Přístupnostní navigace
E-application
Search Search Close
Publication detail
ŠŤASTNÝ, J. MOTYČKA, A.
Original Title
Methods and Algorithms for Object Recognition
Type
conference paper
Language
English
Original Abstract
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.
Keywords
Image processing, flag vector, neural network, syntactic analysis.
Authors
ŠŤASTNÝ, J.; MOTYČKA, A.
RIV year
2007
Released
11. 6. 2007
Publisher
Slovak University of Technology
Location
Bratislava
ISBN
978-80-227-2677-1
Book
Process Control 2007
Pages from
145
Pages to
150
Pages count
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" }