Attention-based recurrent neural network for plant disease classification
Plant diseases have a significant impact on global food security and the world's agricultural economy. Their early detection and classification increase the chances of setting up effective control measures, which is why the search for automatic systems that allow this is of major interest to our society. Several recent studies have reported promising results in the classification of plant diseases from RGB images on the basis of Convolutional Neural Networks (CNN). These studies have been successfully experimented on a large number of crops and symptoms, and they have shown significant advantages in the support of human expertise. However, the CNN models still have limitations. In particular, CNN models do not necessarily focus on the visible parts affected by a plant disease to allow their classification, and they can sometimes take into account irrelevant backgrounds or healthy plant parts. In this paper, we therefore develop a new technique based on a Recurrent Neural Network (RNN) to automatically locate infected regions and extract relevant features for disease classification. We show experimentally that our RNN-based approach is more robust and has a greater ability to generalize to unseen infected crop species as well as to different plant disease domain images compared to classical CNN approaches. We also analyze the focus of attention as learned by our RNN and show that our approach is capable of accurately locating infectious diseases in plants. Our approach, which has been tested on a large number of plant species, should thus contribute to the development of more effective means of detecting and classifying crop pathogens in the near future.
Main Authors: | , , , |
---|---|
Format: | article biblioteca |
Language: | eng |
Subjects: | H20 - Maladies des plantes, H50 - Troubles divers des plantes, U30 - Méthodes de recherche, maladie des plantes, pathologie végétale, identification, réseau de neurones, classification, surveillance des cultures, mesure phytosanitaire, agent pathogène, http://aims.fao.org/aos/agrovoc/c_5962, http://aims.fao.org/aos/agrovoc/c_5974, http://aims.fao.org/aos/agrovoc/c_3791, http://aims.fao.org/aos/agrovoc/c_37467, http://aims.fao.org/aos/agrovoc/c_1653, http://aims.fao.org/aos/agrovoc/c_37838, http://aims.fao.org/aos/agrovoc/c_37922, http://aims.fao.org/aos/agrovoc/c_5630, |
Online Access: | http://agritrop.cirad.fr/598375/ http://agritrop.cirad.fr/598375/1/fpls-11-601250.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-cirad-fr-598375 |
---|---|
record_format |
koha |
spelling |
dig-cirad-fr-5983752024-01-29T03:33:08Z http://agritrop.cirad.fr/598375/ http://agritrop.cirad.fr/598375/ Attention-based recurrent neural network for plant disease classification. Lee Sue Han, Goeau Hervé, Bonnet Pierre, Joly Alexis. 2020. Frontiers in Plant Science, 11:601250, 8 p.https://doi.org/10.3389/fpls.2020.601250 <https://doi.org/10.3389/fpls.2020.601250> Attention-based recurrent neural network for plant disease classification Lee, Sue Han Goeau, Hervé Bonnet, Pierre Joly, Alexis eng 2020 Frontiers in Plant Science H20 - Maladies des plantes H50 - Troubles divers des plantes U30 - Méthodes de recherche maladie des plantes pathologie végétale identification réseau de neurones classification surveillance des cultures mesure phytosanitaire agent pathogène http://aims.fao.org/aos/agrovoc/c_5962 http://aims.fao.org/aos/agrovoc/c_5974 http://aims.fao.org/aos/agrovoc/c_3791 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1653 http://aims.fao.org/aos/agrovoc/c_37838 http://aims.fao.org/aos/agrovoc/c_37922 http://aims.fao.org/aos/agrovoc/c_5630 Plant diseases have a significant impact on global food security and the world's agricultural economy. Their early detection and classification increase the chances of setting up effective control measures, which is why the search for automatic systems that allow this is of major interest to our society. Several recent studies have reported promising results in the classification of plant diseases from RGB images on the basis of Convolutional Neural Networks (CNN). These studies have been successfully experimented on a large number of crops and symptoms, and they have shown significant advantages in the support of human expertise. However, the CNN models still have limitations. In particular, CNN models do not necessarily focus on the visible parts affected by a plant disease to allow their classification, and they can sometimes take into account irrelevant backgrounds or healthy plant parts. In this paper, we therefore develop a new technique based on a Recurrent Neural Network (RNN) to automatically locate infected regions and extract relevant features for disease classification. We show experimentally that our RNN-based approach is more robust and has a greater ability to generalize to unseen infected crop species as well as to different plant disease domain images compared to classical CNN approaches. We also analyze the focus of attention as learned by our RNN and show that our approach is capable of accurately locating infectious diseases in plants. Our approach, which has been tested on a large number of plant species, should thus contribute to the development of more effective means of detecting and classifying crop pathogens in the near future. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/publishedVersion http://agritrop.cirad.fr/598375/1/fpls-11-601250.pdf text cc_by info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/ https://doi.org/10.3389/fpls.2020.601250 10.3389/fpls.2020.601250 info:eu-repo/semantics/altIdentifier/doi/10.3389/fpls.2020.601250 info:eu-repo/semantics/altIdentifier/purl/https://doi.org/10.3389/fpls.2020.601250 info:eu-repo/semantics/dataset/purl/https://github.com/AdelineMomo/CNN-plant-disease |
institution |
CIRAD FR |
collection |
DSpace |
country |
