Cargando…

Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network

Detecting plant diseases in the earliest stages, when remedial intervention is most effective, is critical if damage crop quality and farm productivity is to be contained. In this paper, we propose an improved vision-based method of detecting strawberry diseases using a deep neural network (DNN) cap...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Byoungjun, Han, You-Kyoung, Park, Jong-Han, Lee, Joonwhoan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7874225/
https://www.ncbi.nlm.nih.gov/pubmed/33584739
http://dx.doi.org/10.3389/fpls.2020.559172
_version_ 1783649549064077312
author Kim, Byoungjun
Han, You-Kyoung
Park, Jong-Han
Lee, Joonwhoan
author_facet Kim, Byoungjun
Han, You-Kyoung
Park, Jong-Han
Lee, Joonwhoan
author_sort Kim, Byoungjun
collection PubMed
description Detecting plant diseases in the earliest stages, when remedial intervention is most effective, is critical if damage crop quality and farm productivity is to be contained. In this paper, we propose an improved vision-based method of detecting strawberry diseases using a deep neural network (DNN) capable of being incorporated into an automated robot system. In the proposed approach, a backbone feature extractor named PlantNet, pre-trained on the PlantCLEF plant dataset from the LifeCLEF 2017 challenge, is installed in a two-stage cascade disease detection model. PlantNet captures plant domain knowledge so well that it outperforms a pre-trained backbone using an ImageNet-type public dataset by at least 3.2% in mean Average Precision (mAP). The cascade detector also improves accuracy by up to 5.25% mAP. The results indicate that PlantNet is one way to overcome the lack-of-annotated-data problem by applying plant domain knowledge, and that the human-like cascade detection strategy effectively improves the accuracy of automated disease detection methods when applied to strawberry plants.
format Online
Article
Text
id pubmed-7874225
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78742252021-02-11 Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network Kim, Byoungjun Han, You-Kyoung Park, Jong-Han Lee, Joonwhoan Front Plant Sci Plant Science Detecting plant diseases in the earliest stages, when remedial intervention is most effective, is critical if damage crop quality and farm productivity is to be contained. In this paper, we propose an improved vision-based method of detecting strawberry diseases using a deep neural network (DNN) capable of being incorporated into an automated robot system. In the proposed approach, a backbone feature extractor named PlantNet, pre-trained on the PlantCLEF plant dataset from the LifeCLEF 2017 challenge, is installed in a two-stage cascade disease detection model. PlantNet captures plant domain knowledge so well that it outperforms a pre-trained backbone using an ImageNet-type public dataset by at least 3.2% in mean Average Precision (mAP). The cascade detector also improves accuracy by up to 5.25% mAP. The results indicate that PlantNet is one way to overcome the lack-of-annotated-data problem by applying plant domain knowledge, and that the human-like cascade detection strategy effectively improves the accuracy of automated disease detection methods when applied to strawberry plants. Frontiers Media S.A. 2021-01-11 /pmc/articles/PMC7874225/ /pubmed/33584739 http://dx.doi.org/10.3389/fpls.2020.559172 Text en Copyright © 2021 Kim, Han, Park and Lee. http://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
Kim, Byoungjun
Han, You-Kyoung
Park, Jong-Han
Lee, Joonwhoan
Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network
title Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network
title_full Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network
title_fullStr Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network
title_full_unstemmed Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network
title_short Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network
title_sort improved vision-based detection of strawberry diseases using a deep neural network
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7874225/
https://www.ncbi.nlm.nih.gov/pubmed/33584739
http://dx.doi.org/10.3389/fpls.2020.559172
work_keys_str_mv AT kimbyoungjun improvedvisionbaseddetectionofstrawberrydiseasesusingadeepneuralnetwork
AT hanyoukyoung improvedvisionbaseddetectionofstrawberrydiseasesusingadeepneuralnetwork
AT parkjonghan improvedvisionbaseddetectionofstrawberrydiseasesusingadeepneuralnetwork
AT leejoonwhoan improvedvisionbaseddetectionofstrawberrydiseasesusingadeepneuralnetwork