TINY TEXT AHEAD! Move up!
Quality OCR A TANGO OF AVAILABLE RESOURCES Michelle Paolillo, Digital Lifecycle Lead Mira Basara, Ingest Collection Specialist Cornell University
Quality OCR A TANGO OF AVAILABLE RESOURCES Michelle Paolillo, Digital Lifecycle Lead Mira Basara, Ingest Collection Specialist Cornell University
Quality OCR A TANGO OF AVAILABLE RESOURCES Michelle Paolillo, Digital Lifecycle Lead Mira Basara, Ingest Collection Specialist Cornell University
Who among us… …are OCR nerds?
History ‐ OCR at Cornell D‐Lib Magazine , October 1996, http://mirror.dlib.org/dlib/october96/cornell/10chapman.html
evolutions… TextBridge
our current practice CHALLENGES AND STRATEGIES
TextBridge 2007 ABBYY FR 2019
TextBridge 2005 ABBYY FR 2019
Latin Latin, Greek
Inverted, cropped, deskewed image Original image
OCR from Original OCR from inverted, cropped
Character fill – pattern training helps
Fraktur OCR of Fraktur (as found in older German texts) is very difficult. • For many characters, there are rules that govern the form of a character depending in its position. • Other characters that are interpreted differently may resemble each other closely.
Fraktur OCR ‐ Google Cloud Vision
opportunities DECISION POINTS
Points of opportunity Re‐OCR
Forced decision point Upgraded
Testing alternatives
Quality OCR A TANGO OF AVAILABLE RESOURCES Michelle Paolillo, Digital Lifecycle Lead Mira Basara, Ingest Collection Specialist Cornell University
Quality OCR A TANGO OF AVAILABLE RESOURCES Michelle Paolillo, Digital Lifecycle Lead Mira Basara, Ingest Collection Specialist Cornell University
Discussion navigate to www.menti.com And use code 97 04 40
Recommend
More recommend