You welcome !!!
On Sun, Sep 22, 2013 at 11:25 PM, clyde wrote:
> Thank You Oleg and Zdenko!
>
> I am able to solve my problem. I just repeat the procedure in
> https://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3#font_properties_(new_in_3.01)
> .
> Thank you so much!!!
>
> --
> --
>
Thank You Oleg and Zdenko!
I am able to solve my problem. I just repeat the procedure in
https://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3#font_properties_(new_in_3.01)
.
Thank you so much!!!
--
--
You received this message because you are subscribed to the Google
Groups "tesser
On Sun, Sep 22, 2013 at 9:35 PM, clyde wrote:
> Hello again Oleg,,
>
> i am able to create korLang.traineddata, but when I try to use the
> traineddata file I created
> command: tesseract korLang.font1.exp1.tif output -l korLang
>
> I got this error:
> tessdata_manager.SeekToStart(TESSDATA_INTTEM
Hello again Oleg,,
i am able to create korLang.traineddata, but when I try to use the
traineddata file I created
command: tesseract korLang.font1.exp1.tif output -l korLang
I got this error:
tessdata_manager.SeekToStart(TESSDATA_INTTEMP):Error:Assert failed:in file
..\..
\classify\adaptmatch.c
Hi,
First of all please read the wiki of the tesseract. There is a quite good
explanation how to do this.
If it's not enough, you can refer to
http://misteroleg.wordpress.com/2012/12/19/ocr-using-tesseract-and-imagemagick-as-pre-processing-task/
.
Hope it helps.
On Sun, Sep 22, 2013 at 3:33 P
Hello Oleg,
Could you please post the Steps that you did to train Tesseract OCR with
Korean text.
I am hoping for your response. Thank you in advance!
--
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to te
Hi guys,
Finally, the problem was with cygwin, somehow it installed tesseract 2.x
(couple of libraries) and linked to the tesseract 3.0. Probably it mixed up
and disturbed to work correctly. I uninstalled all cygwin packages,
installed MS VS Studio 2008 Express instead, svn-ed tesseract 3.0.1, bu
Interesting
I used cygwin, windows 7.
Generally, I installed leptonika and its dependencies, after that I
installed tesseract 3.0 from the archive file.
./runautoconfig
./configure
make
make install
I checked the config_auto.h ->
/* Version number */
#define PACKAGE_VERSION "3.00"
/* Offic
Looks like you're running Tesseract 2.0x version, which does not
support Oriental scripts. Download, install Tesseract 3.01 and try
training again.
On Apr 29, 7:09 am, Oleg Tikhonov wrote:
> Here is a command and the error/message
>
> $ tesseract.exe ../korean_training/annyong_eng.png
> ../korean
Oleg,
Are you sure with message? "tesseract.exe" indicate that you are using
Windows... (I am not aware that any official linux build system create
'tesseract.exe') But part error message ('/usr/share/tessdata/') indicates
that you are in linux (or unix like) environment...
You wrote that you ins
Zdenko,
Honestly, I did not read a whole page, beg your pardon.
Here is a command and the error/message
$ tesseract.exe ../korean_training/annyong_eng.png
../korean_training/annyong_eng.png -l kor batch.nochop makebox
Unable to load unicharset file /usr/share/tessdata/kor.unicharset
Thanks,
--
Zdenko, Quan and Sven,
Thanks a lot for your suggestions, I think you nailed the problem,
So, I installed the Korean language pack :-) however an archive has only one
file - kor.traineddata.
It doesn't have kor.unicharset, it causes a problem that during "loading"
kor.traineddata, tesseract also de
Hi Oleg,
As Quan said, you need a higher resolution image, about 200--300 dpi
and it needs to be binary (black&white) not grayscale or color.
Screenshots are typically only 72 -- 90 dpi. I see that the wiki says
the character size in pixels in a confusing way.
--Sven
2011/4/28 Quan Nguyen :
> Pri
Print screens are, in general, not adequate for training new
languages. You'd be better off using GIMP to produce your TIFF images.
Be sure to specify the language to bootstrap the new charset, such as:
$ tesseract.exe ../korean_training/kor.ariel.exp1.tif ../
korean_training/kor.ariel.exp1 -l kor
Hi Sven,
Here is what I've done:
1. Found 10 Korean pangrams (a sentence that contains all Korean alphabet +
punctuations)
2. Opened notepad++ and pasted line by line each pangram mixed up with
punctuation, changed encoding to utf8, increased the font size to 12pxl,
formatted a whole text that
On Thu, Apr 28, 2011 at 6:03 PM, Oleg Tikhonov wrote:
> Hi guys,
>
> I've installed tesseract-ocr 3.0 on Windows 7. All work fine if selected
> language is English.
> I tried to add/teach the system the Korean. The first step was creating
> sample of data, I created some tiff files with Korean in
The generated box will not contain Korean characters. Use any box editors
mentioned in training page. Box editors are created for that purpose. Box
editors will split the image blocks from tif provided, and create a
rectangle area and asigns some value to it. Adjust the size of these
rectangles in
Hi Oleg,
Did you create a file with mapping of character codes? Or Korean text
file that you printed and scanned in? Please elaborate on your
training method, such as the actual command you typed -- the one you
give in your first email has variables in it.
--Sven
On Thu, Apr 28, 2011 at 11:23 AM,
It's exactly where I'm started and stuck. The produced box does not contain
any Korean character only Latin ones. And that is a problem.
On Thu, Apr 28, 2011 at 7:08 PM, Sriranga(78yrsold) wrote:
> please read wiki on tesseract3 wherein details how to train lang
>
> On Thu, Apr 28, 2011 at 9:33
please read wiki on tesseract3 wherein details how to train lang
On Thu, Apr 28, 2011 at 9:33 PM, Oleg Tikhonov wrote:
> Hi guys,
>
> I've installed tesseract-ocr 3.0 on Windows 7. All work fine if selected
> language is English.
> I tried to add/teach the system the Korean. The first step was cr
20 matches
Mail list logo
