Hespi: A pipeline for automatically detecting information from hebarium specimen sheets

TL;DR

Hespi is an automated pipeline that uses computer vision and language models to efficiently extract biodiversity data from herbarium specimen sheets, reducing reliance on manual transcription.

Contribution

The paper introduces Hespi, a novel modular pipeline combining object detection, OCR, HTR, and LLMs for automated data extraction from herbarium specimens.

Findings

High accuracy in detecting and extracting text from specimen sheets.

Effective classification of label types (printed, handwritten, mixed).

Modular design allows customization and training of new models.

Abstract

Specimen-associated biodiversity data are crucial for biological, environmental, and conservation sciences. A rate shift is needed to extract data from specimen images efficiently, moving beyond human-mediated transcription. We developed `Hespi' (HErbarium Specimen sheet PIpeline) using advanced computer vision techniques to extract pre-catalogue data from primary specimen labels on herbarium specimens. Hespi integrates two object detection models: one for detecting the components of the sheet and another for fields on the primary primary specimen label. It classifies labels as printed, typed, handwritten, or mixed and uses Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) for extraction. The text is then corrected against authoritative taxon databases and refined using a multimodal Large Language Model (LLM). Hespi accurately detects and extracts text from specimen sheets across international herbaria, and its modular design allows users to train and integrate custom models.