ORIGINAL PAPER
Empirical graphics data conversion to learning sets in apple-tree pests neural identification process
More details
Hide details
Journal of Research and Applications in Agricultural Engineering 2007;52(1):37-40
KEYWORDS
ABSTRACT
The mischievous of insects is mostly about their preying on the cultivated plants. In order to identify a pest correctly, one has to have the ability to identify its key characteristics. These are placed all over the insects corpse. A pest can be described by hundreds or even thousands of 'keys' - depending on the kind or species - what proves how difficult and time-consuming the identification is. ANN (Artificial Neural Networks) can learn, are less sensible to incomplete incoming information, they are processing entered signals and give results in actual time. The above properties and the analysis during the research allow to make a conclusion that ANN may do the identification task similarly to a human being. Thanks to such identification process automation it could be possible to eliminate the objectivism factor.
REFERENCES (5)
1.
Marciniak A., Korbicz J. (1999): Diagnozowanie dynamicznych obiektów nieliniowych z wykorzystaniem statycznych sieci neuronowych. - Mat. XIII Krajowej Konferencji Automatyki.
2.
Tadeusiewicz R., Flasiński M. (1991): Rozpoznawanie obrazów - Warszawa PWN.
3.
Malina W., Smiatacz M.(2005): Metody cyfrowego przetwarzania obrazów - Wydawnictwo ELIT.
4.
Ryszard S. Choraś (2005): Komputerowa wizja. Metody interpretacji i identyfikacji obiektów - Wydawnictwo EXIT.
5.
Boniecki P., Piekarska_Boniecka H. (2004): Neuronowa identyfikacja wybranych szkodników drzew owocowych w oparciu o analizę obrazu - Journal of Research and Applications in Agricultural Engineering, Vol. 49(3), str. 25 - 30.