OCR (Optical Character Recognition)
Optical Character Recognition (OCR) describes the process in which a computer tries to recognise all letters and numbers from an image file's pixels.
This is done by comparing the image's pixel array to the known pixel arrays of various computer fonts as well as other, in parts relatively complex, mathematical procedures. As a result a computer needs a lot of computer power for Optical Character Recognition.
For instance, some Document Management Systems use OCR to generate a full-text index.
As tests have repeatedly shown, the Omnipage-OCR used by bitfarm-Archiv Document Management is the leading OCR world-wide – next to Abby-Finereader. The exact and – in good documents error-free – full-text allows for quick and accurate retrieval of documents, without making extensive tagging necessary.