EUVIMEDOpdag EUVIMED
Open access · CC BY-NC 4.0

From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2

William N Weaver iD, Stephen A Smith iD

Applications in Plant Sciences · 2023-09 · 11 (5)

DOI: 10.1002/aps3.11548 ↗

At a glance

Journal article in Applications in Plant Sciences, published online on 2023-10-16. Written by William N Weaver and 1 co-authors. Institution: Department of Ecology and Evolutionary Biology University of Michigan 1105 N. University Ave. Ann Arbor 48109 Michigan USA. Cited 50 times so far (Crossref); 59 references. The full text is freely available (open access, CC BY-NC 4.0).

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Premise Quantitative plant traits play a crucial role in biological research. However, traditional methods for measuring plant morphology are time consuming and have limited scalability. We present LeafMachine2, a suite of modular machine learning and computer vision tools that can automatically extract a base set of leaf traits from digital plant data sets.

Methods

LeafMachine2 was trained on 494,766 manually prepared annotations from 5648 herbarium images obtained from 288 institutions and representing 2663 species; it employs a set of plant component detection and segmentation algorithms to isolate individual leaves, petioles, fruits, flowers, wood samples, buds, and roots. Our landmarking network automatically identifies and measures nine pseudo‐landmarks that occur on most broadleaf taxa. Text labels and barcodes are automatically identified by an archival component detector and are prepared for optical character recognition methods or natural language processing algorithms.

Results

LeafMachine2 can extract trait data from at least 245 angiosperm families and calculate pixel‐to‐metric conversion factors for 26 commonly used ruler types.

Discussion

LeafMachine2 is a highly efficient tool for generating large quantities of plant trait data, even from occluded or overlapping leaves, field images, and non‐archival data sets. Our project, along with similar initiatives, has made significant progress in removing the bottleneck in plant trait data acquisition from herbarium specimens and shifted the focus toward the crucial task of data revision and quality control.

Subjects

Author keywords

digital extended specimendigital specimen voucherherbariummachine learningmorphometricsneural networksphenologytraits

Authors and institutions

  • Department of Ecology and Evolutionary Biology University of Michigan 1105 N. University Ave. Ann Arbor 48109 Michigan USA.

ORCID profiles: William N Weaver, Stephen A Smith

Cite

APA

Weaver, W. N., & Smith, S. A. (2023). From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2. Applications in Plant Sciences, 11(5). https://doi.org/10.1002/aps3.11548

Vancouver

Weaver WN, Smith SA. From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2. Applications in Plant Sciences. 2023;11(5). doi:10.1002/aps3.11548

BibTeX
@article{Weaver2023,
  author = {Weaver, William N and Smith, Stephen A},
  title = {From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2},
  journal = {Applications in Plant Sciences},
  year = {2023},
  volume = {11},
  number = {5},
  doi = {10.1002/aps3.11548}
}
Start for free →