text localization performance and that a robust and precise grouping stage is able to compensate errors of the character detector. Themethod includes a novel selector of Maximally Stable Extremal Regions (MSER) which exploits region topology. Experimental validation shows that 95.7% characters in the ICDAR dataset are detected using the novel selector of MSERs with a low sensitivity threshold. The proposed method was evaluated on the standard ICDAR 2003 dataset where it achieved state-of-the-art results in both text localization and recognition.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/7E10045" target="_blank" >7E10045: Massive Sets of Heuristics for Machine Learning</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2011

Kód důvěrnosti údajů

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

Název statě ve sborníku

Document Analysis and Recognition (ICDAR), 2011 International Conference on

ISBN

978-1-4577-1350-7

ISSN

1520-5363

e-ISSN

—

Počet stran výsledku

5

Strana od-do

687-691

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Beijing

Datum konání akce

18. 9. 2011

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—