Estimating hidden parameters for text localization and recognition

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F11%3A00187103" target="_blank" >RIV/68407700:21230/11:00187103 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Estimating hidden parameters for text localization and recognition
Original language description
A new method for text line formation for text localization and recognition is proposed. The method exhaustively enumerates short sequences of character regions in order to infer values of hidden text line parameters (such as text direction) and applies the parameters to efficiently limit the search space for longer sequences. The exhaustive enumeration of short sequences is achieved by finding all character region triplets that fulfill constraints of textual content, which keeps the proposed method efficient yet still capable to perform a robust estimation of the hidden parameters in order to correctly initialize the search. The method is applied to character regions which are detected as Maximally Stable Extremal Regions (MSERs). The performance of the method is evaluated on the standard ICDAR 2003 dataset, where the method outperforms (precision 0.60, recall 0.60) a previously published method for text line formation of MSERs.
Czech name
—
Czech description
—

Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
CVWW '11: Proceedings of the 16th Computer Vision Winter Workshop
ISBN
978-3-85125-129-6
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
29-36
Publisher name
Graz University of Technology
Place of publication
Graz
Event location
Mitterberg
Event date
Feb 2, 2011
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)