EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated information extraction from plant specimen labels using OCR and large language models

Juan Wen iD

Biodiversity Data Journal · 19.01.2026 · 14

DOI: 10.3897/bdj.14.e177202 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biodiversity Data Journal, online erschienen am 19.01.2026. Verfasst von Juan Wen. Beteiligte Einrichtung: Kunming Institute of Botany, Chinese Academy of Sciences, Kunming, China Kunming Institute of Botany, Chinese Academy of Sciences Kunming China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The digitization of herbarium specimens is crucial for advancing biodiversity research and data sharing. However, this process is often hindered by the inefficiency of manual transcription and the technical challenges posed by the massive volume of specimens, heterogeneous label layouts, and the prevalence of handwritten texts. To overcome these bottlenecks, this study proposed an automated pipeline that integrates the PadddleOCR engine with the DeepSeek large language model (LLM) for structured information extraction from specimen labels. The pipeline is designed to extract 16 key metadata fields from both printed and handwritten labels. Evaluated on a benchmark dataset, it achieved a high field-level accuracy of 95.4% for printed labels, demonstrating strong reliability. For handwritten labels, the system maintained functionality while correctly identifying its limitations through a confidence-based quality control mechanism. A key finding was the compensatory role of the LLM, which effectively corrected upstream OCR errors, as evidenced by a weak correlation ( r = 0.32) between OCR (Optical Character Recognition) confidence and final extraction accuracy. This hybrid architecture ensures data security through local image processing and cost-efficiency via text-only LLM parsing. This work provides a robust, scalable, and practical solution for accelerating the digitization of botanical collections. The method is directly applicable to real-world digitization workflows and promises to significantly enhance the efficiency of biodiversity data creation and sharing.

Schlagwörter

Stichwörter der Autor:innen

PaddleOCRartificial intelligenceinformation extractionlarge language modelplant specimen digitizationtext recognition

Autor:innen und Institutionen

  • Kunming Institute of Botany, Chinese Academy of Sciences, Kunming, China Kunming Institute of Botany, Chinese Academy of Sciences Kunming China.

ORCID-Profile: Juan Wen

Zitieren

APA

Wen, J. (2026). Automated information extraction from plant specimen labels using OCR and large language models. Biodiversity Data Journal, 14. https://doi.org/10.3897/bdj.14.e177202

Vancouver

Wen J. Automated information extraction from plant specimen labels using OCR and large language models. Biodiversity Data Journal. 2026;14. doi:10.3897/bdj.14.e177202

BibTeX
@article{Wen2026,
  author = {Wen, Juan},
  title = {Automated information extraction from plant specimen labels using OCR and large language models},
  journal = {Biodiversity Data Journal},
  year = {2026},
  volume = {14},
  doi = {10.3897/bdj.14.e177202}
}
Kostenlos starten →