Automatic selection of binarization method from images with serial numbers on industrial products

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27360%2F20%3A10247099" target="_blank" >RIV/61989100:27360/20:10247099 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.37904/metal.2020.3636" target="_blank" >http://dx.doi.org/10.37904/metal.2020.3636</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.37904/metal.2020.3636" target="_blank" >10.37904/metal.2020.3636</a>

Result language
angličtina
Original language name
Automatic selection of binarization method from images with serial numbers on industrial products
Original language description
The article deals with the automatic selection of the binarization method using advanced methods of artificial intelligence. The input images to the algorithms are images of serial numbers from industrial environments, for example on iron and steel billets, slabs, etc. The surface of these products is in most cases severely damaged by industrial processes, such as traces of cut, rust, noise, surface roughness, etc. Text recognition is a very common topic nowadays. All investigated solutions are based on the fact that each image is binarized by a single defined method and the accuracy of recognition is given only by the quality of learning of the neural network. Especially in an industrial environment, it is difficult to create a universal method for unambiguous methods for text recognition. The innovation described in this article is the automatic selection of the binarization method (from the Bradley, Niblack, Sauvola methods etc.), which increases the accuracy already in the phase before the text recognition itself, which with the subsequent correct combination of filters leads to an overall increase in accuracy. (C) 2020 TANGER Ltd., Ostrava.
Czech name
—
Czech description
—

Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
METAL 2020 : 29th International Conference on Metallurgy and Materials : conference proceedings : May 20-22, 2020, Brno, Czech Republic, EU
ISBN
978-80-87294-97-0
ISSN
2694-9296
e-ISSN
—
Number of pages
5
Pages from-to
1357-1361
Publisher name
Tanger
Place of publication
Ostrava
Event location
Brno
Event date
May 20, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)