Hi, everyone,Dose tessrect- ocr can output confidence level of the result?
I need not only a character but also a confidence level value. Dose anybody
knows? thank you
--
You received this message because you are subscribed to the Google
Groups tesseract-ocr group.
To post to this group, send
hello~guys...I need your help.
I am trying to train a new langage data, but when I was making box for a
bmpFile,Empty Page!! come.
I don't know why this happened...It puzzle me for a long time.
I found if 1 appears,the problem comes, and if not, everyting is fine.by
the way , 1 is a number.
--
If you build using the latest source
(r806http://code.google.com/p/tesseract-ocr/source/detail?r=806),
you'll get the word confidence in the hOCR output.
On Monday, November 12, 2012 1:54:34 AM UTC-6, lirong wrote:
Hi, everyone,Dose tessrect- ocr can output confidence level of the result?
I
The Powershell script train.ps1 on AddOns page can help automate the
training process.
http://code.google.com/p/tesseract-ocr/wiki/AddOns
On Tuesday, May 17, 2011 2:08:53 AM UTC-5, Eyal wrote:
Hi,
I tried to train some letters when I ran the *mftraining *with the
parameters*:*
Hi,
On Friday, November 2, 2012 1:25:22 PM UTC+1, Rong Xiao wrote:
hi,I have tried tesseract-ocr on chinese,but I found that it can do well
on only few fonts. I want to know what kind of fonts are included
in chi_sim.traineddata?
I'm also interested in this information (which fonts has it
Oh, sorry. I use tesseract 3.0.2, win7 32bit. Processing that I did:
1. Generate Training Images: eng.timesitalic.exp0.tif
2.Make Box Files: tesseract eng.timesitalic.exp0.tif
eng.timesitalic.exp0 batch.nochop makebox
3.Bootstrapping a new character set:
tesseract
What kind of your bmpFile? bmpFile must is *.tif
--
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 from this group, send email to
On Mon, Nov 12, 2012 at 3:23 PM, Mi Tran nuon...@gmail.com wrote:
What kind of your bmpFile? bmpFile must is *.tif
This is not true - it can be any image type supported by leptonica.
--
Zdenko
--
You received this message because you are subscribed to the Google
Groups tesseract-ocr
check also error messages - if you did not run shapeclustering then
mftraining should not produce any output (in 3.02 version) ;-) Also it
looks like you forget to rename output files from training tools!
You need to follow training wiki[1]!
[1]
I'd be grateful if someone could help me here.
Here is my request to Zdenko and the reply.
Could you perhaps help me understand, and then change the page, the
meaning of:
A quick check is to count the pixels of the x-height of your characters.
(X-height is the height of the lower case x.)
Measure the height of a lower case 'x' in your image using an image
program, such as Gimp or the standard image viewer on your platform (such
as Windows Paint or Mac Preview).
If the height of a lower-case 'x' in your text is less than 20 pixels, you
need to resize it or rescan your documents.
leptonica is tool support training?
Vào 22:38:58 UTC+7 Thứ hai, ngày 12 tháng mười một năm 2012, zdenop đã viết:
On Mon, Nov 12, 2012 at 3:23 PM, Mi Tran nuo...@gmail.com
javascript:wrote:
What kind of your bmpFile? bmpFile must is *.tif
This is not true - it can be any image type
Does anyone here use FreeOCR? I downloaded FreeOCR V3 a while ago and was
happy with it. Then I saw that there was version 4.2, so I thought that
would be even better, but Tesseract V3 that comes with it doesn't work as
well as the version included with FreeOCR V3 (at least with the current
Does it take a while to show up or is it lost in the 'pipes' of the
Internet?
--
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 from this group, send email to
cheers
that was easy!!
many thanks
I wonder if Z will now change the FAQ to tell ppl to use an image
program to do the measuring?
Cheers
kevin1mccre...@gmail.com
32 Hawera Rd
Kohimarama 1071
Auckland, New Zealand
+64 (0)9 528 1174 home
+64 (0)226 710 335 cell
http://kmccready.wordpress.com
Your image appears to be only 96 dpi, try using an image at a higher dpi
On Sunday, November 4, 2012 9:00:51 PM UTC-5, Rong Xiao wrote:
https://lh3.googleusercontent.com/-gwRhWSanaHo/UJcdfs8hiSI/ABQ/8jlKa2ZypFs/s1600/chi_test4.jpg
such as this image.it 's not very complex.
On
在 2012年11月12日星期一UTC+8下午10时23分26秒,MiT写道:
What kind of your bmpFile? bmpFile must is *.tif
I have tried a *.tif file, but it didn't work.Any suggestion?
--
You received this message because you are subscribed to the Google
Groups tesseract-ocr group.
To post to this group, send email to
As far as I know this list is moderated e.g. your first post should be
approved by moderator... But I am not familiar with details (I am not
moderator ;-) )
--
Zdenko
On Mon, Nov 12, 2012 at 8:27 PM, Random Terrain
replayabil...@randomterrain.com wrote:
Does it take a while to show up or is
If you are serious about your training project, please invest your time to
read wiki (once again if necessary). It is there.
--
Zdenko
On Tue, Nov 13, 2012 at 1:20 AM, Mi Tran nuon...@gmail.com wrote:
Thanks zdenop , I have ran shapeclustering and read training wiki. But it
still has error.
Leptonica is library that handle images for tesseract.
--
Zdenko
On Tue, Nov 13, 2012 at 1:36 AM, MiT nuon...@gmail.com wrote:
leptonica is tool support training?
Vào 22:38:58 UTC+7 Thứ hai, ngày 12 tháng mười một năm 2012, zdenop đã
viết:
On Mon, Nov 12, 2012 at 3:23 PM, Mi Tran
20 matches
Mail list logo