Issue Information
Applications in Plant Sciences · 2026-09 · 14 (5)
DOI: 10.1002/aps3.70087 ↗At a glance
Journal article in Applications in Plant Sciences, published online on 2026-10-29.
Abstract (original language)
Cover illustration: Composite of nine single-species wildflower seed scans generated using a domestic flatbed scanner and processed with a custom segmentation pipeline adapted from the open-source Cellpose library, originally developed for cellular imaging. The pipeline identified seed contours more accurately than conventional ImageJ-based image analysis, albeit at greater computational cost. Seeds from each species were scanned separately, and the red contours show the boundaries the segmentation model identified around individual seeds, which were then used either directly as image inputs or to derive numerical trait values. Accurate segmentation allowed individual seeds to be isolated from the original scans and provided the data used in subsequent species-classification analyses, which showed that no single model was universally optimal, with performance depending on trade-offs among accuracy, computational cost, and whether classification involved only known species or also unseen taxa. In “Integrating machine learning, deep learning, and image analysis for seed species classification,” Ashworth et al. compare alternative image-segmentation and classification approaches for developing an accessible workflow for wildflower seed identification. Clockwise from top left: Daucus carota, Centaurea nigra, Prunella vulgaris, Achillea millefolium, Galium verum, Rumex acetosa, Leucanthemum vulgare, Malva moschata, and Knautia arvensis. (Image credit: Jonathan Ashworth and Jose J. De Vega)
Cite
APA
(2026). Issue Information. Applications in Plant Sciences, 14(5). https://doi.org/10.1002/aps3.70087
Vancouver
Issue Information. Applications in Plant Sciences. 2026;14(5). doi:10.1002/aps3.70087
BibTeX
@article{euvimed2026,
title = {Issue Information},
journal = {Applications in Plant Sciences},
year = {2026},
volume = {14},
number = {5},
doi = {10.1002/aps3.70087}
}
EUVIMED