Illinois Digital Newspaper Collection: Crowd-Sourced OCR Correction

Written by William Schlaack, Digital Reformatting Coordinator

Looking for something to do that incorporates reading primary sources, exploring historical events, and expanding access to Library materials? Then head on over to the Illinois Digital Newspaper Collections (IDNC) and try your hand at text-correction! All that is required is a free user account and a keen eye.

While always growing IDNC currently provides free access to 158,430 issues from 146 newspapers from across the country. During the digitization process, newspapers are scanned using a special software featuring Optical Character Recognition (OCR). OCR software recognizes the shape of images and assigns alphabetical values to them. Due to the mass, automated nature of this process certain fonts, charts, and images are output incorrectly, resulting in garbled text that is not useful for keyword searching. Text correction thus improves the accuracy of keyword searches and helps researchers like you.

Before user text correction
During user text correction.
After user text correction.

For detailed instructions click here. If you have any questions feel free to email idnc@library.illinois.edu – thank you!