Francia |
countrycode |
FR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-cirad-fr |
tag |
biblioteca |
region |
Europa del Oeste |
libraryname |
Biblioteca del CIRAD Francia |
language |
eng |
topic |
H20 - Maladies des plantes H50 - Troubles divers des plantes U30 - Méthodes de recherche maladie des plantes pathologie végétale identification réseau de neurones classification surveillance des cultures mesure phytosanitaire agent pathogène http://aims.fao.org/aos/agrovoc/c_5962 http://aims.fao.org/aos/agrovoc/c_5974 http://aims.fao.org/aos/agrovoc/c_3791 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1653 http://aims.fao.org/aos/agrovoc/c_37838 http://aims.fao.org/aos/agrovoc/c_37922 http://aims.fao.org/aos/agrovoc/c_5630 H20 - Maladies des plantes H50 - Troubles divers des plantes U30 - Méthodes de recherche maladie des plantes pathologie végétale identification réseau de neurones classification surveillance des cultures mesure phytosanitaire agent pathogène http://aims.fao.org/aos/agrovoc/c_5962 http://aims.fao.org/aos/agrovoc/c_5974 http://aims.fao.org/aos/agrovoc/c_3791 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1653 http://aims.fao.org/aos/agrovoc/c_37838 http://aims.fao.org/aos/agrovoc/c_37922 http://aims.fao.org/aos/agrovoc/c_5630 |
spellingShingle |
H20 - Maladies des plantes H50 - Troubles divers des plantes U30 - Méthodes de recherche maladie des plantes pathologie végétale identification réseau de neurones classification surveillance des cultures mesure phytosanitaire agent pathogène http://aims.fao.org/aos/agrovoc/c_5962 http://aims.fao.org/aos/agrovoc/c_5974 http://aims.fao.org/aos/agrovoc/c_3791 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1653 http://aims.fao.org/aos/agrovoc/c_37838 http://aims.fao.org/aos/agrovoc/c_37922 http://aims.fao.org/aos/agrovoc/c_5630 H20 - Maladies des plantes H50 - Troubles divers des plantes U30 - Méthodes de recherche maladie des plantes pathologie végétale identification réseau de neurones classification surveillance des cultures mesure phytosanitaire agent pathogène http://aims.fao.org/aos/agrovoc/c_5962 http://aims.fao.org/aos/agrovoc/c_5974 http://aims.fao.org/aos/agrovoc/c_3791 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1653 http://aims.fao.org/aos/agrovoc/c_37838 http://aims.fao.org/aos/agrovoc/c_37922 http://aims.fao.org/aos/agrovoc/c_5630 Lee, Sue Han Goeau, Hervé Bonnet, Pierre Joly, Alexis Attention-based recurrent neural network for plant disease classification |
description |
Plant diseases have a significant impact on global food security and the world's agricultural economy. Their early detection and classification increase the chances of setting up effective control measures, which is why the search for automatic systems that allow this is of major interest to our society. Several recent studies have reported promising results in the classification of plant diseases from RGB images on the basis of Convolutional Neural Networks (CNN). These studies have been successfully experimented on a large number of crops and symptoms, and they have shown significant advantages in the support of human expertise. However, the CNN models still have limitations. In particular, CNN models do not necessarily focus on the visible parts affected by a plant disease to allow their classification, and they can sometimes take into account irrelevant backgrounds or healthy plant parts. In this paper, we therefore develop a new technique based on a Recurrent Neural Network (RNN) to automatically locate infected regions and extract relevant features for disease classification. We show experimentally that our RNN-based approach is more robust and has a greater ability to generalize to unseen infected crop species as well as to different plant disease domain images compared to classical CNN approaches. We also analyze the focus of attention as learned by our RNN and show that our approach is capable of accurately locating infectious diseases in plants. Our approach, which has been tested on a large number of plant species, should thus contribute to the development of more effective means of detecting and classifying crop pathogens in the near future. |
format |
article |
topic_facet |
H20 - Maladies des plantes H50 - Troubles divers des plantes U30 - Méthodes de recherche maladie des plantes pathologie végétale identification réseau de neurones classification surveillance des cultures mesure phytosanitaire agent pathogène http://aims.fao.org/aos/agrovoc/c_5962 http://aims.fao.org/aos/agrovoc/c_5974 http://aims.fao.org/aos/agrovoc/c_3791 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1653 http://aims.fao.org/aos/agrovoc/c_37838 http://aims.fao.org/aos/agrovoc/c_37922 http://aims.fao.org/aos/agrovoc/c_5630 |
author |
Lee, Sue Han Goeau, Hervé Bonnet, Pierre Joly, Alexis |
author_facet |
Lee, Sue Han Goeau, Hervé Bonnet, Pierre Joly, Alexis |
author_sort |
Lee, Sue Han |
title |
Attention-based recurrent neural network for plant disease classification |
title_short |
Attention-based recurrent neural network for plant disease classification |
title_full |
Attention-based recurrent neural network for plant disease classification |
title_fullStr |
Attention-based recurrent neural network for plant disease classification |
title_full_unstemmed |
Attention-based recurrent neural network for plant disease classification |
title_sort |
attention-based recurrent neural network for plant disease classification |
url |
http://agritrop.cirad.fr/598375/ http://agritrop.cirad.fr/598375/1/fpls-11-601250.pdf |
work_keys_str_mv |
AT leesuehan attentionbasedrecurrentneuralnetworkforplantdiseaseclassification AT goeauherve attentionbasedrecurrentneuralnetworkforplantdiseaseclassification AT bonnetpierre attentionbasedrecurrentneuralnetworkforplantdiseaseclassification AT jolyalexis attentionbasedrecurrentneuralnetworkforplantdiseaseclassification |
_version_ |
1792500168622342144 |