Cargando…

Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties

Extending over millennia, grapevine cultivation encompasses several thousand cultivars. Cultivar (cultivated variety) identification is traditionally dealt by ampelography, requiring repeated observations by experts along the growth cycle of fruiting plants. For on-time evaluations, molecular geneti...

Descripción completa

Detalles Bibliográficos
Autores principales: Nasiri, Amin, Taheri-Garavand, Amin, Fanourakis, Dimitrios, Zhang, Yu-Dong, Nikoloudakis, Nikolaos
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8399703/
https://www.ncbi.nlm.nih.gov/pubmed/34451673
http://dx.doi.org/10.3390/plants10081628
_version_ 1783745141476950016
author Nasiri, Amin
Taheri-Garavand, Amin
Fanourakis, Dimitrios
Zhang, Yu-Dong
Nikoloudakis, Nikolaos
author_facet Nasiri, Amin
Taheri-Garavand, Amin
Fanourakis, Dimitrios
Zhang, Yu-Dong
Nikoloudakis, Nikolaos
author_sort Nasiri, Amin
collection PubMed
description Extending over millennia, grapevine cultivation encompasses several thousand cultivars. Cultivar (cultivated variety) identification is traditionally dealt by ampelography, requiring repeated observations by experts along the growth cycle of fruiting plants. For on-time evaluations, molecular genetics have been successfully performed, though in many instances, they are limited by the lack of referable data or the cost element. This paper presents a convolutional neural network (CNN) framework for automatic identification of grapevine cultivar by using leaf images in the visible spectrum (400–700 nm). The VGG16 architecture was modified by a global average pooling layer, dense layers, a batch normalization layer, and a dropout layer. Distinguishing the intricate visual features of diverse grapevine varieties, and recognizing them according to these features was conceivable by the obtained model. A five-fold cross-validation was performed to evaluate the uncertainty and predictive efficiency of the CNN model. The modified deep learning model was able to recognize different grapevine varieties with an average classification accuracy of over 99%. The obtained model offers a rapid, low-cost and high-throughput grapevine cultivar identification. The ambition of the obtained tool is not to substitute but complement ampelography and quantitative genetics, and in this way, assist cultivar identification services.
format Online
Article
Text
id pubmed-8399703
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83997032021-08-29 Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties Nasiri, Amin Taheri-Garavand, Amin Fanourakis, Dimitrios Zhang, Yu-Dong Nikoloudakis, Nikolaos Plants (Basel) Article Extending over millennia, grapevine cultivation encompasses several thousand cultivars. Cultivar (cultivated variety) identification is traditionally dealt by ampelography, requiring repeated observations by experts along the growth cycle of fruiting plants. For on-time evaluations, molecular genetics have been successfully performed, though in many instances, they are limited by the lack of referable data or the cost element. This paper presents a convolutional neural network (CNN) framework for automatic identification of grapevine cultivar by using leaf images in the visible spectrum (400–700 nm). The VGG16 architecture was modified by a global average pooling layer, dense layers, a batch normalization layer, and a dropout layer. Distinguishing the intricate visual features of diverse grapevine varieties, and recognizing them according to these features was conceivable by the obtained model. A five-fold cross-validation was performed to evaluate the uncertainty and predictive efficiency of the CNN model. The modified deep learning model was able to recognize different grapevine varieties with an average classification accuracy of over 99%. The obtained model offers a rapid, low-cost and high-throughput grapevine cultivar identification. The ambition of the obtained tool is not to substitute but complement ampelography and quantitative genetics, and in this way, assist cultivar identification services. MDPI 2021-08-08 /pmc/articles/PMC8399703/ /pubmed/34451673 http://dx.doi.org/10.3390/plants10081628 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Nasiri, Amin
Taheri-Garavand, Amin
Fanourakis, Dimitrios
Zhang, Yu-Dong
Nikoloudakis, Nikolaos
Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties
title Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties
title_full Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties
title_fullStr Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties
title_full_unstemmed Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties
title_short Automated Grapevine Cultivar Identification via Leaf Imaging and Deep Convolutional Neural Networks: A Proof-of-Concept Study Employing Primary Iranian Varieties
title_sort automated grapevine cultivar identification via leaf imaging and deep convolutional neural networks: a proof-of-concept study employing primary iranian varieties
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8399703/
https://www.ncbi.nlm.nih.gov/pubmed/34451673
http://dx.doi.org/10.3390/plants10081628
work_keys_str_mv AT nasiriamin automatedgrapevinecultivaridentificationvialeafimaginganddeepconvolutionalneuralnetworksaproofofconceptstudyemployingprimaryiranianvarieties
AT taherigaravandamin automatedgrapevinecultivaridentificationvialeafimaginganddeepconvolutionalneuralnetworksaproofofconceptstudyemployingprimaryiranianvarieties
AT fanourakisdimitrios automatedgrapevinecultivaridentificationvialeafimaginganddeepconvolutionalneuralnetworksaproofofconceptstudyemployingprimaryiranianvarieties
AT zhangyudong automatedgrapevinecultivaridentificationvialeafimaginganddeepconvolutionalneuralnetworksaproofofconceptstudyemployingprimaryiranianvarieties
AT nikoloudakisnikolaos automatedgrapevinecultivaridentificationvialeafimaginganddeepconvolutionalneuralnetworksaproofofconceptstudyemployingprimaryiranianvarieties