EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Image-based recognition of parasitoid wasps using advanced neural networks

Hossein Shirali, Jeremy Hübner, Robin Both, Michael Raupach, Markus Reischl, Stefan Schmidt, Christian Pylatiuk

Invertebrate Systematics · 2024

DOI: 10.1071/is24011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Invertebrate Systematics, 2024. Verfasst von Hossein Shirali und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), D-76149 Karlsruhe, Germany. Hauptthemen laut MEDLINE: Wasps, Neural Networks, Computer. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Museum für Naturkunde Berlin, German Federal Ministry of Education and Research, Natural, Artificial and Cognitive Information Processing (NACIP) program of the Helmholtz Association.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hymenoptera has some of the highest diversity and number of individuals among insects. Many of these species potentially play key roles as food sources, pest controllers and pollinators. However, little is known about the diversity and biology and ~80% of the species have not yet been described. Classical taxonomy based on morphology is a rather slow process but DNA barcoding has already brought considerable progress in identification. Innovative methods such as image-based identification and automation can further speed up the process. We present a proof of concept for image data recognition of a parasitic wasp family, the Diapriidae (Hymenoptera), obtained as part of the GBOL III project. These tiny (1.2–4.5 mm) wasps were photographed and identified using DNA barcoding to provide a solid ground truth for training a neural network. Taxonomic identification was used down to the genus level. Subsequently, three different neural network architectures were trained, evaluated and optimised. As a result, 11 different genera of diaprids and one mixed group of ‘other Hymenoptera’ can be classified with an average accuracy of 96%. Additionally, the sex of the specimen can be classified automatically with an accuracy of >97%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WaspsNeural Networks, ComputerAnimalsDNA Barcoding, TaxonomicImage Processing, Computer-AssistedFemaleClassificationSpecies SpecificityMale

Autor:innen und Institutionen

  • Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), D-76149 Karlsruhe, Germany.
  • Zoologische Staatssammlung München, Münchhausenstraße 21, D-81247 Munich, Germany.
  • Deceased. Formerly at Zoologische Staatssammlung München, Münchhausenstraße 21, D-81247 Munich, Germany.

Förderung

  • Museum für Naturkunde Berlin
  • German Federal Ministry of Education and Research
  • Natural, Artificial and Cognitive Information Processing (NACIP) program of the Helmholtz Association

Zitieren

APA

Shirali, H., Hübner, J., Both, R., Raupach, M., Reischl, M., Schmidt, S., & Pylatiuk, C. (2024). Image-based recognition of parasitoid wasps using advanced neural networks. Invertebrate Systematics. https://doi.org/10.1071/is24011

Vancouver

Shirali H, Hübner J, Both R, Raupach M, Reischl M, Schmidt S, et al. Image-based recognition of parasitoid wasps using advanced neural networks. Invertebrate Systematics. 2024. doi:10.1071/is24011

BibTeX
@article{Shirali2024,
  author = {Shirali, Hossein and Hübner, Jeremy and Both, Robin and Raupach, Michael and Reischl, Markus and Schmidt, Stefan and Pylatiuk, Christian},
  title = {Image-based recognition of parasitoid wasps using advanced neural networks},
  journal = {Invertebrate Systematics},
  year = {2024},
  doi = {10.1071/is24011}
}
Kostenlos starten →