Dear Salahuddin,
thanks for your appreciation. I agree with you
about the OCR requirements in all OS. But there are so many issues that its
quite complicated to look after all the issues. The preprocessor can be
modulated and I have plan to do that. If you are interested to do this then
I can assist you.
I am really happy to see that you are working in this field. Hope your
contribution will play a big role.
Regards,
----
Hasnat
Center for Research on Bangla Language Processing (CRBLP)
http://mhasnat.googlepages.com/
On Mon, Jun 8, 2009 at 12:43 AM, Salahuddin Pasha <[email protected]>wrote:
> Dear Hasnat,
> Thank you for your mail and your contribution. I have
> tried BanglaOCR after I got your mail but I found there is no Mac OS X and
> native Linux support.
>
> Just asking is it possible to make the preprocessor modulated so that we
> can use it with the default Tesseract-OCR (or a patch).
> I have installed Tesseract-OCR svn release in Mac OS X and Debian Linux
> without any single hassle, it simply works.
> Thanks in advance.
>
> Regards
> Salahuddin
>
>
> On Jun 6, 2009, at 11:50 AM, Hasnat wrote:
>
> Dear Salahuddin,
> nice to know about your work. I am working on
> BanglaOCR and developed Tesseract based BanglaOCR at our lab. Version 0.7 is
> released recently and the development for the next version is ongoing. The
> tessdata.ban is prepared by me. In the BanglaOCR you will find the complete
> preprocessor and also post processor. The link for the BanglaOCR is :
> http://code.google.com/p/banglaocr/
>
> Regards,
> ----
> Hasnat
> Center for Research on Bangla Language Processing (CRBLP)
> http://mhasnat.googlepages.com/
>
>
> On Fri, Jun 5, 2009 at 4:46 PM, 74yrs old <[email protected]> wrote:
>
>> please contact Hasnat who is doing research on Bangla at CRBLP. His email
>> address = Hasnat <[email protected]>
>>
>>
>> On Fri, Jun 5, 2009 at 1:29 PM, salahuddin66 <[email protected]>wrote:
>>
>>>
>>> Dear all,
>>>
>>> I am working on a bangla preprocessor for OCR. It converts the
>>> connected alphabet into separate alphabet then process by tesseract.
>>>
>>>
>>> I have also made a web-based interface, after upload image in our
>>> website, it preprocess the image using our preprocessor and later on
>>> convert with tesseract and show the output. (License: GPL).
>>>
>>> Example:
>>> http://dhaka.ankur.org.bd:2121/bangla_preprocessor_demo.pdf
>>> http://dhaka.ankur.org.bd:2121/bangla_preprocessor_demo.png
>>>
>>>
>>> I could not find any contact address for "tessdata.ban" people (they
>>> did a great job), any idea ?
>>>
>>> Do you think it might helpful for other people if I start a web-based
>>> tesseract-ocr testing place for other languages as well ?
>>>
>>> Bangla preprocessor is still under development, any comments or
>>> suggestion would helpful for us ?
>>>
>>>
>>>
>>> Regards,
>>> Salahuddin
>>>
>>> salahuddin66.blogspot.com
>>> salahuddin66.deviantart.com
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>
>>
>>
>
>
>
>
>
> >
>
--~--~---------~--~----~------------~-------~--~----~
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
-~----------~----~----~----~------~----~------~--~---
