Optical Character Recognition (OCR) Definition

Optical character recognition (OCR) refers to the software used to convert letters and numbers that are non-editable into a format that can be edited. For example, a magazine article is something that can't be edited. Using OCR software, you could convert this article into a Microsoft Word document and then be able to change any of the words.

Before being able to use OCR software, you will need to get the document in to an electronic format if it isn't already in one. This can be accomplished by scanning it. The higher the quality of the scan and the higher the contrast there is between the characters and the background, the more likely the OCR software will recognize the text. However, even the best of the consumer-grade OCR software isn't perfect so expect a few mistakes.

Typical uses of optical character recognition software include processing checks, archiving library material, and letter sorting by the postal office.

Other Definitions