Cargando…

Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes

Recognizing plant diseases is a major challenge in agriculture, and recent works based on deep learning have shown high efficiency in addressing problems directly related to this area. Nonetheless, weak performance has been observed when a model trained on a particular dataset is evaluated in new gr...

Descripción completa

Detalles Bibliográficos
Autores principales: Fuentes, Alvaro, Yoon, Sook, Lee, Mun Haeng, Park, Dong Sun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8716922/
https://www.ncbi.nlm.nih.gov/pubmed/34975931
http://dx.doi.org/10.3389/fpls.2021.682230
_version_ 1784624423494483968
author Fuentes, Alvaro
Yoon, Sook
Lee, Mun Haeng
Park, Dong Sun
author_facet Fuentes, Alvaro
Yoon, Sook
Lee, Mun Haeng
Park, Dong Sun
author_sort Fuentes, Alvaro
collection PubMed
description Recognizing plant diseases is a major challenge in agriculture, and recent works based on deep learning have shown high efficiency in addressing problems directly related to this area. Nonetheless, weak performance has been observed when a model trained on a particular dataset is evaluated in new greenhouse environments. Therefore, in this work, we take a step towards these issues and present a strategy to improve model accuracy by applying techniques that can help refine the model’s generalization capability to deal with complex changes in new greenhouse environments. We propose a paradigm called “control to target classes.” The core of our approach is to train and validate a deep learning-based detector using target and control classes on images collected in various greenhouses. Then, we apply the generated features for testing the inference of the system on data from new greenhouse conditions where the goal is to detect target classes exclusively. Therefore, by having explicit control over inter- and intra-class variations, our model can distinguish data variations that make the system more robust when applied to new scenarios. Experiments demonstrate the effectiveness and efficiency of the proposed approach on our extended tomato plant diseases dataset with 14 classes, from which 5 are target classes and the rest are control classes. Our detector achieves a recognition rate of target classes of 93.37% mean average precision on the inference dataset. Finally, we believe that our study offers valuable guidelines for researchers working in plant disease recognition with complex input data.
format Online
Article
Text
id pubmed-8716922
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-87169222021-12-31 Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes Fuentes, Alvaro Yoon, Sook Lee, Mun Haeng Park, Dong Sun Front Plant Sci Plant Science Recognizing plant diseases is a major challenge in agriculture, and recent works based on deep learning have shown high efficiency in addressing problems directly related to this area. Nonetheless, weak performance has been observed when a model trained on a particular dataset is evaluated in new greenhouse environments. Therefore, in this work, we take a step towards these issues and present a strategy to improve model accuracy by applying techniques that can help refine the model’s generalization capability to deal with complex changes in new greenhouse environments. We propose a paradigm called “control to target classes.” The core of our approach is to train and validate a deep learning-based detector using target and control classes on images collected in various greenhouses. Then, we apply the generated features for testing the inference of the system on data from new greenhouse conditions where the goal is to detect target classes exclusively. Therefore, by having explicit control over inter- and intra-class variations, our model can distinguish data variations that make the system more robust when applied to new scenarios. Experiments demonstrate the effectiveness and efficiency of the proposed approach on our extended tomato plant diseases dataset with 14 classes, from which 5 are target classes and the rest are control classes. Our detector achieves a recognition rate of target classes of 93.37% mean average precision on the inference dataset. Finally, we believe that our study offers valuable guidelines for researchers working in plant disease recognition with complex input data. Frontiers Media S.A. 2021-12-16 /pmc/articles/PMC8716922/ /pubmed/34975931 http://dx.doi.org/10.3389/fpls.2021.682230 Text en Copyright © 2021 Fuentes, Yoon, Lee and Park. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Fuentes, Alvaro
Yoon, Sook
Lee, Mun Haeng
Park, Dong Sun
Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes
title Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes
title_full Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes
title_fullStr Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes
title_full_unstemmed Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes
title_short Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes
title_sort improving accuracy of tomato plant disease diagnosis based on deep learning with explicit control of hidden classes
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8716922/
https://www.ncbi.nlm.nih.gov/pubmed/34975931
http://dx.doi.org/10.3389/fpls.2021.682230
work_keys_str_mv AT fuentesalvaro improvingaccuracyoftomatoplantdiseasediagnosisbasedondeeplearningwithexplicitcontrolofhiddenclasses
AT yoonsook improvingaccuracyoftomatoplantdiseasediagnosisbasedondeeplearningwithexplicitcontrolofhiddenclasses
AT leemunhaeng improvingaccuracyoftomatoplantdiseasediagnosisbasedondeeplearningwithexplicitcontrolofhiddenclasses
AT parkdongsun improvingaccuracyoftomatoplantdiseasediagnosisbasedondeeplearningwithexplicitcontrolofhiddenclasses