Hi Debayanin, >I plan to increase accuracy (it stands at 87% .>now) and implement morphological operations Better to proceed with your plan, since Indic is very complex script -without loss of time. When succeeded, your plan automatically will be incorporated in Tesseract and ocropus project. with regards, -sriranga(76yrsold)
On Wed, Oct 8, 2008 at 9:40 PM, [EMAIL PROTECTED] <[EMAIL PROTECTED]>wrote: > > Dear Ray/Tom, > I did some work on adding Indic script support to Tesseract this > summer. The hack-blog may be found at > http://debayanin.googlepages.com/hackingtessearct > and the project is at http://code.google.com/p/tesseractindic/ . I > knew, before i started the project, that my work will not be absorbed > to the main branch, as it was not of sufficient quality. I worked for > under a month on this. > After a few months i learned that Tom had implemented "matraa > clipping" using morphological operations (http://sites.google.com/site/ > ocropus/languages/devanagari-hindi-sanskrit<http://sites.google.com/site/ocropus/languages/devanagari-hindi-sanskrit>and > http://sites.google.com/site/ocropus/morphological-operations), which > is a better method than using projection operation. > Recently, Sarai, an organisation that works on FLOSS projects in India > has announced a fellowship for work on Indic OCR. One of the proposals > likely to be accepted is to work farther in adding Indic script > support to Tesseract. I plan to increase accuracy (it stands at 87% > now) and implement morphological operations. But for that, i need an > "ack" from you guys. Are you planning to implement Indic language > support anytime soon. Will our work overlap on yours? Could you tell > me when exactly you do plan to implement it? > Eagerly waiting for a reply, from any person who knows. > > ~Debayan > > > --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en -~----------~----~----~----~------~----~------~--~---
