Related Experiment Video
Updated: Jul 6, 2025

Robust DNA Isolation and High-throughput Sequencing Library Construction for Herbarium Specimens
Published on: March 8, 2018
A novel automated label data extraction and data base generation system from herbarium specimen images using OCR and
Atsuko Takano1, Theodor C H Cole2, Hajime Konagai3
1Institute of Natural Science and Environment, University of Hyogo/The Museum of Nature and Human Activities, Hyogo, 6 Chome, Yayoigaoka, Sanda, Hyogo, 669-1546, Japan. takano@hitohaku.jp.
Automated digital extraction of herbarium specimen data is now possible using optical character recognition (OCR) and named entity recognition (NER) techniques. This advancement improves documentation and global information availability for natural history collections worldwide.
Area of Science:
- Biodiversity Informatics
- Digital Curation
- Natural History Collections
Background:
- Improving data accessibility from natural history specimens is crucial for global research.
- Herbaria are increasingly digitizing collections, but efficient data extraction remains a challenge.
Purpose of the Study:
- To develop a fully automatic system for extracting label data from herbarium specimen images.
- To enhance the efficiency of data entry and processing for natural history collections.
Main Methods:
- Utilized optical character recognition (OCR) for text identification.
- Employed named entity recognition (NER) for structured data extraction.
- Developed a system runnable on standard desktop computers.
Main Results:
- Achieved advancements in fully automatic label data extraction from herbarium images.
- Demonstrated applicability to diverse natural history specimens, including entomological collections.
- System is adaptable for widespread use in digitization efforts.
Conclusions:
- The developed system significantly facilitates the digitization and publication of natural history museum specimens.
- This technology can be applied globally to improve documentation and information availability.
- Enables efficient data processing for enhanced scientific accessibility.
More Related Videos
11:14Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry
Published on: October 2, 2016
08:55Author Spotlight: Harnessing DNA Barcode Technology to Enhance the Efficiency of Medicinal Plant Identification
Published on: November 1, 2024