Cargando…

Classification and localization of maize leaf spot disease based on weakly supervised learning

Precisely discerning disease types and vulnerable areas is crucial in implementing effective monitoring of crop production. This forms the basis for generating targeted plant protection recommendations and automatic, precise applications. In this study, we constructed a dataset comprising six types...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Shuai, Xing, Ziyao, Wang, Hengbin, Gao, Xiang, Dong, Xinrui, Yao, Yu, Zhang, Runda, Zhang, Xiaodong, Li, Shaoming, Zhao, Yuanyuan, Liu, Zhe
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10201986/
https://www.ncbi.nlm.nih.gov/pubmed/37223797
http://dx.doi.org/10.3389/fpls.2023.1128399
_version_ 1785045355812880384
author Yang, Shuai
Xing, Ziyao
Wang, Hengbin
Gao, Xiang
Dong, Xinrui
Yao, Yu
Zhang, Runda
Zhang, Xiaodong
Li, Shaoming
Zhao, Yuanyuan
Liu, Zhe
author_facet Yang, Shuai
Xing, Ziyao
Wang, Hengbin
Gao, Xiang
Dong, Xinrui
Yao, Yu
Zhang, Runda
Zhang, Xiaodong
Li, Shaoming
Zhao, Yuanyuan
Liu, Zhe
author_sort Yang, Shuai
collection PubMed
description Precisely discerning disease types and vulnerable areas is crucial in implementing effective monitoring of crop production. This forms the basis for generating targeted plant protection recommendations and automatic, precise applications. In this study, we constructed a dataset comprising six types of field maize leaf images and developed a framework for classifying and localizing maize leaf diseases. Our approach involved integrating lightweight convolutional neural networks with interpretable AI algorithms, which resulted in high classification accuracy and fast detection speeds. To evaluate the performance of our framework, we tested the mean Intersection over Union (mIoU) of localized disease spot coverage and actual disease spot coverage when relying solely on image-level annotations. The results showed that our framework achieved a mIoU of up to 55.302%, indicating the feasibility of using weakly supervised semantic segmentation based on class activation mapping techniques for identifying disease spots in crop disease detection. This approach, which combines deep learning models with visualization techniques, improves the interpretability of the deep learning models and achieves successful localization of infected areas of maize leaves through weakly supervised learning. The framework allows for smart monitoring of crop diseases and plant protection operations using mobile phones, smart farm machines, and other devices. Furthermore, it offers a reference for deep learning research on crop diseases.
format Online
Article
Text
id pubmed-10201986
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-102019862023-05-23 Classification and localization of maize leaf spot disease based on weakly supervised learning Yang, Shuai Xing, Ziyao Wang, Hengbin Gao, Xiang Dong, Xinrui Yao, Yu Zhang, Runda Zhang, Xiaodong Li, Shaoming Zhao, Yuanyuan Liu, Zhe Front Plant Sci Plant Science Precisely discerning disease types and vulnerable areas is crucial in implementing effective monitoring of crop production. This forms the basis for generating targeted plant protection recommendations and automatic, precise applications. In this study, we constructed a dataset comprising six types of field maize leaf images and developed a framework for classifying and localizing maize leaf diseases. Our approach involved integrating lightweight convolutional neural networks with interpretable AI algorithms, which resulted in high classification accuracy and fast detection speeds. To evaluate the performance of our framework, we tested the mean Intersection over Union (mIoU) of localized disease spot coverage and actual disease spot coverage when relying solely on image-level annotations. The results showed that our framework achieved a mIoU of up to 55.302%, indicating the feasibility of using weakly supervised semantic segmentation based on class activation mapping techniques for identifying disease spots in crop disease detection. This approach, which combines deep learning models with visualization techniques, improves the interpretability of the deep learning models and achieves successful localization of infected areas of maize leaves through weakly supervised learning. The framework allows for smart monitoring of crop diseases and plant protection operations using mobile phones, smart farm machines, and other devices. Furthermore, it offers a reference for deep learning research on crop diseases. Frontiers Media S.A. 2023-05-08 /pmc/articles/PMC10201986/ /pubmed/37223797 http://dx.doi.org/10.3389/fpls.2023.1128399 Text en Copyright © 2023 Yang, Xing, Wang, Gao, Dong, Yao, Zhang, Zhang, Li, Zhao and Liu 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
Yang, Shuai
Xing, Ziyao
Wang, Hengbin
Gao, Xiang
Dong, Xinrui
Yao, Yu
Zhang, Runda
Zhang, Xiaodong
Li, Shaoming
Zhao, Yuanyuan
Liu, Zhe
Classification and localization of maize leaf spot disease based on weakly supervised learning
title Classification and localization of maize leaf spot disease based on weakly supervised learning
title_full Classification and localization of maize leaf spot disease based on weakly supervised learning
title_fullStr Classification and localization of maize leaf spot disease based on weakly supervised learning
title_full_unstemmed Classification and localization of maize leaf spot disease based on weakly supervised learning
title_short Classification and localization of maize leaf spot disease based on weakly supervised learning
title_sort classification and localization of maize leaf spot disease based on weakly supervised learning
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10201986/
https://www.ncbi.nlm.nih.gov/pubmed/37223797
http://dx.doi.org/10.3389/fpls.2023.1128399
work_keys_str_mv AT yangshuai classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT xingziyao classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT wanghengbin classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT gaoxiang classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT dongxinrui classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT yaoyu classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT zhangrunda classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT zhangxiaodong classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT lishaoming classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT zhaoyuanyuan classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning
AT liuzhe classificationandlocalizationofmaizeleafspotdiseasebasedonweaklysupervisedlearning