Library Calendar

Back to Listing

Making Scanned Text Machine Readable through Optical Character Recognition

Event Type
digital humanities
University Library - Scholarly Commons
The workshop will be held in the Main Library, Library 314. Take the north stairwell (Armory and Wright Street entrance) to the 3rd floor of the Main Library and make a left at the top of the stairs.
Mar 31, 2017   11:00 am - 12:00 pm  
Claire Berman
Originating Calendar
Savvy Researcher Workshops - University Library

Optical Character Recognition (OCR) is a process that converts scanned images and documents into editable, searchable formats. OCR helps your computer to recognize letter shapes in a scanned document and turn them into text you can copy and edit as needed. This allows you to extract information from documents quickly and easily. OCR also enables these texts to be used in key data and text mining projects. This workshop will give attendees a basic understanding of how to make use of optical character recognition software, including Adobe Acrobat Pro, ABBYY FineReader, and Tesseract, in their research, as well as give them a chance for hands-on experience with these programs in the Scholarly Commons.

link for robots only