UPDATE: Recording: Strategies for an OCR directed workflow
UPDATE: Google Notes from Strategies Webinar
Are you interested in discovering ways to use OCR output to speed up digitization?
Have you read the OCR research by Drinkwater et al (2014) showing that transcribers (paid or volunteer) like ordered data sets? So far, those entering data prefer images sorted by country and collector. New York Botanical Garden's, Stephen Gottschalk is experimenting with database procedures to find and group label images based on ocr output.
Please join us for a live demo and discussion of this method and other potential ways to use OCR output to improve the data transcription/validation/discovery process.
When: August 25th, 11 AM EDT
Where: http://idigbio.adobeconnect.com/augmentocr (headsets recommended)
Presenter: Stephen Gottschalk, NYBG Project Coordinator
Hosts: Brought to you by The iDigBio Augmenting OCR Working Group (aOCR wg) and iDigBio's Andrea Matsunaga from ACIS and the New York Botanical Garden (NYBG).
Questions: Please send them to Deb Paul dpaul AT fsu.edu or on Twitter @idbdeb
