Cargando…

Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+

The plant leaf veins coupling feature representation and measurement method based on DeepLabV3+ is proposed to solve problems of slow segmentation, partial occlusion of leaf veins, and low measurement accuracy of leaf veins parameters. Firstly, to solve the problem of slow segmentation, the lightwei...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Xiaobao, Xu, Biao, Gu, Wenjuan, Yin, Yanchao, Wang, Hongcheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9730334/
https://www.ncbi.nlm.nih.gov/pubmed/36507417
http://dx.doi.org/10.3389/fpls.2022.1043884
_version_ 1784845645283065856
author Liu, Xiaobao
Xu, Biao
Gu, Wenjuan
Yin, Yanchao
Wang, Hongcheng
author_facet Liu, Xiaobao
Xu, Biao
Gu, Wenjuan
Yin, Yanchao
Wang, Hongcheng
author_sort Liu, Xiaobao
collection PubMed
description The plant leaf veins coupling feature representation and measurement method based on DeepLabV3+ is proposed to solve problems of slow segmentation, partial occlusion of leaf veins, and low measurement accuracy of leaf veins parameters. Firstly, to solve the problem of slow segmentation, the lightweight MobileNetV2 is selected as the extraction network for DeepLabV3+. On this basis, the Convex Hull-Scan method is applied to repair leaf veins. Subsequently, a refinement algorithm, Floodfill MorphologyEx Medianblur Morphological Skeleton (F-3MS), is proposed, reducing the burr phenomenon of leaf veins’ skeleton lines. Finally, leaf veins’ related parameters are measured. In this study, mean intersection over union (MIoU) and mean pixel accuracy (mPA) reach 81.50% and 92.89%, respectively, and the average segmentation speed reaches 9.81 frames per second. Furthermore, the network model parameters are compressed by 89.375%, down to 5.813M. Meanwhile, leaf veins’ length and width are measured, yielding an accuracy of 96.3642% and 96.1358%, respectively.
format Online
Article
Text
id pubmed-9730334
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-97303342022-12-09 Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+ Liu, Xiaobao Xu, Biao Gu, Wenjuan Yin, Yanchao Wang, Hongcheng Front Plant Sci Plant Science The plant leaf veins coupling feature representation and measurement method based on DeepLabV3+ is proposed to solve problems of slow segmentation, partial occlusion of leaf veins, and low measurement accuracy of leaf veins parameters. Firstly, to solve the problem of slow segmentation, the lightweight MobileNetV2 is selected as the extraction network for DeepLabV3+. On this basis, the Convex Hull-Scan method is applied to repair leaf veins. Subsequently, a refinement algorithm, Floodfill MorphologyEx Medianblur Morphological Skeleton (F-3MS), is proposed, reducing the burr phenomenon of leaf veins’ skeleton lines. Finally, leaf veins’ related parameters are measured. In this study, mean intersection over union (MIoU) and mean pixel accuracy (mPA) reach 81.50% and 92.89%, respectively, and the average segmentation speed reaches 9.81 frames per second. Furthermore, the network model parameters are compressed by 89.375%, down to 5.813M. Meanwhile, leaf veins’ length and width are measured, yielding an accuracy of 96.3642% and 96.1358%, respectively. Frontiers Media S.A. 2022-11-24 /pmc/articles/PMC9730334/ /pubmed/36507417 http://dx.doi.org/10.3389/fpls.2022.1043884 Text en Copyright © 2022 Liu, Xu, Gu, Yin and Wang 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
Liu, Xiaobao
Xu, Biao
Gu, Wenjuan
Yin, Yanchao
Wang, Hongcheng
Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+
title Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+
title_full Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+
title_fullStr Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+
title_full_unstemmed Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+
title_short Plant leaf veins coupling feature representation and measurement method based on DeepLabV3+
title_sort plant leaf veins coupling feature representation and measurement method based on deeplabv3+
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9730334/
https://www.ncbi.nlm.nih.gov/pubmed/36507417
http://dx.doi.org/10.3389/fpls.2022.1043884
work_keys_str_mv AT liuxiaobao plantleafveinscouplingfeaturerepresentationandmeasurementmethodbasedondeeplabv3
AT xubiao plantleafveinscouplingfeaturerepresentationandmeasurementmethodbasedondeeplabv3
AT guwenjuan plantleafveinscouplingfeaturerepresentationandmeasurementmethodbasedondeeplabv3
AT yinyanchao plantleafveinscouplingfeaturerepresentationandmeasurementmethodbasedondeeplabv3
AT wanghongcheng plantleafveinscouplingfeaturerepresentationandmeasurementmethodbasedondeeplabv3