EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From pixels to data: automated reconstruction of taxonomic series from whole-drawer images in historical insect collections

Sneha Bhansali, Nikolai Ignatev, Marianna Simões

Natural History Collections and Museomics · 22.07.2026 · 3

DOI: 10.3897/nhcm.3.196081 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Natural History Collections and Museomics, online erschienen am 22.07.2026. Verfasst von Sneha Bhansali und 2 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Natural history collections are structured knowledge systems in which taxonomic and historical information is embedded within specimens, labels and their physical arrangement. However, in large entomological collections, much of this information remains inaccessible because it is not captured in standardised digital formats. Whole-drawer imaging offers a scalable approach to digitisation, but existing workflows primarily focus on specimen-level extraction and often neglect the curatorial structure encoded in drawer organisation. Here, we present an open-source workflow that transforms whole-drawer images into structured, machine-readable inventory data, while preserving their spatial arrangement and taxonomic context. The pipeline integrates low-cost imaging, barcode linkage, deep learning-based object detection (YOLOv.11) and optical character recognition (OCR) to reconstruct taxonomic series and estimate specimen counts per taxon from drawer images. The approach was developed for the Coleoptera collection of the Senckenberg Research Institute Frankfurt, encompassing approximately 1.9 million specimens which are stored in more than 5,000 drawers. Model training on Carabidae collection drawers overall achieved high performance (precision 99.2%, recall 97.9%, mAP0.5 98.5%), with reasonable transferability to other beetle families and Hymenoptera drawers tested. By treating the drawer as the primary unit of digitisation, this workflow provides a scalable intermediate layer between physical collections and specimen-level databases. It enables rapid assessment of taxonomic composition, supports collection management and digitisation planning and contributes to the mobilisation of biodiversity data from large historical collections.

Zitieren

APA

Bhansali, S., Ignatev, N., & Simões, M. (2026). From pixels to data: automated reconstruction of taxonomic series from whole-drawer images in historical insect collections. Natural History Collections and Museomics, 3. https://doi.org/10.3897/nhcm.3.196081

Vancouver

Bhansali S, Ignatev N, Simões M. From pixels to data: automated reconstruction of taxonomic series from whole-drawer images in historical insect collections. Natural History Collections and Museomics. 2026;3. doi:10.3897/nhcm.3.196081

BibTeX
@article{Bhansali2026,
  author = {Bhansali, Sneha and Ignatev, Nikolai and Simões, Marianna},
  title = {From pixels to data: automated reconstruction of taxonomic series from whole-drawer images in historical insect collections},
  journal = {Natural History Collections and Museomics},
  year = {2026},
  volume = {3},
  doi = {10.3897/nhcm.3.196081}
}
Kostenlos starten →