optical character recognition

optical character recognition (OCR), method for the machine-reading of typeset, typed, and, in some cases, hand-printed letters, numbers, and symbols using optical sensing and a computer. The light reflected by a printed text, for example, is recorded as patterns of light and dark areas by an array of photoelectric cells in a optical scanner. A computer program analyzes the patterns and identifies the characters they represent, with some tolerance for less than perfect and uniform text. OCR is also used to produce text files from computer files that contain images of alphanumeric characters, such as those produced by fax transmissions. See also computer graphics; pen-based computer; personal digital assistant.

The Columbia Electronic Encyclopedia, 6th ed. Copyright © 2024, Columbia University Press. All rights reserved.

See more Encyclopedia articles on: Computers and Computing