Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning

Mango fruit are sensitive and can easily develop brown spots after suffering mechanical stress during postharvest handling, transport and marketing. The manual inspection of this fruit used today cannot detect the damage in very early stages of maturity and to date no automatic tool capable of such...

Full description

Bibliographic Details
Main Authors: Vélez-Rivera, Nayeli, Gómez-Sanchís, Juan, Chanona-Perez, Jorge, Carrasco, Juan José, Millán-Giraldo, Mónica, Lorente, Delia, Cubero, Sergio, Blasco, José
Format: article
Language:Inglés
Published: 2017
Online Access:http://hdl.handle.net/20.500.11939/4689
_version_ 1855032161728462848
author Vélez-Rivera, Nayeli
Gómez-Sanchís, Juan
Chanona-Perez, Jorge
Carrasco, Juan José
Millán-Giraldo, Mónica
Lorente, Delia
Cubero, Sergio
Blasco, José
author_browse Blasco, José
Carrasco, Juan José
Chanona-Perez, Jorge
Cubero, Sergio
Gómez-Sanchís, Juan
Lorente, Delia
Millán-Giraldo, Mónica
Vélez-Rivera, Nayeli
author_facet Vélez-Rivera, Nayeli
Gómez-Sanchís, Juan
Chanona-Perez, Jorge
Carrasco, Juan José
Millán-Giraldo, Mónica
Lorente, Delia
Cubero, Sergio
Blasco, José
author_sort Vélez-Rivera, Nayeli
collection ReDivia
description Mango fruit are sensitive and can easily develop brown spots after suffering mechanical stress during postharvest handling, transport and marketing. The manual inspection of this fruit used today cannot detect the damage in very early stages of maturity and to date no automatic tool capable of such detection has been developed, since current systems based on machine vision only detect very visible damage. The application of hyperspectral imaging to the postharvest quality inspection of fruit is relatively recent and research is still underway to find a method of estimating internal properties or detecting invisible damage. This work describes a new system to evaluate mechanically induced damage in the pericarp of ‘Manila’ mangos at different stages of ripeness based on the analysis of hyperspectral images. Images of damaged and intact areas of mangos were acquired in the range 650–1100 nm using a hyperspectral computer vision system and then analysed to select the most discriminating wavelengths for distinguishing and classifying the two zones. Eleven feature-selection methods were used and compared to determine the wavelengths, while another five classification methods were used to segment the resulting multispectral images and classify the skin of the mangos as sound or damaged. A 97.9% rate of correct classification of pixels was achieved on the third day after the damage had been caused using k-Nearest Neighbours and the whole spectra and the figure dropped to 91.4% when only the most discriminant bands were used.
format article
id ReDivia4689
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2017
publishDateRange 2017
publishDateSort 2017
record_format dspace
spelling ReDivia46892025-04-25T14:44:10Z Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning Vélez-Rivera, Nayeli Gómez-Sanchís, Juan Chanona-Perez, Jorge Carrasco, Juan José Millán-Giraldo, Mónica Lorente, Delia Cubero, Sergio Blasco, José Mango fruit are sensitive and can easily develop brown spots after suffering mechanical stress during postharvest handling, transport and marketing. The manual inspection of this fruit used today cannot detect the damage in very early stages of maturity and to date no automatic tool capable of such detection has been developed, since current systems based on machine vision only detect very visible damage. The application of hyperspectral imaging to the postharvest quality inspection of fruit is relatively recent and research is still underway to find a method of estimating internal properties or detecting invisible damage. This work describes a new system to evaluate mechanically induced damage in the pericarp of ‘Manila’ mangos at different stages of ripeness based on the analysis of hyperspectral images. Images of damaged and intact areas of mangos were acquired in the range 650–1100 nm using a hyperspectral computer vision system and then analysed to select the most discriminating wavelengths for distinguishing and classifying the two zones. Eleven feature-selection methods were used and compared to determine the wavelengths, while another five classification methods were used to segment the resulting multispectral images and classify the skin of the mangos as sound or damaged. A 97.9% rate of correct classification of pixels was achieved on the third day after the damage had been caused using k-Nearest Neighbours and the whole spectra and the figure dropped to 91.4% when only the most discriminant bands were used. 2017-06-01T10:10:45Z 2017-06-01T10:10:45Z 2014 JUN 2014 article Velez Rivera, N., Gomez-Sanchis, J., Chanona-Perez, J., J. Carrasco, J., Millan-Giraldo, M., Lorente, D. et al. (2014). Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning. Biosystems Engineering, 122, 91-98. 1537-5110 http://hdl.handle.net/20.500.11939/4689 10.1016/j.biosystemseng.2014.03.009 en openAccess Impreso
spellingShingle Vélez-Rivera, Nayeli
Gómez-Sanchís, Juan
Chanona-Perez, Jorge
Carrasco, Juan José
Millán-Giraldo, Mónica
Lorente, Delia
Cubero, Sergio
Blasco, José
Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning
title Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning
title_full Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning
title_fullStr Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning
title_full_unstemmed Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning
title_short Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning
title_sort early detection of mechanical damage in mango using nir hyperspectral images and machine learning
url http://hdl.handle.net/20.500.11939/4689
work_keys_str_mv AT velezriveranayeli earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning
AT gomezsanchisjuan earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning
AT chanonaperezjorge earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning
AT carrascojuanjose earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning
AT millangiraldomonica earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning
AT lorentedelia earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning
AT cuberosergio earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning
AT blascojose earlydetectionofmechanicaldamageinmangousingnirhyperspectralimagesandmachinelearning