OCR is a common and useful method of digitizing texts so that they can be electronically edited, searched, and manipulated. OCR-ed texts can be used in to aid work in cognitive computing, machine translation, text-to-speech, and text mining.
Performing OCR on a text can be an important step in digitizing the document for use in your research, or in making the contents of the document widely accessible to others. By performing OCR, the contents of the document become digitally available in a searchable, easily manipulated format, and can be used for a variety of scholarly purposes.