Hyperspectral imaging to assess the presence of powdery mildew (Erysiphe necator) in cv. Carignan Noir grapevine bunches
Fecha
2020Autor
Versión
Acceso abierto / Sarbide irekia
Tipo
Artículo / Artikulua
Versión
Versión publicada / Argitaratu den bertsioa
Identificador del proyecto
ES/1PE/TIN2016-77356-P
Impacto
|
10.3390/agronomy10010088
Resumen
Powdery mildew is a worldwide major fungal disease for grapevine, which adversely affects both crop yield and produce quality. Disease identification is based on visible signs of a pathogen once the plant has already been infected; therefore, techniques that allow objective diagnosis of the disease are currently needed. In this study, the potential of hyperspectral imaging (HSI) technology to ass ...
[++]
Powdery mildew is a worldwide major fungal disease for grapevine, which adversely affects both crop yield and produce quality. Disease identification is based on visible signs of a pathogen once the plant has already been infected; therefore, techniques that allow objective diagnosis of the disease are currently needed. In this study, the potential of hyperspectral imaging (HSI) technology to assess the presence of powdery mildew in grapevine bunches was evaluated. Thirty Carignan Noir grape bunches, 15 healthy and 15 infected, were analyzed using a lab-scale HSI system (900–1700 nm spectral range). Image processing was performed to extract spectral and spatial image features and then, classification models by means of Partial Least Squares Discriminant Analysis (PLS-DA) were carried out for healthy and infected pixels distinction within grape bunches. The best discrimination was achieved for the PLS-DA model with smoothing (SM), Standard Normal Variate (SNV) and mean centering (MC) pre-processing combination, reaching an accuracy of 85.33% in the cross-validation model and a satisfactory classification and spatial location of either healthy or infected pixels in the external validation. The obtained results suggested that HSI technology combined with chemometrics could be used for the detection of powdery mildew in black grapevine bunches. [--]
Materias
Image analysis,
NIR-HSI,
Chemometrics,
Fungal disease,
Vitis vinifera L.
Editor
MDPI
Publicado en
Agronomy 2020, 10, 88
Departamento
Universidad Pública de Navarra. Departamento de Ingeniería /
Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas /
Universidad Pública de Navarra. Departamento de Agronomía, Biotecnología y Alimentación /
Nafarroako Unibertsitate Publikoa. Ingeniaritza Saila /
Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematika Saila /
Nafarroako Unibertsitate Publikoa. Agronomia, Bioteknologia eta Elikadura Saila
Versión del editor
Entidades Financiadoras
This research received funding from the Department of Economic Development of the Navarre
Government (Project: DECIVID (Res.104E/2017)), by the Spanish Ministry of Economy and Competitiveness
(Project TIN2016-77356-P) and by the research services of the Universidad Pública de Navarra. C.P.-R is a
beneficiary of postgraduate scholarships funded by Universidad Pública de Navarra (FPI-UPNA-2017
(Res.654/2017)).