Detection of defects on apples using hyperspectral reflection visualization combining both vegetation index analysis and neural network

Autor:	A. A. Zhirkova, P. V. Balabanov, A. G. Divin, A. S. Egorov, V. A. Yudaev
Rok vydání:	2020
Předmět:	History Artificial neural network Computer science Reflection (physics) Hyperspectral imaging Vegetation Index Computer Science Applications Education Remote sensing Visualization
Zdroj:	Journal of Physics: Conference Series. 1515:032064
ISSN:	1742-6596 1742-6588
DOI:	10.1088/1742-6596/1515/3/032064
Popis:	The article shows the possibility of using vegetation indices to build algorithms for recognizing defects in plant tissue of apples. The authors demonstrate that it is advisable to use halogen lamps as light sources for apples hyperspectral control, but LED backlighting to correct the spectrum at the edges of the 400-1000 nm range is preferable to use. The experimentally obtained spectra of the optical radiation reflected from the apples plant tissue in the mentioned wavelength range are presented and show the possibility of identifying defects using vegetation indices. At the same time, the risk of obtaining false defects for some varieties of apples is revealed. To reduce this risk, it is proposed to use artificial Deep Feedforward neural networks with one hidden layer.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::94f9c518e239f1f52e62b69a8803394d https://doi.org/10.1088/1742-6596/1515/3/032064 Zobrazit plný text záznamu