
Originally Posted by
Michael Hanel
Different programs pick up scanned material with different levels of accuracy, depending a lot on the quality of the material which is scanned initially. However, even if you had perfect images to scan for Abbott (which isn't the case), the OCR programs would still have a devil of a time with all the languages together. Character recognition is hard enough in one language, let alone Greek, Hebrew and English together. That said, some programs do boast that they are better at doing this than others, but again I think their boasts are only meaningful under "optimum" conditions. Then the real question is whether it's better from a matter of resources to spend time OCRing and then correcting a text or just typing it all by hand.