2009/12/9 Murthy Raju <[email protected]>: > Hi All, > > I am Murthy Raju from Chennai and have just joined the group. I am not a > developer of C or C++, but would love to be of any help with my knowledge of > Telugu, Tamil and Hindi. > > I attended Debayan Banerjee's talk at Foss.in on his OCR project and was > very impressed with it. Will be glad to be of some help there. I mentioned > to Debayan when I met him at Foss.in about Project Madurai > (http://www.projectmadurai.org/)
Thanks Mr. Murthy for making the effort to get in touch by joining the list. Surely the set of scanned images and text will help me in the process of testing the OCR. I have mailed the project madurai admin for it, and await his/her reply. For your information, I am thinking of another model for testing. I am planning to render out text to an image and then OCR it for testing. This model will free dependencies for testing on external sources such as the ones you pointed out. However, once we have done testing like that, we will probably have to move to real world testing scenario with scanned images which have different kind of noises associated with them. Hence, that set will be useful. We need to set up some kind of infrastructure for hosting all these language specific resources for OCR. I am thinking how to do that best. For the time being Sir, join the project mailing list http://groups.google.com/group/indic-ocr, visit the project page http://code.google.com/p/tesseractindic and read through http://hacking-tesseract.blogspot.com/ if you have the time. -- Regards, Debayan Banerjee ------------------------------------------------------------------------------ Return on Information: Google Enterprise Search pays you back Get the facts. http://p.sf.net/sfu/google-dev2dev _______________________________________________ IndLinux-group mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/indlinux-group
