optical character recognition (OCR)
Optical character recognition (OCR) began with machine-readable fonts, which can be seen as an alternative to barcodes. For this purpose, national and international standardization bodies developed their own fonts.
OCR-A is an alphanumeric font that uses highly stylized typefaces and offers hardly any possibility of confusion. This typeface can be found in the check number field on checks; it is standardized under DIN 66008.
A broader approach is taken by the OCR-Bfont, which was developed by the European Computer Manufacturers Association( ECMA) and standardized nationally by the German Institute for Standardization (DIN 66009). (DIN 66009). It consists of numerals, as well as upper and lower case letters. This font type can be found on machine-readable deposit slips.
There is also OCR-H, which is specified in DIN 66225 and serves as a reference font for handwritten block letters.
Since optical character recognition is of interest for many applications, the OCR topic has been broadened for PC technology and has developed rapidly there. It is about intelligent character recognition and handwriting recognition in text recognition that is independent of writing.
In all methods of character recognition, texts are captured by a scanner or reading pen and processed in the computer. Since the computer recognizes a scanned text as a graphic, it is necessary to break it down into individual letters, which can then be processed in a text program. To do this, the program compares the individual graphic letters with a predefined letter mask and then generates a letter if a certain correspondence between the scanned and mask letters is detected.
Letters, digits and characters recognized by OCR can be reconstructed in their original form. OCR is a component of PC-based fax programs. Despite the continuous improvement in recognition, a small percentage of text capture remains incorrect, depending on the quality of the capture.