Thank you Don for the comments.
On Tue, Feb 8, 2011 at 4:06 PM, SpeedyChair wrote:
> Another way to prepare a PDF document for tesseract is to use the 'convert'
> command from the ImageMagick package to split an image only PDF file into a
> series of GrayScale TIFF images, one for each page. Th
If you used tesseract 2.04, you should have a look at tessdll\tessdll.cpp.
>From tesseract 3.x, orcshell.h/.cpp have been removed. So you need to do
backward.
I try to do the same on my project, hope it releases soon.
Cong.
From: tesseract-ocr@googlegroups.com [mailto:tesseract-ocr@
Dear Jon,
Beginning for analyzing; I try also to detect lines, corners; but results
are not good. I think due to images are low contrast.
Please try to analyze with some data line profiles:
ROI-left-profile:
https://picasaweb.google.com/congnguyenba/TesseractBasedOCR#5576706091073985
3
Dear Andres,
The recognition results which I showed, have achieved after I had used my
simple tesseract engine 3.01 .net wrapper (link here:
http://code.google.com/p/tesseractdotnet/).
ROI detection is cropping ROI manually, after that I used my company
software to filter.
About filteri
VietOCR.NET is a VS2008-based C# project that uses tessnet2. Its
source can be found at:
http://sf.net/projects/vietocr
Good luck.
On Feb 10, 11:54 am, Seena Anup wrote:
> Hi,
>
> I downloaded Tessnet2 binary from this
> pagehttp://www.pixel-technology.com/freeware/tessnet2/
>
> I tried execut
VietOCR.NET is a VS2008-based C# project that uses tessnet2. Its
source can be found at:
http://sf.net/projects/vietocr
Good luck.
On Feb 15, 12:49 am, noobsaibot wrote:
> Hi guys i am a C# developer and working tirelessly on some projects
> which require tessnet integration.but unfortunate
Vicky,
I may be able to convert your local-minima code to OpenCV code; can you send
me the result files as well as the filter?
I wrote some Python code that uses OpenCV to crop the headstone images to
show just the stone. Its not perfect, but it works OK. The Hough algorithm
and the other corne
I've successfully created a box file with tesseract
now after running the unicharset_extractor
having it creating the unicharset file that looks like:
...
n 3 NULL -1
s 3 NULL 23
t 3 NULL 43
...
I've continued with this command
mftraining -U unicharset -O testlang.u
Hello,
A few comments from my side, sorry for being disordered, but I have not much
time right now.
In OpenCV you can use thresholding with the Otsu algorithm, it’s not
documented in the documentation of the threshold function, but the parameter
is CV_THRESH_OTSU.
Otsu thresholding involves the
On Feb 20, 9:02 pm, Jon Andersen wrote:
> My project athttp://RecordAGrave.comis about recording headstones from
> graves and posting the text and images on the Net so that people can
> research their family history. I would appreciate some advice on how to
> pre-process these headstone images t
All three messages were received by the list. All Googlegroups mailing list
prevent the sender from receiving his own post back. They figure they never
fail and your own posts returning to you are not necessary. It confuses
many people.
Don Marang
Vinux Software Development Coordinator (vin
I do not have my own page built just for speedy-ocr at the moment. The Ubuntu
10.0.4 Lucid package is hosted on Launchpad in our Vinux Lucid PPA.
To add the Vinux Lucid repository to your system, type:
sudo add-apt-repository ppa:vinux/vinux-lucid
Then install speedy-ocr with the following
Dmitry,
unfortunately I have not enough of time for tests :-(. I still hope Ray will
release more info before final 3.01. At the moment I focus on box editor.
BR,
Zdenko
On Tue, Feb 22, 2011 at 9:27 AM, Dmitry Silaev wrote:
> Interesting. I was wondering about Cube since its traces began to
>
I might not understood you fully, but this is an obvious excerpt from
"baseapi.h":
"Each SetRectangle clears the recogntion results so multiple
rectangles
can be recognized with the same image"
Indeed, SetRectangle() calls ClearResults() which "deletes the pageres
and
clears the block list ready
Interesting. I was wondering about Cube since its traces began to
appear in the source code but had no enough time to investigate it
thorougly
Zdenko, would you please kindly share your other findings on Cube?
Regards,
Dmitry
On Tue, Feb 22, 2011 at 11:13 AM, zdenko podobny wrote:
> I doubt tha
I doubt that google will release their (full) training set :-(
Have a look at svn to file eng.cube.size [1]. You can see there name of
fonts that was training for English in 3.01. As far as I understood there is
(unpublished/not released) possibility to train language data directly on
font files.
16 matches
Mail list logo
