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...
Autores principales: | , , , |
---|---|
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 |