On Fri, 30 Sep 2011, merve t wrote:
again My question is should not the installation distribute headers into
usr/include directory???
Generally, external packages built from sources get installed into
/usr/local or /opt by default. That way they survive system upgrades
without being partially
Hi Robert,
How do I get an efficiency and speed of recognizing text through OCR
like your app? Did you mix up a lot of libraries? is it achievable
through tesseract android tools alone?
I am just trying to obtain a string through OCR but not translate it
and instead send it to a server for further
On Fri, Sep 30, 2011 at 6:20 PM, merve t wrote:
> Hello,
> I installed tesseract-ocr software on ubuntu linux by downloading from svn
> and compiling and making and installing.
> Now i am looking at /usr/include directory and can not see tesseract
> related headers.
>
> You should not look at "/u
Hello,
I installed tesseract-ocr software on ubuntu linux by downloading from svn
and compiling and making and installing.
Now i am looking at /usr/include directory and can not see tesseract related
headers.
Also when i try to compile a source file of mine which includes headers of
tesseract, i g
First, I have generated a trained data, saw no errors, use the trainned data
and get good results.
Then using different tif images, i generated a multipage tif using
imagemagick but in mftraining it gives the error.
After that i have tried to generate a train data using multipage tif pages
as si
That's not what tesseract is for.
On 09/30/2011 04:22 AM, Togu Muara wrote:
Hi all,
Sorry if report.
I wanna know, does tesseract has the ability for converting TIF to
PDF?
Thank you very much
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group
tesseract try to convert image to txt or html/hocr.
I remember that there are some tools that use tesseract for adding text to
djvu. Just quick check with google brought this:
http://www.djvu.org/forum/phpbb/viewtopic.php?t=765
http://en.wikisource.org/wiki/Help:DjVu_files/OCR_with_Tesseract
http:
After some research, let me reply my own questions regarding methods:
@ http://tesseract-ocr.googlecode.com/svn/trunk/doc/tesseracticdar2007.pdf,
general flow chart is explained thoroughly, with method names.
However, I don't seem to be able to reach referenced documents, which
is a shame at my en
Hi Saurabh Gandhi :
It's been resolved as you suggested.
Thank you very much !!!
B.R.Aiqing Yu
在 2011-09-27 11:48:24,"Saurabh Gandhi" 写道:
By setting chop_enable as zero, we were able to disable the splitting of a
single character.
Not sure if that
Hello.
I am new in OCR, and now I got a problem.
I have got a program generated tiff image (white background without
noise, and not so regular font type).
The program generate this characters: ö ü , but lot's of time the
tesseract recognize: o and u. And lots of time the o and u charaters
recogni
Sriranga,
Quoting original poster of the post I've linked:
"This bug does NOT occur in the compiled windows exe which is provided
in the download section.
The bug occurs in the version r582 I took from the trunk & compiled.
I'm working on Windows 7 - Visual studio 2010
If I remove the first cha
you mean that by removing the first character (s.no:1 of the box file) from
the box file
or the last character(s.no:54 of the box file), which avoids the crash ?.
On Fri, Sep 30, 2011 at 1:34 PM, Calomer wrote:
> Merve,
>
> Do you receive the error when you train again, or when you are using
>
Merve,
Do you receive the error when you train again, or when you are using
the trained file?
Which version are you using ?
Did you try to use your (successful) trained file ?
I have bumped into an old problem like yours on
http://code.google.com/p/tesseract-ocr/issues/detail?id=490. Official
p
Hi all,
Sorry if report.
I wanna know, does tesseract has the ability for converting TIF to
PDF?
Thank you very much
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to tesseract-ocr@googlegroups.com
To unsubsc
Sven,
Now I'm curious. What kind of tweaks are you talking about ?
Appending old language training data with new fonts?
Pre-enhancement of the image (skew transformation on italic
characters, contract enhancement on low-contrast fonts etc) ?
I'd love to know any other tweaks there is.
Thanks
O
15 matches
Mail list logo