Cargando…

Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning

Past studies of plant disease and pest recognition used classification methods that presented a singular recognition result to the user. Unfortunately, incorrect recognition results may be output, which may lead to further crop damage. To address this issue, there is a need for a system that suggest...

Descripción completa

Detalles Bibliográficos
Autores principales: Gu, Yeong Hyeon, Yin, Helin, Jin, Dong, Park, Jong-Han, Yoo, Seong Joon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8716927/
https://www.ncbi.nlm.nih.gov/pubmed/34975933
http://dx.doi.org/10.3389/fpls.2021.724487
_version_ 1784624424709783552
author Gu, Yeong Hyeon
Yin, Helin
Jin, Dong
Park, Jong-Han
Yoo, Seong Joon
author_facet Gu, Yeong Hyeon
Yin, Helin
Jin, Dong
Park, Jong-Han
Yoo, Seong Joon
author_sort Gu, Yeong Hyeon
collection PubMed
description Past studies of plant disease and pest recognition used classification methods that presented a singular recognition result to the user. Unfortunately, incorrect recognition results may be output, which may lead to further crop damage. To address this issue, there is a need for a system that suggest several candidate results and allow the user to make the final decision. In this study, we propose a method for diagnosing plant diseases and identifying pests using deep features based on transfer learning. To extract deep features, we employ pre-trained VGG and ResNet 50 architectures based on the ImageNet dataset, and output disease and pest images similar to a query image via a k-nearest-neighbor algorithm. In this study, we use a total of 23,868 images of 19 types of hot-pepper diseases and pests, for which, the proposed model achieves accuracies of 96.02 and 99.61%, respectively. We also measure the effects of fine-tuning and distance metrics. The results show that the use of fine-tuning-based deep features increases accuracy by approximately 0.7–7.38%, and the Bray–Curtis distance achieves an accuracy of approximately 0.65–1.51% higher than the Euclidean distance.
format Online
Article
Text
id pubmed-8716927
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-87169272021-12-31 Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning Gu, Yeong Hyeon Yin, Helin Jin, Dong Park, Jong-Han Yoo, Seong Joon Front Plant Sci Plant Science Past studies of plant disease and pest recognition used classification methods that presented a singular recognition result to the user. Unfortunately, incorrect recognition results may be output, which may lead to further crop damage. To address this issue, there is a need for a system that suggest several candidate results and allow the user to make the final decision. In this study, we propose a method for diagnosing plant diseases and identifying pests using deep features based on transfer learning. To extract deep features, we employ pre-trained VGG and ResNet 50 architectures based on the ImageNet dataset, and output disease and pest images similar to a query image via a k-nearest-neighbor algorithm. In this study, we use a total of 23,868 images of 19 types of hot-pepper diseases and pests, for which, the proposed model achieves accuracies of 96.02 and 99.61%, respectively. We also measure the effects of fine-tuning and distance metrics. The results show that the use of fine-tuning-based deep features increases accuracy by approximately 0.7–7.38%, and the Bray–Curtis distance achieves an accuracy of approximately 0.65–1.51% higher than the Euclidean distance. Frontiers Media S.A. 2021-12-16 /pmc/articles/PMC8716927/ /pubmed/34975933 http://dx.doi.org/10.3389/fpls.2021.724487 Text en Copyright © 2021 Gu, Yin, Jin, Park and Yoo. 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
Gu, Yeong Hyeon
Yin, Helin
Jin, Dong
Park, Jong-Han
Yoo, Seong Joon
Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning
title Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning
title_full Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning
title_fullStr Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning
title_full_unstemmed Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning
title_short Image-Based Hot Pepper Disease and Pest Diagnosis Using Transfer Learning and Fine-Tuning
title_sort image-based hot pepper disease and pest diagnosis using transfer learning and fine-tuning
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8716927/
https://www.ncbi.nlm.nih.gov/pubmed/34975933
http://dx.doi.org/10.3389/fpls.2021.724487
work_keys_str_mv AT guyeonghyeon imagebasedhotpepperdiseaseandpestdiagnosisusingtransferlearningandfinetuning
AT yinhelin imagebasedhotpepperdiseaseandpestdiagnosisusingtransferlearningandfinetuning
AT jindong imagebasedhotpepperdiseaseandpestdiagnosisusingtransferlearningandfinetuning
AT parkjonghan imagebasedhotpepperdiseaseandpestdiagnosisusingtransferlearningandfinetuning
AT yooseongjoon imagebasedhotpepperdiseaseandpestdiagnosisusingtransferlearningandfinetuning