Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
ŠKORPIL, V. ŠŤASTNÝ, J.
Originální název
Comparison Methods for Object Recognition
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
This paper describes our new unpublished results and outputs of selected methods for object recognition. It is continued to our former research. We are focused to the identification with the aid of moments, with the aid of syntactical analysis and with the aid of neural network algorithms. Momentum method is very sensitive to entry image quality. Syntactic analysis is suitable for rotated objects, high-speed classification and for small changes in the segment edge. Neural network algorithms can be used for high-speed classification with randomly rotated objects and for some differences between learned etalons and classified objects.
Klíčová slova
Neural network, Invariant moments, Primitives, Syntactical analysis, Back-propagation algorithm.
Autoři
ŠKORPIL, V.; ŠŤASTNÝ, J.
Rok RIV
2009
Vydáno
21. 7. 2009
Nakladatel
WSEAS
Místo
Rhodos, Greece
ISBN
978-960-474-097-0
Kniha
Proceedings of the 13th WSEAS International Conference on Systems
Edice
Číslo edice
1
Strany od
607
Strany do
610
Strany počet
4
BibTex
@inproceedings{BUT29438, author="Vladislav {Škorpil} and Jiří {Šťastný}", title="Comparison Methods for Object Recognition", booktitle="Proceedings of the 13th WSEAS International Conference on Systems", year="2009", series="WSEAS", number="1", pages="607--610", publisher="WSEAS", address="Rhodos, Greece", isbn="978-960-474-097-0" }