Cargando…

A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants

The ubiquity of Smartphone applications that aim to identify organisms, including plants, make them potentially useful for increasing people’s engagement with the natural world. However, how well such applications actually identify plants has not been compressively investigated nor has an easily rep...

Descripción completa

Detalles Bibliográficos
Autores principales: Campbell, Neil, Peacock, Julie, Bacon, Karen L.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10075466/
https://www.ncbi.nlm.nih.gov/pubmed/37018219
http://dx.doi.org/10.1371/journal.pone.0283386
_version_ 1785019934402674688
author Campbell, Neil
Peacock, Julie
Bacon, Karen L.
author_facet Campbell, Neil
Peacock, Julie
Bacon, Karen L.
author_sort Campbell, Neil
collection PubMed
description The ubiquity of Smartphone applications that aim to identify organisms, including plants, make them potentially useful for increasing people’s engagement with the natural world. However, how well such applications actually identify plants has not been compressively investigated nor has an easily repeatable scoring system to compare across plant groups been developed. This study investigated the ability of six common Smartphone applications (Google Lens, iNaturalist, Leaf Snap, Plant Net, Plant Snap, Seek) to identify herbaceous plants and developed a repeatable scoring system to assess their success. Thirty-eight species of plant were photographed in their natural habitats using a standard Smartphone (Samsung Galaxy A50) and assessed in each app without image enhancement. All apps showed considerable variation across plant species and were better able to identify flowers than leaves. Plant Net and Leaf Snap outperformed the other apps. Even the higher preforming apps did not have an accuracy above ~88% and lower scoring apps were considerably below this. Smartphone apps present a clear opportunity to encourage people to engage more with plants. Their accuracy can be good, but should not be considered excellent or assumed to be correct, particularly if the species in question may be toxic or otherwise problematic.
format Online
Article
Text
id pubmed-10075466
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-100754662023-04-06 A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants Campbell, Neil Peacock, Julie Bacon, Karen L. PLoS One Research Article The ubiquity of Smartphone applications that aim to identify organisms, including plants, make them potentially useful for increasing people’s engagement with the natural world. However, how well such applications actually identify plants has not been compressively investigated nor has an easily repeatable scoring system to compare across plant groups been developed. This study investigated the ability of six common Smartphone applications (Google Lens, iNaturalist, Leaf Snap, Plant Net, Plant Snap, Seek) to identify herbaceous plants and developed a repeatable scoring system to assess their success. Thirty-eight species of plant were photographed in their natural habitats using a standard Smartphone (Samsung Galaxy A50) and assessed in each app without image enhancement. All apps showed considerable variation across plant species and were better able to identify flowers than leaves. Plant Net and Leaf Snap outperformed the other apps. Even the higher preforming apps did not have an accuracy above ~88% and lower scoring apps were considerably below this. Smartphone apps present a clear opportunity to encourage people to engage more with plants. Their accuracy can be good, but should not be considered excellent or assumed to be correct, particularly if the species in question may be toxic or otherwise problematic. Public Library of Science 2023-04-05 /pmc/articles/PMC10075466/ /pubmed/37018219 http://dx.doi.org/10.1371/journal.pone.0283386 Text en © 2023 Campbell et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Campbell, Neil
Peacock, Julie
Bacon, Karen L.
A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants
title A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants
title_full A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants
title_fullStr A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants
title_full_unstemmed A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants
title_short A repeatable scoring system for assessing Smartphone applications ability to identify herbaceous plants
title_sort repeatable scoring system for assessing smartphone applications ability to identify herbaceous plants
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10075466/
https://www.ncbi.nlm.nih.gov/pubmed/37018219
http://dx.doi.org/10.1371/journal.pone.0283386
work_keys_str_mv AT campbellneil arepeatablescoringsystemforassessingsmartphoneapplicationsabilitytoidentifyherbaceousplants
AT peacockjulie arepeatablescoringsystemforassessingsmartphoneapplicationsabilitytoidentifyherbaceousplants
AT baconkarenl arepeatablescoringsystemforassessingsmartphoneapplicationsabilitytoidentifyherbaceousplants
AT campbellneil repeatablescoringsystemforassessingsmartphoneapplicationsabilitytoidentifyherbaceousplants
AT peacockjulie repeatablescoringsystemforassessingsmartphoneapplicationsabilitytoidentifyherbaceousplants
AT baconkarenl repeatablescoringsystemforassessingsmartphoneapplicationsabilitytoidentifyherbaceousplants