EUVIMEDEUVIMED entdecken
KommentarOpen Access · CC BY-NC 4.0

PlantSAM: An object detection‐driven segmentation pipeline for herbarium specimens

Youcef Sklab iD, Florian Castanet, Hanane Ariouat, Souhila Arib, Jean-Daniel Zucker, Eric Chenin, Edi Prifti

Applications in Plant Sciences · 2025-11 · 13 (6)

DOI: 10.1002/aps3.70034 ↗

Kurz gefasst

Kommentar in der Zeitschrift Applications in Plant Sciences, online erschienen am 12.12.2025. Verfasst von Youcef Sklab und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institut de Recherche pour le Développement (IRD) Sorbonne Université, UMMISCO Paris France. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Premise Deep learning–based classification of herbarium images is hampered by background heterogeneity, which introduces noise and artifacts that can potentially mislead models and degrade their accuracy. Addressing these effects is essential to enhance overall performance.

Methods

We introduce PlantSAM, an automated segmentation pipeline that integrates YOLOv10 for plant region detection and the Segment Anything Model (SAM2) for segmentation. YOLOv10 generates bounding box prompts to guide SAM2, enhancing segmentation accuracy. Both models were fine‐tuned on herbarium images and evaluated using intersection over union (IoU) and Sørensen–Dice coefficient metrics.

Results

PlantSAM achieved state‐of‐the‐art segmentation performance, with an IoU of 0.94 and a Sørensen–Dice coefficient of 0.97. Incorporating segmented images into classification models led to consistent performance improvements across five tested botanical traits, with accuracy gains of up to 4.36% and F1 score improvements of 4.15%.

Conclusions

Our findings highlight the importance of background removal in herbarium image analysis, as it significantly enhances classification performance by enabling models to focus more effectively on the foreground plant structures.

Schlagwörter

Stichwörter der Autor:innen

Segment Anything Model (SAM)YOLOv10botanical analysisherbarium specimenssemantic segmentation

Autor:innen und Institutionen

  • Institut de Recherche pour le Développement (IRD) Sorbonne Université, UMMISCO Paris France.
  • Laboratoire Etis, UMR 8051 CNRS CY Cergy Paris Université Cergy-Pontoise France.
  • Sorbonne Université, INSERM, Nutrition et Obesities; systemic approaches, NutriOmique, AP-HP Hôpital Pitié-Salpêtrière Paris France.

ORCID-Profile: Youcef Sklab

Zitieren

APA

Sklab, Y., Castanet, F., Ariouat, H., Arib, S., Zucker, J. D., Chenin, E., & Prifti, E. (2025). PlantSAM: An object detection‐driven segmentation pipeline for herbarium specimens. Applications in Plant Sciences, 13(6). https://doi.org/10.1002/aps3.70034

Vancouver

Sklab Y, Castanet F, Ariouat H, Arib S, Zucker JD, Chenin E, et al. PlantSAM: An object detection‐driven segmentation pipeline for herbarium specimens. Applications in Plant Sciences. 2025;13(6). doi:10.1002/aps3.70034

BibTeX
@article{Sklab2025,
  author = {Sklab, Youcef and Castanet, Florian and Ariouat, Hanane and Arib, Souhila and Zucker, Jean-Daniel and Chenin, Eric and Prifti, Edi},
  title = {PlantSAM: An object detection‐driven segmentation pipeline for herbarium specimens},
  journal = {Applications in Plant Sciences},
  year = {2025},
  volume = {13},
  number = {6},
  doi = {10.1002/aps3.70034}
}
Kostenlos starten →