EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using pose estimation to identify regions and points on natural history specimens

Yichen He iD, Christopher R Cooney, Steve Maddock iD, Gavin H Thomas iD

PLOS Computational Biology · 2023

DOI: 10.1371/journal.pcbi.1010933 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2023. Verfasst von Yichen He und 3 weiteren Autor:innen. Beteiligte Einrichtung: Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield; Alfred Denny Building, University of Sheffield, Sheffield, United K…. Hauptthemen laut MEDLINE: Birds, Snails, Classification. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Leverhulme Trust, Natural Environment Research Council, European Research Council grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A key challenge in mobilising growing numbers of digitised biological specimens for scientific research is finding high-throughput methods to extract phenotypic measurements on these datasets. In this paper, we test a pose estimation approach based on Deep Learning capable of accurately placing point labels to identify key locations on specimen images. We then apply the approach to two distinct challenges that each requires identification of key features in a 2D image: (i) identifying body region-specific plumage colouration on avian specimens and (ii) measuring morphometric shape variation in Littorina snail shells. For the avian dataset, 95% of images are correctly labelled and colour measurements derived from these predicted points are highly correlated with human-based measurements. For the Littorina dataset, more than 95% of landmarks were accurately placed relative to expert-labelled landmarks and predicted landmarks reliably captured shape variation between two distinct shell ecotypes (‘crab’ vs ‘wave’). Overall, our study shows that pose estimation based on Deep Learning can generate high-quality and high-throughput point-based measurements for digitised image-based biodiversity datasets and could mark a step change in the mobilisation of such data. We also provide general guidelines for using pose estimation methods on large-scale biological datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BirdsSnailsClassificationAnimals

Autor:innen und Institutionen

  • Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield; Alfred Denny Building, University of Sheffield, Sheffield, United Kingdom.
  • Department of Computer Science, University of Sheffield; Regent Court, University of Sheffield, Sheffield, United Kingdom.
  • Bird Group, Department of Life Sciences, The Natural History Museum at Tring; Tring, United Kingdom.

ORCID-Profile: Yichen He, Steve Maddock, Gavin H Thomas

Förderung

  • Leverhulme Trust
  • Natural Environment Research Council
  • European Research Council grant
  • Royal Society

Zitieren

APA

He, Y., Cooney, C. R., Maddock, S., & Thomas, G. H. (2023). Using pose estimation to identify regions and points on natural history specimens. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1010933

Vancouver

He Y, Cooney CR, Maddock S, Thomas GH. Using pose estimation to identify regions and points on natural history specimens. PLOS Computational Biology. 2023. doi:10.1371/journal.pcbi.1010933

BibTeX
@article{He2023,
  author = {He, Yichen and Cooney, Christopher R and Maddock, Steve and Thomas, Gavin H},
  title = {Using pose estimation to identify regions and points on natural history specimens},
  journal = {PLOS Computational Biology},
  year = {2023},
  doi = {10.1371/journal.pcbi.1010933}
}
Kostenlos starten →