High Throughput Information Extraction of Printed Specimen Labels from Large-Scale Digitization of Entomological Collections using a Semi-Automated Pipeline
Margot Belot, Joël Tuberosa, Leonardo Preuss, Olha Svezhentseva, Magdalena Claessen, Christian Bölling, Franziska Schuster, Théo Léger
This paper develops a semi-automated pipeline for extracting metadata from insect specimen labels using computer vision and OCR, achieving 98% accuracy in printed label extraction.
bioRxiv · Jul 9, 2025 · PreprintBioinformatics