What is OCR

OCR is an acronym for "Optical Character Recognition" and refers to software which can translate images into text.  OCR software might be used to convert a scanned page or fax document (both are in image format) from image format to searchable-text or "full text" format.  

OCR software attempts to do what the human brain does - translate shapes into letters.  Different software products approach this problem with different strategies.  "Artifacts" on an image (lines, handwriting fuzzy characters) may confuse the OCR software and thus reduce the accuracy of translation from image to full-text.

Please rate this article