Cargando…

A novel method for maize leaf disease classification using the RGB-D post-segmentation image data

Maize (Zea mays L.) is one of the most important crops, influencing food production and even the whole industry. In recent years, global crop production has been facing great challenges from diseases. However, most of the traditional methods make it difficult to efficiently identify disease-related...

Descripción completa

Detalles Bibliográficos
Autores principales: Nan, Fei, Song, Yang, Yu, Xun, Nie, Chenwei, Liu, Yadong, Bai, Yali, Zou, Dongxiao, Wang, Chao, Yin, Dameng, Yang, Wude, Jin, Xiuliang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10562608/
https://www.ncbi.nlm.nih.gov/pubmed/37822341
http://dx.doi.org/10.3389/fpls.2023.1268015
_version_ 1785118165930344448
author Nan, Fei
Song, Yang
Yu, Xun
Nie, Chenwei
Liu, Yadong
Bai, Yali
Zou, Dongxiao
Wang, Chao
Yin, Dameng
Yang, Wude
Jin, Xiuliang
author_facet Nan, Fei
Song, Yang
Yu, Xun
Nie, Chenwei
Liu, Yadong
Bai, Yali
Zou, Dongxiao
Wang, Chao
Yin, Dameng
Yang, Wude
Jin, Xiuliang
author_sort Nan, Fei
collection PubMed
description Maize (Zea mays L.) is one of the most important crops, influencing food production and even the whole industry. In recent years, global crop production has been facing great challenges from diseases. However, most of the traditional methods make it difficult to efficiently identify disease-related phenotypes in germplasm resources, especially in actual field environments. To overcome this limitation, our study aims to evaluate the potential of the multi-sensor synchronized RGB-D camera with depth information for maize leaf disease classification. We distinguished maize leaves from the background based on the RGB-D depth information to eliminate interference from complex field environments. Four deep learning models (i.e., Resnet50, MobilenetV2, Vgg16, and Efficientnet-B3) were used to classify three main types of maize diseases, i.e., the curvularia leaf spot [Curvularia lunata (Wakker) Boedijn], the small spot [Bipolaris maydis (Nishik.) Shoemaker], and the mixed spot diseases. We finally compared the pre-segmentation and post-segmentation results to test the robustness of the above models. Our main findings are: 1) The maize disease classification models based on the pre-segmentation image data performed slightly better than the ones based on the post-segmentation image data. 2) The pre-segmentation models overestimated the accuracy of disease classification due to the complexity of the background, but post-segmentation models focusing on leaf disease features provided more practical results with shorter prediction times. 3) Among the post-segmentation models, the Resnet50 and MobilenetV2 models showed similar accuracy and were better than the Vgg16 and Efficientnet-B3 models, and the MobilenetV2 model performed better than the other three models in terms of the size and the single image prediction time. Overall, this study provides a novel method for maize leaf disease classification using the post-segmentation image data from a multi-sensor synchronized RGB-D camera and offers the possibility of developing relevant portable devices.
format Online
Article
Text
id pubmed-10562608
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-105626082023-10-11 A novel method for maize leaf disease classification using the RGB-D post-segmentation image data Nan, Fei Song, Yang Yu, Xun Nie, Chenwei Liu, Yadong Bai, Yali Zou, Dongxiao Wang, Chao Yin, Dameng Yang, Wude Jin, Xiuliang Front Plant Sci Plant Science Maize (Zea mays L.) is one of the most important crops, influencing food production and even the whole industry. In recent years, global crop production has been facing great challenges from diseases. However, most of the traditional methods make it difficult to efficiently identify disease-related phenotypes in germplasm resources, especially in actual field environments. To overcome this limitation, our study aims to evaluate the potential of the multi-sensor synchronized RGB-D camera with depth information for maize leaf disease classification. We distinguished maize leaves from the background based on the RGB-D depth information to eliminate interference from complex field environments. Four deep learning models (i.e., Resnet50, MobilenetV2, Vgg16, and Efficientnet-B3) were used to classify three main types of maize diseases, i.e., the curvularia leaf spot [Curvularia lunata (Wakker) Boedijn], the small spot [Bipolaris maydis (Nishik.) Shoemaker], and the mixed spot diseases. We finally compared the pre-segmentation and post-segmentation results to test the robustness of the above models. Our main findings are: 1) The maize disease classification models based on the pre-segmentation image data performed slightly better than the ones based on the post-segmentation image data. 2) The pre-segmentation models overestimated the accuracy of disease classification due to the complexity of the background, but post-segmentation models focusing on leaf disease features provided more practical results with shorter prediction times. 3) Among the post-segmentation models, the Resnet50 and MobilenetV2 models showed similar accuracy and were better than the Vgg16 and Efficientnet-B3 models, and the MobilenetV2 model performed better than the other three models in terms of the size and the single image prediction time. Overall, this study provides a novel method for maize leaf disease classification using the post-segmentation image data from a multi-sensor synchronized RGB-D camera and offers the possibility of developing relevant portable devices. Frontiers Media S.A. 2023-09-26 /pmc/articles/PMC10562608/ /pubmed/37822341 http://dx.doi.org/10.3389/fpls.2023.1268015 Text en Copyright © 2023 Nan, Song, Yu, Nie, Liu, Bai, Zou, Wang, Yin, Yang and Jin 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
Nan, Fei
Song, Yang
Yu, Xun
Nie, Chenwei
Liu, Yadong
Bai, Yali
Zou, Dongxiao
Wang, Chao
Yin, Dameng
Yang, Wude
Jin, Xiuliang
A novel method for maize leaf disease classification using the RGB-D post-segmentation image data
title A novel method for maize leaf disease classification using the RGB-D post-segmentation image data
title_full A novel method for maize leaf disease classification using the RGB-D post-segmentation image data
title_fullStr A novel method for maize leaf disease classification using the RGB-D post-segmentation image data
title_full_unstemmed A novel method for maize leaf disease classification using the RGB-D post-segmentation image data
title_short A novel method for maize leaf disease classification using the RGB-D post-segmentation image data
title_sort novel method for maize leaf disease classification using the rgb-d post-segmentation image data
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10562608/
https://www.ncbi.nlm.nih.gov/pubmed/37822341
http://dx.doi.org/10.3389/fpls.2023.1268015
work_keys_str_mv AT nanfei anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT songyang anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT yuxun anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT niechenwei anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT liuyadong anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT baiyali anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT zoudongxiao anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT wangchao anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT yindameng anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT yangwude anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT jinxiuliang anovelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT nanfei novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT songyang novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT yuxun novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT niechenwei novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT liuyadong novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT baiyali novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT zoudongxiao novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT wangchao novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT yindameng novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT yangwude novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata
AT jinxiuliang novelmethodformaizeleafdiseaseclassificationusingthergbdpostsegmentationimagedata