red images but when i tried it
> for black and white background accuracy was not appropriate for that
> also.Is there any condition for size,color,font for images that i
> should use to get proper accuracy or there is some any other reason??
> I am using it for iphone.
>
> On Mar 7, 4:
Hi,
On which images you are trying to recognize the text?? What is your
application??
Sandeeep
On Wed, Mar 7, 2012 at 3:34 PM, swati sharma wrote:
> Hi
>
> I have tried Tesseract Ocr codes but they are not giving a proper
> accuracy.What can be the reason for it??
> I am using an updated lepto
you can whitelist ur required characters i.e numbers or alphabets by doing
dis in tesseractmain.cpp
*api.SetVariable("tessedit_char_whitelist", "0123456789. ");*
*
*
*then tesseract wil only choose numbers to perform recognition.*
*
*
*Regards*
*Sandeep
*
On Thu, Oct 13, 2011 at 10:28 PM, Sven Ped
Zoom ur image and check whether the character 'I' and 't' are joined or not.
I guess pixels of both characters are joined thats why Tesseract spells it
'H'.
Please confirm
Regards
Sandeep
On Tue, Oct 4, 2011 at 2:53 PM, merve t wrote:
> Hello,
> I think my problem is related to this.
> But a l
Hi Top Contributors of Tesseract,
Can any one help me out for this problem
Regards,
Sandeep
-- Forwarded message --
From: Sandeep Parmar
Date: Wed, Sep 21, 2011 at 3:34 PM
Subject: Issue in while doing char by char recognition of text
To: tesseract-ocr@googlegroups.com
Dear
Dear all,
I have written an application on top of Tesseract and I am calling
'api.getUTF8text()' with whitelisting all uppercase alphabets.
I was performing char by char recognition and I frequently got the following
two mistakes
1) Alphabet B was recognised as E
2) Alphabet M was recognised as
Dear all,
I successfully created my 'eng.traineddata' by referring the training
guidelines on tesseract site. I am getting pretty good results with the
fonts I added to my training set.
However I was not getting good results for some images so I searched for
that particular font type on net & add
TA_PREFIX" environment variable. By default it points to
> "C:\Program Files\Tesseract-OCR\"
>
> Warm regards,
> Dmitri Silaev
> www.CustomOCR.com
>
>
>
>
>
> On Tue, Aug 30, 2011 at 8:31 AM, Sandeep Parmar
> wrote:
> > Dear all,
> > Can a
Dear all,
Can anybody tell why eng.traineddata file is to be placed in "C:\Program
Files\Tesseract-OCR\tessdata\" folder only.
I want to change the location of eng.traineddata file. How can I do that?
Regards
Sandeep
--
You received this message because you are subscribed to the Google
Group
Hi,
which tesseract version you are using?
Sandeep
On Fri, Aug 5, 2011 at 5:21 PM, Chitra Sharavanan <
chitra.sharava...@gmail.com> wrote:
> lower case l is recognized as forward slash (/)
> eg., Places -> P/aces
> but the word location does not have any issues
> location -> location
>
> --
> Y
Dear all,
can anyone tell me which fonts are included in 'eng.traineddata' of
tesseract 3.01?
Regards
Sandeep
--
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 unsubscribe fr
hi Zdenko,
Thanks for your reply. Actually i got my mistake on the very next instance
when i posted this query.
Now its working fine. :)
Thanks
Sandeep
On Sat, Jul 30, 2011 at 1:50 PM, zdenko podobny wrote:
>
>
> On Sat, Jul 30, 2011 at 6:43 AM, Sandeep Parmar <
> sandeep.thea
Deal all,
I am getting following error while training the Box files
"read_params_file: parameter not found: tessedit_use_nn"
What could be the reason for this error? I tried searching the answer on
forum but it didnt worked.
Please help.
Thanks and regards
Sandeep
--
You received this messag
ul 28, 2011 at 5:32 PM, zdenko podobny wrote:
>
>
> On Thu, Jul 28, 2011 at 12:16 PM, Sandeep Parmar <
> sandeep.theart...@gmail.com> wrote:
>
>> Hi Zdenko,
>>
>> these results are very much similar to the one which i got using older
>> version(tess
00 and
> it gave me similar result as r596 (yes there are differences).
> What OS you use?
>
> Zdenko
>
> On Thu, Jul 28, 2011 at 10:11 AM, Sandeep Parmar <
> sandeep.theart...@gmail.com> wrote:
>
>> hi zdenko/sriranga,
>>
>> please find the zipped folder a
boxer?
>
>
> On Thu, Jul 28, 2011 at 12:26 PM, Sandeep Parmar <
> sandeep.theart...@gmail.com> wrote:
>
>> Hello Everyone,
>>
>> I downloaded the latest tesseract 3.01 from the svn and was trying to
>> train the tesseract for new fonts.
>>
>&g
Hello Everyone,
I downloaded the latest tesseract 3.01 from the svn and was trying to train
the tesseract for new fonts.
I created the box files by following the command
"tesseract [lang].[fontname].exp[num].tif [lang].[fontname].exp[num] -l
yournewlanguage batch.nochop makebox "
given on trainin
Hello everyone,
I am using the following code snippet, within this I would like to know
whether 'GetUTF8Text' will destroy my source image 'arr_image' or not
after performing recognition.
*api.SetImage((const unsigned char*)arr_image[loop_index3],*
* **width[loop_index3],*
* **height[loop
Hello everyone,
I was trying to use tessdll project to create a dll out of tesseract (using
Visual Studio 2008) which I further plan to use in my application which is
compiled on GCC (under mingw). I understand that it has been mentioned in
one of the ReadMe pages that the current tessdll project
Hi,
Which visual studio you have? VS2006/VS2008 ? In tesseract source folder,
there is folder named 'VS2008' which has the 'tesseract.sln' file created in
Visual Studio 2008. Try that.
Regards,
Sandeep
On Mon, Jul 18, 2011 at 12:24 PM, Saqib wrote:
> I am all new to Tesseract, I cant even start
e procedure from the link
> http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3 and
> that's it.
> Hope, it will help you...
>
> -haydar
>
> On Jun 24, 7:14 am, Sandeep Parmar
> wrote:
> > Hi all,
> >
> > I am evaluating tesseract for my pr
Hi all,
I am evaluating tesseract for my project and I found that its very good
compared to other free OCRs. However I have some
doubts regarding Training Tesseract 3.0 for new font types.I did two things
while training tesseract..
1) I made a text document containing all the Alphabets, numbers a
Hi all,
I am evaluating tesseract for my project and I found that its very good
compared to other free OCRs. However I have some
doubts regarding Training Tesseract 3.0 for new font types.I did two things
while training tesseract..
1) I made a text document containing all the Alphabets, numbers a
23 matches
Mail list logo