Sklab Youcef auteur aut IRD Castanet F. auteur aut IRD Ariouat H. auteur aut IRD Arib S. auteur aut IRD Zucker Jean-Daniel auteur aut IRD Chenin Eric auteur aut IRD Prifti Edi auteur aut IRD text journalArticle eng text/pdf reformatted digital access 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 S & oslash;rensen-Dice coefficient metrics.Results PlantSAM achieved state-of-the-art segmentation performance, with an IoU of 0.94 and a S & oslash;rensen-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. specialized botanical analysis herbarium specimens Segment Anything Model (SAM) semantic segmentation YOLOv10 076 020 [Early access] [14 p.] 2025 2168-0450 https://www.documentation.ird.fr/hor/fdi:010095889 10.1002/aps3.70034 2168-0450 [F B010095889] https://www.documentation.ird.fr/hor/fdi:010095889 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2026-01/010095889.pdf IRD - Base Horizon / Pleins textes 2026-01-14 2026-06-12 fdi:010095889 fre