Optical character recognition (OCR) is a function by which special software converts printed text into a format that can be edited with a word-processing program. The software works with data provided by a cameralike machine called a scanner. This machine converts printed information into digital format–that is, into the digits 0 and 1 that computers use to process information.
A scanner converts a page of information into a set of digits representing a single picture. But for text editing, the computer needs a set of digits for each letter, number, and other symbol. OCR software converts the scanned information into these individual sets. The software also corrects spelling errors that occur during conversion.
