Thank you very much for answer! But as I say, VietOCR doesn't make workable
files for me and I don't know why. Even if I use "vie" language made by
that program without any changes, I got an error "Attempted to read or
write protected memory" on the line
if (processor.Init(@".\tessdata\\", "vie", (int)eOcrEngineMode.OEM_DEFAULT))
By the way, do you see two ending slashes? :) I got the same error with
native "eng" languag if I use one and no slahes at all. Tried two slashes
and it began to work! But for "vie" language data that trick doesn't work.
What about only numbers -I like to use
processor.SetVariable("tessedit_char_whitelist", "0123456789");
It works fine, but I get wrong numbers sometimes.
Thank for your advice about resolution, I'll try.
пятница, 31 октября 2014 г., 17:20:18 UTC+3 пользователь shree написал:
>
> change image to 300 dpi
>
> try vietocr - in screenshot mode -
> try with the vietnamese traineddata
>
> ----------------
>
> with commandline tesseract use 'digits' config file as parameter
>
> "recognizing only numbers is actually answered on the tesseract FAQ
> <http://code.google.com/p/tesseract-ocr/wiki/FAQ> page. See that page for
> more info, but if you have the version 3 package, the config files are
> already set up. You just specify on the commandline:
>
> tesseract image.tif outputbase nobatch digits
>
>
>
> ShreeDevi
> ____________________________________________________________
> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com
>
> On Fri, Oct 31, 2014 at 6:33 PM, Gennady Goncharov <[email protected]
> <javascript:>> wrote:
>
>> Hi, first of all I must say thank you for all developers, who did so much
>> job to create Tesseract OCR! That's really cool!
>>
>> But I have one problem with using it and can't solve it by myself, so
>> please help me!
>>
>> Result of recognize atteched image is 105 500. Why is it 500 not 600? I
>> tried a lot of ways to solve it:
>> - I used tesseract2 and tesseract3;
>> - I tried to train it by special font with jTessBoxEditor (after that it
>> doesn't work at all - error about attempting to read data);
>> - I tried to scale the image four times with highqualitybicube.
>>
>> Nothing works. And I have a question - could anybody train tesseract3 for
>> a font supercell-magic? It is attached. I need only numbers.
>>
>> Any help would be greatly appreciated!
>>
>> --
>> You received this message because you are subscribed to the Google Groups
>> "tesseract-ocr" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to [email protected] <javascript:>.
>> To post to this group, send email to [email protected]
>> <javascript:>.
>> Visit this group at http://groups.google.com/group/tesseract-ocr.
>> To view this discussion on the web visit
>> https://groups.google.com/d/msgid/tesseract-ocr/e46e341f-0ce0-4ec3-9709-4826849a7ce0%40googlegroups.com
>>
>> <https://groups.google.com/d/msgid/tesseract-ocr/e46e341f-0ce0-4ec3-9709-4826849a7ce0%40googlegroups.com?utm_medium=email&utm_source=footer>
>> .
>> For more options, visit https://groups.google.com/d/optout.
>>
>
>
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/1a96b2c6-e1d4-4b7b-a1a4-3b32c5470d06%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
