A process in which a machine scans, recognizes, and encodes information printed or typed in alphanumeric characters. The first devices, marketed around 1955, could only recognize a limited repertoire of characters that had to be produced in a font that was optimized for machine recognition but was still recognizable by people. By the mid-1970s OCR A font and OCR B font were the dominant fonts and were close to a normal letter-press appearance. Modern OCR equipment can read most typed or printed documents and high recognition rates are achieved. OCR A and B fonts are still used for applications requiring high accuracy and in cases when context cannot aid recognition. In some instances printed information intended for MICR (magnetic-ink character recognition) is read by optical recognition techniques, as with some check readers associated with bank teller terminals.

OCR software is now readily available for many low-cost scanners giving good recognition rates for printed material using the Latin alphabet. The more difficult problems posed by other character sets and handwriting are areas of ongoing research.