EUVIMEDObjevte EUVIMED
ÜbersichtsarbeitOpen access · CC BY 4.0

A comprehensive review of detection, optical character recognition, and structuring methods for herbarium label digitization

Hiba Abbad iD, Hanane Ariouat, Nicolas Turenne, Eric Chenin, Abderrazak Sebaa, Edi Prifti, Jean-Daniel Zucker, Youcef Sklab iD

Applications in Plant Sciences · 2026-11-06

DOI: 10.1002/aps3.70084 ↗

At a glance

Übersichtsarbeit in Applications in Plant Sciences, published online on 2026-11-06. Written by Hiba Abbad and 7 co-authors. Institution: Laboratoire LITAN, École Supérieure en Sciences et Technologies de l'Informatique et du Numérique (ESTIN) Béjaïa Algeria. 68 references. The full text is freely available (open access, CC BY 4.0). Funded by: Agence Nationale de la Recherche.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Global herbarium digitization has produced over 50 million specimen images, many of which contain handwritten or printed labels with rich metadata such as species names, collection dates, localities, and ecological notes. Manual transcription of this information is labor intensive, error prone, and not scalable, which has motivated the development of automated solutions. This systematic review examines studies published between 2018 and 2026, identified through electronic database searches and backward reference screening, focusing on deep learning and computer vision approaches for herbarium label digitization. The reviewed methods include convolutional neural networks, transformer‐based models, large language models, and open‐source pipelines for optical character recognition and structured metadata extraction from historical and handwritten botanical records. The results highlight significant advances in label detection, text recognition accuracy, and metadata structuring enabled by deep learning techniques, although reported performance varies considerably depending on dataset quality, handwriting complexity, and domain adaptation strategies. Despite this progress, substantial challenges remain in handling historical handwriting styles, heterogeneous label layouts, and multilingual collections. Future research should emphasize the creation of curated benchmark datasets and the development of scalable, robust artificial intelligence (AI) pipelines to enhance the reliability, efficiency, and generalizability of automated herbarium digitization systems.

Subjects

Author keywords

deep learningherbarium digitizationlabel detectionlarge language models (LLMs)metadata structuringnamed entity recognition (NER)optical character recognition (OCR)

Authors and institutions

  • Laboratoire LITAN, École Supérieure en Sciences et Technologies de l'Informatique et du Numérique (ESTIN) Béjaïa Algeria.
  • Institut de Recherche pour le Développement (IRD) Sorbonne Université, UMMISCO Paris France.
  • INRAE MathNum France.
  • Muséum national d'Histoire naturelle (MNHN), Institut de Systématique, Évolution, Biodiversité (ISYEB) Paris France.
  • Sorbonne Université, INSERM, Nutrition et Obesities; systemic approaches, NutriOmique, AP-HP, Hôpital Pitié-Salpêtrière Paris France.

ORCID profiles: Hiba Abbad, Youcef Sklab

Funding

  • Agence Nationale de la Recherche

Cite

APA

Abbad, H., Ariouat, H., Turenne, N., Chenin, E., Sebaa, A., Prifti, E., Zucker, J. D., & Sklab, Y. (2026). A comprehensive review of detection, optical character recognition, and structuring methods for herbarium label digitization. Applications in Plant Sciences. https://doi.org/10.1002/aps3.70084

Vancouver

Abbad H, Ariouat H, Turenne N, Chenin E, Sebaa A, Prifti E, et al. A comprehensive review of detection, optical character recognition, and structuring methods for herbarium label digitization. Applications in Plant Sciences. 2026. doi:10.1002/aps3.70084

BibTeX
@article{Abbad2026,
  author = {Abbad, Hiba and Ariouat, Hanane and Turenne, Nicolas and Chenin, Eric and Sebaa, Abderrazak and Prifti, Edi and Zucker, Jean-Daniel and Sklab, Youcef},
  title = {A comprehensive review of detection, optical character recognition, and structuring methods for herbarium label digitization},
  journal = {Applications in Plant Sciences},
  year = {2026},
  doi = {10.1002/aps3.70084}
}
Start for free →