What is OCR?

OCR meaning in Digital terms is Optical Character Recognition (OCR) is a technology that allows dots or pixels representing machine generated characters in a raster image to be converted into digitally coded text. In addition to recognizing and coding text, OCR programs attempt to recognize and code the structural elements of a document page, such as columns and non-text graphical elements. Intelligent Character Recognition (ICR) is a related technology designed to recognize hand written characters. OCR is generally part of a workflow that begins with the scanning documents. Scanned images may be further processed or "cleaned" (for example, see contrast stretching) prior to OCR to improve accuracy of the recognition process. Modern OCR applications are capable of producing multiple output formats such as ASCII, RTF, Microsoft Word or PDF. While some hardware applications for OCR exist, the vast majority of OCR is performed by software applications.


reference: Federal Agencies Digital Guidelines Initiative – Glossary