What is OCR and where does it fit in with imaging?
OCR is a method which involves the computer ‘reading’ the words on an image and converting the text into a form which can then be processed by the computer. A variety of packages are available which run under windows, some specialist packages can even be trained to recognize handwriting and signatures. OCR is often used to capture text from a document to form part of the index. The text can then be exported into other applications if desired. Relatively speaking, OCR is still in its infancy and no package can as yet claim to be 100% accurate. Thus OCR used for indexing purposes would require some manual verification, particularly if it is used to key primary fields.
