OCR or Optical Character Recognition technology, is software which allows text on a scanned document to be read by a computer. Since documents are initially scanned as an image, a computer only has a record of light and color. Once OCR software is integrated, characters can be recognized, allowing documents to be searched. OCR (optical character recognition) is the software we use to turn a simple scanned image of your paper into a fully text-searchable digital document. Once OCR is employed, applications can recognize individual characters and effectively "read" the document.
There are many advantages and disadvantages to OCR technology. Although it is fast and can simplify your work load enormously compared to manually searching your documents - it is not perfect. OCR technology has a 99% accuracy rating. This means that there is a possibility that it may not correctly recognize some characters.
To learn more about OCR technology visit Wikipedia OCR