On Saturday, August 13, 2016 at 2:11:16 PM UTC+5:30, Nalin Linux wrote:
>
>
>> 1) do your work inside /usr/share/tesseract-ocr/tessdata, or
>> 2) copy everything in
>> /usr/share/tesseract-ocr/tessdata to /home/linux/tessdata.
>>
> But this make my trainer GUI ask permission of user to copy
Hello,
I am a new member of this mailing list. I am creating a small project to read
electronic screens through OCR. In other words, we set up some equipment that
capture
the VGA output of computers and other devices, and converts the signal to RCA
composite, so I can take pictures and
Can anyone please reply or at least help me with this question? I want to
know if these files can help improve accuracy!
--
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
If there is other solution how to separate "must" part of the project with
"optional" data on github.com, please share it.
Zdenko
On Wed, Aug 17, 2016 at 3:32 PM, John Muccigrosso
wrote:
> On Wednesday, August 17, 2016 at 3:54:29 AM UTC-4, zdenop wrote:
>>
>> tesseract
On Wednesday, August 17, 2016 at 3:54:29 AM UTC-4, zdenop wrote:
>
> tesseract library/engine[1] is separated from language trained data[2].
> Main reason for this split is size of trained data and users need only
> few of them.
> Trained data should be placed to the same tessdata directory where
Are you sure you set variable correctly? Can you post your test case?
If you use C++ - have a look at GetThresholdedImage[1]
[1]
https://github.com/tesseract-ocr/tesseract/blob/master/api/baseapi.h#L385
Zdenko
On Wed, Aug 17, 2016 at 2:01 AM, Dimitry Kovalev
wrote:
>
Can I use it for whole word or only for each symbol?
среда, 17 августа 2016 г., 2:29:32 UTC+3 пользователь Quan Nguyen написал:
>
> Try ChoiceIterator API.
>
> On Tuesday, August 16, 2016 at 6:51:03 AM UTC-5, Sergei Turko wrote:
>>
>> Hi. Is there any kind of voting? Can I get recognition variant
7 matches
Mail list logo