Metraipolis › archive › dc_fc5aa0714f35
Automated pipeline for herbarium label digitization — arXiv:2608.28676
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28676
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:53:12.167Z
- SHA-256 of the archived text
c8cfa806f3ab24fc1504fc1a3bf7557842748ee5b6de06c134c54a079b0882bc- Stable URL of this page
https://metraipolis.com/documento/dc_fc5aa0714f35
How to cite
Automated pipeline for herbarium label digitization — arXiv:2608.28676 — arXiv (en), https://arxiv.org/abs/2608.28676 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc5aa0714f35 (Metraipolis archive dc_fc5aa0714f35, sha256 c8cfa806f3ab24fc1504fc1a3bf7557842748ee5b6de06c134c54a079b0882bc)
BibTeX
@misc{dcfc5aa0714f35,
title = {Automated pipeline for herbarium label digitization — arXiv:2608.28676},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28676},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc5aa0714f35; sha256 c8cfa806f3ab24fc1504fc1a3bf7557842748ee5b6de06c134c54a079b0882bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28676. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Digitized herbarium collections, now comprising over 100 million freely accessible specimen images, have become a critical resource for addressing fundamental questions in ecology and evolutionary biology. Yet the rich metadata encoded in herbarium labels (collector identities, geographic localities, collection dates, and ecological observations) remains largely inaccessible at scale, constraining both biodiversity informatics and the construction of specimen-specific image-text corpora for multimodal AI. We present HERBIOME, a modular end-to-end pipeline for automated herbarium label digitization, integrating YOLOv8-based component detection, CRAFT Hezar word-level text localization, fine-tuned TrOCR for recognition of mixed handwritten and printed text, and GPT-4o Mini for semantic metadata structuring into standardized fields. TrOCR was trained on a multi-source dataset combining general transcription corpora (CREMMA-AN, PictoCatalogs) with herbarium-specific data (RéColNat), achieving a Character Error Rate of 4.05-4.10%. End-to-end evaluation on 450 French herbarium specimens, using a dual-metric framework of Maximum Window Similarity (MWS: 0.614-0.618) and Semantic Metadata Accuracy (SMA: 0.440-0.445), reveals that hybrid training strategies improve semantic fidelity while random sampling maximizes surface similarity, with taxonomic fields remaining the principal bottleneck. By automating the extraction of structured metadata from complex, heterogeneous labels, HERBIOME reduces transcription burden, enables the construction of paired image-text datasets that faithfully capture specimen individuality, which is a prerequisite for next-generation multimodal biodiversity AI systems. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28676 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:47.925Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).