Detail publikace
Methods and Algorithms for Object Recognition
ŠŤASTNÝ, J. MOTYČKA, A.
Anglický název
Methods and Algorithms for Object Recognition
Typ
Stať ve sborníku v databázi WoS či Scopus
Jazyk
en
Originální abstrakt
The paper deals with problems of computer image processing with a view to applications in the area of industrial robotics. Besides classical methods for object recognition especially nontraditional methods and algorithms (the Multi Layer Perceptron neural network algorithm and the Levenshtein algorithm) were tested in simulation environment. Implemented algorithms were tested on the simulated objects of technological scene given. The results of the simulation experiments show that the Multi Layer Perceptron neural network with the Back-Propagation algorithm and the Levenshtein algorithm are very promising for object recognition of technological scenes for the use of industrial robots control.
Klíčová slova anglicky
Image processing, flag vector, neural network, syntactic analysis.
Vydáno
2007-06-11
Nakladatel
Slovak University of Technology
Místo
Bratislava
ISBN
978-80-227-2677-1
Kniha
Process Control 2007
Strany od–do
145–150
Počet stran
6
BIBTEX
@inproceedings{BUT28319,
author="Jiří {Šťastný} and Arnošt {Motyčka}",
title="Methods and Algorithms for Object Recognition",
booktitle="Process Control 2007",
year="2007",
pages="145--150",
publisher="Slovak University of Technology",
address="Bratislava",
isbn="978-80-227-2677-1"
}