An Introduction to OCR and Image Derivatives
Full-text search in a digital image collection enables students, researchers, and other library patrons to find the content they're looking for. But how do you optimize your text conversion to get the best results?
Optical character recognition (OCR) isn't new technology, but it is still evolving and improving.
In this webinar, recorded April 27, 2016, Eric Larson, vice president of digitization services, walks you through the basics of OCR and the derivative files you'll need to enable text discovery in your digital collections.
Eric covers what you can expect from today's OCR engines, what they can and can't do. He talks about optimizing images at the capture stage to make OCR more reliable. And he discusses the pairing of images and text in various formats.