Please use this identifier to cite or link to this item: http://dx.doi.org/10.34960/26
Title: D4.1 Methods for Automated Text Digitisation
Authors: Owen, David
Groom, Quentin
Hardisty, Alex
Leegwater, Thijs
van Walsum, Myriam
Wijkamp, Noortje
Spasić, Irena
Contributors: Dillen, Mathias
Livermore, Laurence
Phillips, Sarah
Wu, Zhengzhe
Keywords: Digitisation
Publication Date: 2019
Publisher: ICEDIG
Citation: Owen David, Groom Quentin, Hardisty Alex, Leegwater Thijs, van Walsum Myriam, Wijkamp Noortje, & Spasić Irena. (2019). Methods for Automated Text Digitisation. Zenodo.
Abstract: In this document we describe an effective approach to automated text digitisation with respect to specimen labels. These labels contain much useful data about the specimen including its collector, country of origin and collection date. Our approach to automatically extracting these data takes the form of a pipeline. Recommendations are made for the pipeline’s component parts based on some of the state-of-the-art technologies.
URI: https://know.dissco.eu/handle/item/91
DOI: https://doi.org/10.5281/zenodo.3364502
Appears in the Folders:ICEDIG Work Package 4 - Business Framework

Files in This Item:
File Description SizeFormat 
Deliverable D4.1 ICEDIG - Methods for Automated Text Digitisation.pdf3.42 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License