EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Humans in the loop: Community science and machine learning synergies for overcoming herbarium digitization bottlenecks

Robert Guralnick iD, Raphael LaFrance, Michael Denslow, Samantha Blickhan, Mark Bouslog, Sean Miller, Jenn Yost, Jason Best, Deborah L Paul, Elizabeth Ellwood iD, Edward Gilbert, Julie Allen

Applications in Plant Sciences · 2024-01 · 12 (1)

DOI: 10.1002/aps3.11560 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applications in Plant Sciences, online erschienen am 03.01.2024. Verfasst von Robert Guralnick und 11 weiteren Autor:innen. Beteiligte Einrichtung: Florida Museum of Natural History University of Florida Gainesville Florida USA. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Premise Among the slowest steps in the digitization of natural history collections is converting imaged labels into digital text. We present here a working solution to overcome this long‐recognized efficiency bottleneck that leverages synergies between community science efforts and machine learning approaches.

Methods

We present two new semi‐automated services. The first detects and classifies typewritten, handwritten, or mixed labels from herbarium sheets. The second uses a workflow tuned for specimen labels to label text using optical character recognition (OCR). The label finder and classifier was built via humans‐in‐the‐loop processes that utilize the community science Notes from Nature platform to develop training and validation data sets to feed into a machine learning pipeline.

Results

Our results showcase a >93% success rate for finding and classifying main labels. The OCR pipeline optimizes pre‐processing, multiple OCR engines, and post‐processing steps, including an alignment approach borrowed from molecular systematics. This pipeline yields >4‐fold reductions in errors compared to off‐the‐shelf open‐source solutions. The OCR workflow also allows human validation using a custom Notes from Nature tool.

Discussion

Our work showcases a usable set of tools for herbarium digitization including a custom‐built web application that is freely accessible. Further work to better integrate these services into existing toolkits can support broad community use.

Schlagwörter

Stichwörter der Autor:innen

Notes from NatureOCRcitizen sciencedigitizationhumans in the loopmachine learningnatural history collectionsobject classificationobject detection

Autor:innen und Institutionen

  • Florida Museum of Natural History University of Florida Gainesville Florida USA.
  • The Adler Planetarium Chicago Illinois USA.
  • California Polytechnic State University San Luis Obispo California USA.
  • Botanical Research Institute of Texas and Fort Worth Botanic Garden Fort Worth Texas USA.
  • Prairie Research Institute University of Illinois Urbana-Champaign Champaign Illinois USA.
  • Arizona State University Tempe Arizona USA.

ORCID-Profile: Robert Guralnick, Elizabeth Ellwood

Zitieren

APA

Guralnick, R., LaFrance, R., Denslow, M., Blickhan, S., Bouslog, M., Miller, S., Yost, J., Best, J., Paul, D. L., Ellwood, E., Gilbert, E., & Allen, J. (2024). Humans in the loop: Community science and machine learning synergies for overcoming herbarium digitization bottlenecks. Applications in Plant Sciences, 12(1). https://doi.org/10.1002/aps3.11560

Vancouver

Guralnick R, LaFrance R, Denslow M, Blickhan S, Bouslog M, Miller S, et al. Humans in the loop: Community science and machine learning synergies for overcoming herbarium digitization bottlenecks. Applications in Plant Sciences. 2024;12(1). doi:10.1002/aps3.11560

BibTeX
@article{Guralnick2024,
  author = {Guralnick, Robert and LaFrance, Raphael and Denslow, Michael and Blickhan, Samantha and Bouslog, Mark and Miller, Sean and Yost, Jenn and Best, Jason and Paul, Deborah L and Ellwood, Elizabeth and Gilbert, Edward and Allen, Julie},
  title = {Humans in the loop: Community science and machine learning synergies for overcoming herbarium digitization bottlenecks},
  journal = {Applications in Plant Sciences},
  year = {2024},
  volume = {12},
  number = {1},
  doi = {10.1002/aps3.11560}
}
Kostenlos starten →