Advancements in data extraction from natural history collections: automatic label extraction from specimen images using OCR and NER

Abstract

Digital extraction of label data from natural history specimens along with more efficient procedures of data entry will become essential for documentation and global information availability in the near future. Herbarium collections have made great advances in this direction lately. In this study, using optical character recognition (OCR) and named entity recognition (NER) techniques, we have been able to almost automatically extract label data from herbarium specimen images. This system can be developed and run on a PC with standard specifications, and can also be applied to extracting label data from diverse kinds of natural history specimens, such as those in entomological collections. This system can facilitate the digitization and publication of natural history museum specimens around the world.