Quote:
Originally Posted by Ghitulescu
Again my friend you're talking about English and its 26 letters. Have you ever, to give an example, tried to scan Polish or Hungarian books? I am sure no. And even there there are errors that need human proofing, like I and l (capital i and small L). I know there are programs that can learn the characters/glyphs but still have the English rules (there are languages where "i" is written as such, for instance).
|
Which is precisely why a good OCR program, like Abbyy FineReader, knows about different languages: you tell it what language the book you're scanning is written in, and it adapts its interpretation of the text accordingly.
You have to accept the fact that no OCR program is perfect, and that proof-reading is always going to be essential, but good OCR programs are very good indeed, and should certainly (for novels at least) get you to the "one error every few pages" level of accuracy, which is really all that you can hope for.