University of Illinois Urbana-Champaign

Help iDigBio reveal hidden data: iDigBio Augmenting OCR working group needs you

Paul, Deborah L.; Heidorn, P. Bryan; Best, Jason; Gilbert, Edward; Neill, Amanda; Nelson, Gil; Ulate, William

Permalink

https://hdl.handle.net/2142/42502

Description

Title
Help iDigBio reveal hidden data: iDigBio Augmenting OCR working group needs you
Author(s)
  • Paul, Deborah L.
  • Heidorn, P. Bryan
  • Best, Jason
  • Gilbert, Edward
  • Neill, Amanda
  • Nelson, Gil
  • Ulate, William
Issue Date
2013-02
Keyword(s)
  • OCR
  • natural language
  • information analysis
  • machine language
  • information organization
  • information services
  • research methods
  • information retrieval
  • qualitative data analysis
  • iDigBio hackathon
Abstract
Integrated Digitized Biodiversity Collections, iDigBio, is funded under the National Science Foundation's (NSF) Advancing Digitization of Biological Collections (ADBC) program to help hundreds of natural history museums get specimen data out of millions of drawers and off of specimen labels into an integrated database for everyone. Over 130 museums are working together, funded as Thematic Collection Networks (TCNs), to capture standardized data to send to iDigBio's HUB, Home Uniting Biocollections cyberinfrastructure. Optical Character Recognition (OCR) and OCR output analysis play an important role in many museum object-to-image-to-data digitization workflows and are integral to several of the current TCN digitization projects. The iDigBio Augmenting OCR working group (AOCR) was formed to develop a multi-faceted approach to improvement of OCR strategies, including investigation of image segmentation, autocorrection of typographical errors, semantic autocorrection, autonormalization, automated text segmentation, generating consensus records, and user interfaces.
Publisher
iSchools
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/42502
DOI
https://doi.org/10.9776/13471
Copyright and License Information
Copyright © 2013 is held by the authors. Copyright permissions, when appropriate, must be obtained directly from the authors.

Owning Collections

iConference 2013 workshops PRIMARY