Sorry to say but the OCR for Devanāgarī is hasn't been well developed. I had tried many OCR literally all existing free as well as commercial OCR for Devanāgarī but nothing works. The greatest disappointment was zero availability of any commercial OCR supporting Devanāgarī and the free Chitrankan from Indian Government which is joke in name of OCR. This is an area where lots of work needs to be done.
One, promising OCR that I found was from Germany, it is name SanskritOCR. I tried it under wine(under Fedora) and the recognition was over 90% with hi-resolution scans. The interface is in German but that won't been an issue it looks like English.;) Just do a Google search and download the tool, I don't have it right now. The one thing you need to consider is it gives the output in IAST - which is an form of loss-less transliteration for Devanāgarī (this is IAST). You can find couple of online tools to convert IAST to Devanāgarī. It also has some issues, but it works pretty much ok. You can also manually check the recognition. I hope that you get you working. Regards, Ujjwol ॐ स॒ह ना॑ववतु । स॒ह नौ॑ भुनक्तु । स॒ह वी॒र्यं॑ करवावहै । ते॒ज॒स्वि ना॒वधी॑तमस्तु॒ मा वि॑द्विषा॒वहै॑ ॥ ॐ शान्ति॒ः शान्ति॒ः शान्ति॑ः ॥ -- FOSS Nepal mailing list: [email protected] http://groups.google.com/group/foss-nepal To unsubscribe, e-mail: [email protected] Mailing List Guidelines: http://wiki.fossnepal.org/index.php?title=Mailing_List_Guidelines Community website: http://www.fossnepal.org/
