Cargando…

Inside out: transforming images of lab-grown plants for machine learning applications in agriculture

INTRODUCTION: Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences between two plants of the same genotype, often as a...

Descripción completa

Detalles Bibliográficos
Autores principales: Krosney, Alexander E., Sotoodeh, Parsa, Henry, Christopher J., Beck, Michael A., Bidinosti, Christopher P.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10358354/
https://www.ncbi.nlm.nih.gov/pubmed/37483870
http://dx.doi.org/10.3389/frai.2023.1200977
_version_ 1785075643758673920
author Krosney, Alexander E.
Sotoodeh, Parsa
Henry, Christopher J.
Beck, Michael A.
Bidinosti, Christopher P.
author_facet Krosney, Alexander E.
Sotoodeh, Parsa
Henry, Christopher J.
Beck, Michael A.
Bidinosti, Christopher P.
author_sort Krosney, Alexander E.
collection PubMed
description INTRODUCTION: Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences between two plants of the same genotype, often as a result of different growing conditions. Synthetically-augmented datasets have shown promise in improving existing models when real data is not available. METHODS: In this paper, we employ a contrastive unpaired translation (CUT) generative adversarial network (GAN) and simple image processing techniques to translate indoor plant images to appear as field images. While we train our network to translate an image containing only a single plant, we show that our method is easily extendable to produce multiple-plant field images. RESULTS: Furthermore, we use our synthetic multi-plant images to train several YoloV5 nano object detection models to perform the task of plant detection and measure the accuracy of the model on real field data images. DISCUSSION: The inclusion of training data generated by the CUT-GAN leads to better plant detection performance compared to a network trained solely on real data.
format Online
Article
Text
id pubmed-10358354
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103583542023-07-21 Inside out: transforming images of lab-grown plants for machine learning applications in agriculture Krosney, Alexander E. Sotoodeh, Parsa Henry, Christopher J. Beck, Michael A. Bidinosti, Christopher P. Front Artif Intell Artificial Intelligence INTRODUCTION: Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences between two plants of the same genotype, often as a result of different growing conditions. Synthetically-augmented datasets have shown promise in improving existing models when real data is not available. METHODS: In this paper, we employ a contrastive unpaired translation (CUT) generative adversarial network (GAN) and simple image processing techniques to translate indoor plant images to appear as field images. While we train our network to translate an image containing only a single plant, we show that our method is easily extendable to produce multiple-plant field images. RESULTS: Furthermore, we use our synthetic multi-plant images to train several YoloV5 nano object detection models to perform the task of plant detection and measure the accuracy of the model on real field data images. DISCUSSION: The inclusion of training data generated by the CUT-GAN leads to better plant detection performance compared to a network trained solely on real data. Frontiers Media S.A. 2023-07-06 /pmc/articles/PMC10358354/ /pubmed/37483870 http://dx.doi.org/10.3389/frai.2023.1200977 Text en Copyright © 2023 Krosney, Sotoodeh, Henry, Beck and Bidinosti. 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 Artificial Intelligence
Krosney, Alexander E.
Sotoodeh, Parsa
Henry, Christopher J.
Beck, Michael A.
Bidinosti, Christopher P.
Inside out: transforming images of lab-grown plants for machine learning applications in agriculture
title Inside out: transforming images of lab-grown plants for machine learning applications in agriculture
title_full Inside out: transforming images of lab-grown plants for machine learning applications in agriculture
title_fullStr Inside out: transforming images of lab-grown plants for machine learning applications in agriculture
title_full_unstemmed Inside out: transforming images of lab-grown plants for machine learning applications in agriculture
title_short Inside out: transforming images of lab-grown plants for machine learning applications in agriculture
title_sort inside out: transforming images of lab-grown plants for machine learning applications in agriculture
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10358354/
https://www.ncbi.nlm.nih.gov/pubmed/37483870
http://dx.doi.org/10.3389/frai.2023.1200977
work_keys_str_mv AT krosneyalexandere insideouttransformingimagesoflabgrownplantsformachinelearningapplicationsinagriculture
AT sotoodehparsa insideouttransformingimagesoflabgrownplantsformachinelearningapplicationsinagriculture
AT henrychristopherj insideouttransformingimagesoflabgrownplantsformachinelearningapplicationsinagriculture
AT beckmichaela insideouttransformingimagesoflabgrownplantsformachinelearningapplicationsinagriculture
AT bidinostichristopherp insideouttransformingimagesoflabgrownplantsformachinelearningapplicationsinagriculture