Cargando…

Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum)

PREMISE: Equisetum is a distinctive vascular plant genus with 15 extant species worldwide. Species identification is complicated by morphological plasticity and frequent hybridization events, leading to a disproportionately high number of misidentified specimens. These may be correctly identified by...

Descripción completa

Detalles Bibliográficos
Autores principales: Pryer, Kathleen M., Tomasi, Carlo, Wang, Xiaohan, Meineke, Emily K., Windham, Michael D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7328651/
https://www.ncbi.nlm.nih.gov/pubmed/32626613
http://dx.doi.org/10.1002/aps3.11372
_version_ 1783552769183973376
author Pryer, Kathleen M.
Tomasi, Carlo
Wang, Xiaohan
Meineke, Emily K.
Windham, Michael D.
author_facet Pryer, Kathleen M.
Tomasi, Carlo
Wang, Xiaohan
Meineke, Emily K.
Windham, Michael D.
author_sort Pryer, Kathleen M.
collection PubMed
description PREMISE: Equisetum is a distinctive vascular plant genus with 15 extant species worldwide. Species identification is complicated by morphological plasticity and frequent hybridization events, leading to a disproportionately high number of misidentified specimens. These may be correctly identified by applying appropriate computer vision tools. METHODS: We hypothesize that aerial stem nodes can provide enough information to distinguish among Equisetum hyemale, E. laevigatum, and E . ×ferrissii, the latter being a hybrid between the other two. An object detector was trained to find nodes on a given image and to distinguish E. hyemale nodes from those of E. laevigatum. A classifier then took statistics from the detection results and classified the given image into one of the three taxa. Both detector and classifier were trained and tested on expert manually annotated images. RESULTS: In our exploratory test set of 30 images, our detector/classifier combination identified all 10 E. laevigatum images correctly, as well as nine out of 10 E. hyemale images, and eight out of 10 E. ×ferrissii images, for a 90% classification accuracy. DISCUSSION: Our results support the notion that computer vision may help with the identification of herbarium specimens once enough manual annotations become available.
format Online
Article
Text
id pubmed-7328651
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-73286512020-07-02 Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum) Pryer, Kathleen M. Tomasi, Carlo Wang, Xiaohan Meineke, Emily K. Windham, Michael D. Appl Plant Sci Application Articles PREMISE: Equisetum is a distinctive vascular plant genus with 15 extant species worldwide. Species identification is complicated by morphological plasticity and frequent hybridization events, leading to a disproportionately high number of misidentified specimens. These may be correctly identified by applying appropriate computer vision tools. METHODS: We hypothesize that aerial stem nodes can provide enough information to distinguish among Equisetum hyemale, E. laevigatum, and E . ×ferrissii, the latter being a hybrid between the other two. An object detector was trained to find nodes on a given image and to distinguish E. hyemale nodes from those of E. laevigatum. A classifier then took statistics from the detection results and classified the given image into one of the three taxa. Both detector and classifier were trained and tested on expert manually annotated images. RESULTS: In our exploratory test set of 30 images, our detector/classifier combination identified all 10 E. laevigatum images correctly, as well as nine out of 10 E. hyemale images, and eight out of 10 E. ×ferrissii images, for a 90% classification accuracy. DISCUSSION: Our results support the notion that computer vision may help with the identification of herbarium specimens once enough manual annotations become available. John Wiley and Sons Inc. 2020-07-01 /pmc/articles/PMC7328651/ /pubmed/32626613 http://dx.doi.org/10.1002/aps3.11372 Text en © 2020 Pryer et al. Applications in Plant Sciences is published by Wiley Periodicals LLC on behalf of the Botanical Society of America This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Application Articles
Pryer, Kathleen M.
Tomasi, Carlo
Wang, Xiaohan
Meineke, Emily K.
Windham, Michael D.
Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum)
title Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum)
title_full Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum)
title_fullStr Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum)
title_full_unstemmed Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum)
title_short Using computer vision on herbarium specimen images to discriminate among closely related horsetails (Equisetum)
title_sort using computer vision on herbarium specimen images to discriminate among closely related horsetails (equisetum)
topic Application Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7328651/
https://www.ncbi.nlm.nih.gov/pubmed/32626613
http://dx.doi.org/10.1002/aps3.11372
work_keys_str_mv AT pryerkathleenm usingcomputervisiononherbariumspecimenimagestodiscriminateamongcloselyrelatedhorsetailsequisetum
AT tomasicarlo usingcomputervisiononherbariumspecimenimagestodiscriminateamongcloselyrelatedhorsetailsequisetum
AT wangxiaohan usingcomputervisiononherbariumspecimenimagestodiscriminateamongcloselyrelatedhorsetailsequisetum
AT meinekeemilyk usingcomputervisiononherbariumspecimenimagestodiscriminateamongcloselyrelatedhorsetailsequisetum
AT windhammichaeld usingcomputervisiononherbariumspecimenimagestodiscriminateamongcloselyrelatedhorsetailsequisetum