Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images

Anthracnose is one of the primary diseases that affect olive production before and after harvest, causing severe damage and economic losses. The objective of this work is to detect this disease in the early stages, using hyperspectral images and advanced modelling techniques of Deep Learning (DL) an...

Full description

Bibliographic Details
Main Authors: Fazari, Antonio, Pellicer-Valero, Óscar, Gómez-Sanchís, Juan, Bernardi, Bruno, Cubero, Sergio, Benalia, Souraya, Zimbalatti, Giuseppe, Blasco, José
Format: contributionToPeriodical
Language:Inglés
Published: Elsevier 2022
Subjects:
Online Access:http://hdl.handle.net/20.500.11939/7962
https://www.sciencedirect.com/science/article/pii/S0168169921002696
_version_ 1855032703845400576
author Fazari, Antonio
Pellicer-Valero, Óscar
Gómez-Sanchís, Juan
Bernardi, Bruno
Cubero, Sergio
Benalia, Souraya
Zimbalatti, Giuseppe
Blasco, José
author_browse Benalia, Souraya
Bernardi, Bruno
Blasco, José
Cubero, Sergio
Fazari, Antonio
Gómez-Sanchís, Juan
Pellicer-Valero, Óscar
Zimbalatti, Giuseppe
author_facet Fazari, Antonio
Pellicer-Valero, Óscar
Gómez-Sanchís, Juan
Bernardi, Bruno
Cubero, Sergio
Benalia, Souraya
Zimbalatti, Giuseppe
Blasco, José
author_sort Fazari, Antonio
collection ReDivia
description Anthracnose is one of the primary diseases that affect olive production before and after harvest, causing severe damage and economic losses. The objective of this work is to detect this disease in the early stages, using hyperspectral images and advanced modelling techniques of Deep Learning (DL) and convolutional neural networks (CNN). The olives were artificially inoculated with the fungus. Hyperspectral images (450–1050 nm) of each olive were acquired until visual symptoms of the disease were observed, in some cases up to 9 days. The olives were classified into two classes: control, inoculated with water, and fungi composed of olives inoculated with the fungus. The ResNet101 architecture was chosen and adapted to process 61-band hyperspectral images with only two classes. The result showed that the applied model is very effective in detecting infected olives since the sensitivity of the method was very high from the beginning (85% on day 3 and 100% onwards). From a commercial point of view, these results align with the need to detect the maximum number of infected fruits.
format contributionToPeriodical
id ReDivia7962
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling ReDivia79622025-04-25T14:48:45Z Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images Fazari, Antonio Pellicer-Valero, Óscar Gómez-Sanchís, Juan Bernardi, Bruno Cubero, Sergio Benalia, Souraya Zimbalatti, Giuseppe Blasco, José Quality inspection Spectral imaging N01 Agricultural engineering U30 Research methods H20 Plant diseases Olea europaea quality Fungi Computer vision Anthracnose is one of the primary diseases that affect olive production before and after harvest, causing severe damage and economic losses. The objective of this work is to detect this disease in the early stages, using hyperspectral images and advanced modelling techniques of Deep Learning (DL) and convolutional neural networks (CNN). The olives were artificially inoculated with the fungus. Hyperspectral images (450–1050 nm) of each olive were acquired until visual symptoms of the disease were observed, in some cases up to 9 days. The olives were classified into two classes: control, inoculated with water, and fungi composed of olives inoculated with the fungus. The ResNet101 architecture was chosen and adapted to process 61-band hyperspectral images with only two classes. The result showed that the applied model is very effective in detecting infected olives since the sensitivity of the method was very high from the beginning (85% on day 3 and 100% onwards). From a commercial point of view, these results align with the need to detect the maximum number of infected fruits. 2022-03-15T12:41:18Z 2022-03-15T12:41:18Z 2021 contributionToPeriodical Fazari, A., Pellicer-Valero, O. J., Gómez-Sanchıs, J., Bernardi, B., Cubero, S., Benalia, S. et al.(2021). Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images. Computers and Electronics in Agriculture, 187, 106252. 0168-1699 http://hdl.handle.net/20.500.11939/7962 10.1016/j.compag.2021.106252 https://www.sciencedirect.com/science/article/pii/S0168169921002696 en info:eu-repo/grantAgreement/ERDF/POCV 2014-2020/51918 This work is co-funded by the projects AEI PID2019-107347RRC31, PID2019-107347RR-C33, IVIA-GVA 51918 and the European Union through the European Regional Development Fund (ERDF) of the Generalitat Valenciana 2014–2020. Atribución-NoComercial-SinDerivadas 3.0 España http://creativecommons.org/licenses/by-nc-nd/3.0/es/ openAccess Elsevier electronico
spellingShingle Quality inspection
Spectral imaging
N01 Agricultural engineering
U30 Research methods
H20 Plant diseases
Olea europaea
quality
Fungi
Computer vision
Fazari, Antonio
Pellicer-Valero, Óscar
Gómez-Sanchís, Juan
Bernardi, Bruno
Cubero, Sergio
Benalia, Souraya
Zimbalatti, Giuseppe
Blasco, José
Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images
title Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images
title_full Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images
title_fullStr Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images
title_full_unstemmed Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images
title_short Application of deep convolutional neural networks for the detection of anthracnose in olives using VIS/NIR hyperspectral images
title_sort application of deep convolutional neural networks for the detection of anthracnose in olives using vis nir hyperspectral images
topic Quality inspection
Spectral imaging
N01 Agricultural engineering
U30 Research methods
H20 Plant diseases
Olea europaea
quality
Fungi
Computer vision
url http://hdl.handle.net/20.500.11939/7962
https://www.sciencedirect.com/science/article/pii/S0168169921002696
work_keys_str_mv AT fazariantonio applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages
AT pellicervalerooscar applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages
AT gomezsanchisjuan applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages
AT bernardibruno applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages
AT cuberosergio applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages
AT benaliasouraya applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages
AT zimbalattigiuseppe applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages
AT blascojose applicationofdeepconvolutionalneuralnetworksforthedetectionofanthracnoseinolivesusingvisnirhyperspectralimages