Augmenting OCR

From iDigBio
Revision as of 16:44, 26 October 2012 by Dpaul (Talk | contribs)

Jump to: navigation, search

Augmenting OCR Working Group (A-OCR) Overview

This is a community derived encyclopedia of information about the Augmenting OCR working group. Members of this working group and the community are encouraged to work together to develop content and deliverables that will serve the broader digitization community.

A-OCR Goals

We are focusing the efforts of the working group to put together materials to help the community get more from their OCR strategies. Topics we are gathering material on include:

  • known effective practices for getting the most from any OCR software.
  • known issues that hinder good (useful) OCR output.
  • reporting findings after working with real image data and programmers to improve parsing of OCR output.
  • lists of OCR software currently being utilized by the natural history collections community.

OCR Related Materials

Check out the following pages. We welcome your input!

Events, Outreach and Education

Workshops

  • iDigBio Augmenting OCR Workshop - Our working group is meeting in Gainesville, Florida, October 1 - 2, 2012. We've put together an exciting and challenging meeting agenda.

iSchools Conference 2013

The iDigBio AOCR working group successfully proposed a half-day workshop put together by members of our working group at the 2013 iSchools Conference, Februay 12 in Fort Worth, Texas.

The iDigBio Augmenting OCR (AOCR) Working Group has put together two upcoming events as part of their efforts to update community knowledge about what is possible with Optical Character Recognition (OCR) and Natural Language Processing (NLP) and find collaborators to spur further development of effective OCR and NLP strategies in digitization. First, the AOCR working group successfully submitted a proposal to the 2013 iSchools Conference for a half-day workshop entitled: "Help iDigBio Reveal Hidden Data: iDigBio Augmenting OCR Working Group Needs You." Several key members of the working group, via panel presentations, plan to introduce the iSchools community to the scope and challenges of digitizing natural history collections with a focus on the use of OCR and NLP. Panel presentations planned encompass an all-inclusive world view including the curator, researcher, public user-interface, and aggregators. Using break-out groups, the AOCR working group hopes to find new insights and partners. Second, in an effort to further define effective OCR and NLP strategies and better delineate challenges, the AOCR working group set up a hackathon, concurrent with the iSchools 2013 Conference. With herabarium sheet, bryophyte packet and entolomology label sets, programmer + end user teams will be presented with two challenges: 1) to use the OCR software of their choice to output the cleanest OCR possible and 2) to use NLP algorithms in an effort to parse the OCR output into Darwin Core fields. Participants' outputs will be compared and scored with results shared via the iDigBio Wiki.

Hackathon I

Our working group is planning a Hackathon, concurrent with the above iSchools workshop to reach out beyond our natural history collections boarders for those with skills needed to improve and enhance our existing strategies for using OCR of images and parsing OCR output. The Hackathon is scheduled for February 13 - 14 at the Botanical Research Institute of Texas (BRIT). Members of the natural history community will be invited to participate and a general call will go out to the broader community for interested applicants in early to mid November of 2013.

Please let us know if you need assistance modifying this page: iDigBio Help Desk

Also, if you would like to learn more about wiki syntax: Mediawiki Wikitext Examples