Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine

Product inspection is essential to ensure good quality and to avoid fraud. New nectarine cultivars with similar external appearance but different physicochemical properties may be mixed in the market, causing confusion and rejection among consumers, and consequently affecting sales and prices. Hyper...

Descripción completa

Detalles Bibliográficos
Autores principales: Munera, Sandra, Amigo, José M., Aleixos, Nuria, Talens, Pau, Cubero, Sergio, Blasco, José
Formato: acceptedVersion
Lenguaje:Inglés
Publicado: Elsevier 2017
Materias:
Acceso en línea:http://hdl.handle.net/20.500.11939/5740
http://www.sciencedirect.com/science/article/pii/S0956713517305224?via%3Dihub
_version_ 1855032326655836160
author Munera, Sandra
Amigo, José M.
Aleixos, Nuria
Talens, Pau
Cubero, Sergio
Blasco, José
author_browse Aleixos, Nuria
Amigo, José M.
Blasco, José
Cubero, Sergio
Munera, Sandra
Talens, Pau
author_facet Munera, Sandra
Amigo, José M.
Aleixos, Nuria
Talens, Pau
Cubero, Sergio
Blasco, José
author_sort Munera, Sandra
collection ReDivia
description Product inspection is essential to ensure good quality and to avoid fraud. New nectarine cultivars with similar external appearance but different physicochemical properties may be mixed in the market, causing confusion and rejection among consumers, and consequently affecting sales and prices. Hyperspectral reflectance imaging in the range of 450–1040 nm was studied as a non-destructive method to differentiate two cultivars of nectarines with a very similar appearance but different taste. Partial least squares discriminant analysis (PLS-DA) was used to develop a prediction model to distinguish intact fruits of the cultivars using pixel-wise and mean spectrum approaches, and then the model was projected onto the complete surface of fruits allowing visual inspection. The results indicated that mean spectrum of the fruit was the most accurate method, a correct discrimination rate of 94% being achieved. Wavelength selection reduced the dimensionality of the hyperspectral images using the regression coefficients of the PLS-DA model. An accuracy of 96% was obtained by using 14 optimal wavelengths, whereas colour imaging and a trained inspection panel achieved a rate of correct classification of only 57% of the fruits.
format acceptedVersion
id ReDivia5740
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2017
publishDateRange 2017
publishDateSort 2017
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling ReDivia57402025-04-25T14:45:54Z Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine Munera, Sandra Amigo, José M. Aleixos, Nuria Talens, Pau Cubero, Sergio Blasco, José Stone fruit Quality control Cultivar discrimination Non-destructive PLS-DA Colour analysis Hyperspectral image Q01 Food science and technology Stone fruits Cultivars Quality controls Image processing Product inspection is essential to ensure good quality and to avoid fraud. New nectarine cultivars with similar external appearance but different physicochemical properties may be mixed in the market, causing confusion and rejection among consumers, and consequently affecting sales and prices. Hyperspectral reflectance imaging in the range of 450–1040 nm was studied as a non-destructive method to differentiate two cultivars of nectarines with a very similar appearance but different taste. Partial least squares discriminant analysis (PLS-DA) was used to develop a prediction model to distinguish intact fruits of the cultivars using pixel-wise and mean spectrum approaches, and then the model was projected onto the complete surface of fruits allowing visual inspection. The results indicated that mean spectrum of the fruit was the most accurate method, a correct discrimination rate of 94% being achieved. Wavelength selection reduced the dimensionality of the hyperspectral images using the regression coefficients of the PLS-DA model. An accuracy of 96% was obtained by using 14 optimal wavelengths, whereas colour imaging and a trained inspection panel achieved a rate of correct classification of only 57% of the fruits. 2017-12-12T15:45:38Z 2017-12-12T15:45:38Z 2018 acceptedVersion Munera S, Amigo J.M., Aleixos N, Talens P, Cubero S, Blasco J (2018). Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine. Food Control, 86, 1-10. 0956-7135 http://hdl.handle.net/20.500.11939/5740 10.1016/j.foodcont.2017.10.037 http://www.sciencedirect.com/science/article/pii/S0956713517305224?via%3Dihub en info:eu-repo/grantAgreement/MINECO/Programa estatal de i+D+i Orientada a los Retos de la Sociedad/RTA2015-00078-00-00//Sistemas no destructivos para la determinación automática de la calidad interna de frutas en línea utilizando métodos ópticos e información espectral Sistemas no destructivos para la determinación automática de la calidad interna de frutas en línea utilizando métodos ópticos e información espectral INIA (RTA2015-00078-00-00) Sistemas de sensado de interés agrario. Incorporación de tecnologías ópticas para evaluar la cantidad y calidad de la cosecha (IVIA 51431) Elsevier impreso
spellingShingle Stone fruit
Quality control
Cultivar discrimination
Non-destructive
PLS-DA
Colour analysis
Hyperspectral image
Q01 Food science and technology
Stone fruits
Cultivars
Quality controls
Image processing
Munera, Sandra
Amigo, José M.
Aleixos, Nuria
Talens, Pau
Cubero, Sergio
Blasco, José
Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine
title Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine
title_full Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine
title_fullStr Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine
title_full_unstemmed Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine
title_short Potential of VIS-NIR hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine
title_sort potential of vis nir hyperspectral imaging and chemometric methods to identify similar cultivars of nectarine
topic Stone fruit
Quality control
Cultivar discrimination
Non-destructive
PLS-DA
Colour analysis
Hyperspectral image
Q01 Food science and technology
Stone fruits
Cultivars
Quality controls
Image processing
url http://hdl.handle.net/20.500.11939/5740
http://www.sciencedirect.com/science/article/pii/S0956713517305224?via%3Dihub
work_keys_str_mv AT munerasandra potentialofvisnirhyperspectralimagingandchemometricmethodstoidentifysimilarcultivarsofnectarine
AT amigojosem potentialofvisnirhyperspectralimagingandchemometricmethodstoidentifysimilarcultivarsofnectarine
AT aleixosnuria potentialofvisnirhyperspectralimagingandchemometricmethodstoidentifysimilarcultivarsofnectarine
AT talenspau potentialofvisnirhyperspectralimagingandchemometricmethodstoidentifysimilarcultivarsofnectarine
AT cuberosergio potentialofvisnirhyperspectralimagingandchemometricmethodstoidentifysimilarcultivarsofnectarine
AT blascojose potentialofvisnirhyperspectralimagingandchemometricmethodstoidentifysimilarcultivarsofnectarine