Optical Character Recognition (OCR)

Optical Character Recognition is a method for automatic character recognition and aims to recognise characters (letters, numbers) from image files and then assign numerical values to these characters (ASCII, Unicode), which the computer can then read out as electronic, searchable full text. Modern algorithms can recognise printed letters as well as handwritten texts. Today, Intelligent Character Recognition (ICR) is also used to correct the recognised characters based on the context. A recognised "1" can thus be corrected into an "I" if it is used within a word. Recognised: "Ha1lo" -> Corrected: "Hello".

Application examples

Reading out doctor's prescriptions
Reading out handwritten doctor's prescriptions

Mail sorting
Handwritten letters are captured by camera technology. The characters are recognised by OCR and the letters are sorted accordingly.

Adobe Acrobat OCR
Scanned documents can be easily and quickly converted into PDF files with editable text.

Automated digitisation of historical prints
In the meantime, even historical prints with inconsistent orthography, frequent proper names and varying typefaces can be recognised satisfactorily.