In this week’s Tagging the Tower post, GC Digital Fellow Leanne Fan explains how to extract text from images. If you’ve ever saved a photograph of a newspaper or book and you really wanted to copy and select the text in that image, you would find yourself in a sticky situation. Leanne’s post addresses the issue by introducing the concept of OCR (Optical Character Recognition) which encompasses different ways for computers to scan images and identify the text that is contained in them. This is a great post for folks who are hoping to create actionable data from images and in order to perform text analysis.
Read More: Finding the Perfect OCR – GC Digital Fellows