Cargando…
Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set
Traditionally, plant disease recognition has mainly been done visually by human. It is often biased, time-consuming, and laborious. Machine learning methods based on plant leave images have been proposed to improve the disease recognition process. Convolutional neural networks (CNNs) have been adopt...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7746658/ https://www.ncbi.nlm.nih.gov/pubmed/33343595 http://dx.doi.org/10.3389/fpls.2020.583438 |
_version_ | 1783624835808624640 |
---|---|
author | Bi, Luning Hu, Guiping |
author_facet | Bi, Luning Hu, Guiping |
author_sort | Bi, Luning |
collection | PubMed |
description | Traditionally, plant disease recognition has mainly been done visually by human. It is often biased, time-consuming, and laborious. Machine learning methods based on plant leave images have been proposed to improve the disease recognition process. Convolutional neural networks (CNNs) have been adopted and proven to be very effective. Despite the good classification accuracy achieved by CNNs, the issue of limited training data remains. In most cases, the training dataset is often small due to significant effort in data collection and annotation. In this case, CNN methods tend to have the overfitting problem. In this paper, Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is combined with label smoothing regularization (LSR) to improve the prediction accuracy and address the overfitting problem under limited training data. Experiments show that the proposed WGAN-GP enhanced classification method can improve the overall classification accuracy of plant diseases by 24.4% as compared to 20.2% using classic data augmentation and 22% using synthetic samples without LSR. |
format | Online Article Text |
id | pubmed-7746658 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-77466582020-12-19 Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set Bi, Luning Hu, Guiping Front Plant Sci Plant Science Traditionally, plant disease recognition has mainly been done visually by human. It is often biased, time-consuming, and laborious. Machine learning methods based on plant leave images have been proposed to improve the disease recognition process. Convolutional neural networks (CNNs) have been adopted and proven to be very effective. Despite the good classification accuracy achieved by CNNs, the issue of limited training data remains. In most cases, the training dataset is often small due to significant effort in data collection and annotation. In this case, CNN methods tend to have the overfitting problem. In this paper, Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is combined with label smoothing regularization (LSR) to improve the prediction accuracy and address the overfitting problem under limited training data. Experiments show that the proposed WGAN-GP enhanced classification method can improve the overall classification accuracy of plant diseases by 24.4% as compared to 20.2% using classic data augmentation and 22% using synthetic samples without LSR. Frontiers Media S.A. 2020-12-04 /pmc/articles/PMC7746658/ /pubmed/33343595 http://dx.doi.org/10.3389/fpls.2020.583438 Text en Copyright © 2020 Bi and Hu. 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 Bi, Luning Hu, Guiping Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set |
title | Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set |
title_full | Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set |
title_fullStr | Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set |
title_full_unstemmed | Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set |
title_short | Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set |
title_sort | improving image-based plant disease classification with generative adversarial network under limited training set |
topic | Plant Science |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7746658/ https://www.ncbi.nlm.nih.gov/pubmed/33343595 http://dx.doi.org/10.3389/fpls.2020.583438 |
work_keys_str_mv | AT biluning improvingimagebasedplantdiseaseclassificationwithgenerativeadversarialnetworkunderlimitedtrainingset AT huguiping improvingimagebasedplantdiseaseclassificationwithgenerativeadversarialnetworkunderlimitedtrainingset |