Enhancing plant morphological trait identification in herbarium collections through deep learning–based segmentation
Our approach isolates plant elements in herbarium scans by removing background elements to improve classification tasks. We demonstrate that image segmentation significantly enhances the performance of plant morphological trait identification models.
Authors
- Hanane Ariouat (ORCID: https://orcid.org/0009-0002-7066-4358)
- Eric Chenin
- Edi Prifti (ORCID: https://orcid.org/0000-0001-8861-1305)
- Jean‐Daniel Zucker (ORCID: https://orcid.org/0000-0002-5597-7922)
- Youcef Sklab (ORCID: https://orcid.org/0000-0002-7045-9402)
Institutions
- Inserm (FR)
- Sorbonne Université (FR)
- Nutrition et obésité : approches systémiques (FR)
- Unité de Modélisation Mathématique et Informatique des Systèmes Complexes (FR)
- Institut de Recherche pour le Développement (FR)
Publication Details
- Journal
- Applications in Plant Sciences
- Published
- 2025-02-13
- DOI
- https://doi.org/10.1002/aps3.70000
- Citations
- 7
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 12.25
Funders
- Agence Nationale de la Recherche
- Grand Équipement National De Calcul Intensif