Thanks, TP,
As I mentioned in another thread regarding unicharambigs, many times the
OCRed text does not match ground truth, even when the BOX file was
generated using the same text and trained with it. As far as I can figure
out, it seems to be related to chopping of the word.
Many times, I am a
Matt,
I am also facing similar issues with unicharambigs. I have found it helpful
to look in the unicharset file. Some times the values being recognized are
not what was put in the box file and looking at the unicharset helps
identify them.
In fact there are times when I have had to define the ch
Thanks for the information Nick.
I tried my experiment and used the unicharambigs file to turn all my
ligatures into modern character equivalents. It did not substantially
improve the dictionary lookup results. I'll have to try increasing my
confidence in the dictionary using the parameters tha
On Tue, May 7, 2013 at 6:11 AM, sdk wrote:
> My question is, can that setup be used to trace the program flow or see
> how the processing is being done.
Yes, but why do you ask. Are you having problems?
You might have to also compile leptonica, if you want to step into its
functions.
The mai
Hi,
I installed VS 2008 Express edition and installed the Tesseract 3.02
project in it based on the instructions given in
http://tesseract-ocr.googlecode.com/svn/trunk/vs2008/doc/setup.html
The instructions were very clear and easy to floow and I have built
Tessearct using that.
My question
Hi Matt,
> I'm also not sure how these two files are different, or if maybe DangAmbigs is
> from an earlier version of Tesseract or something. I'm using 3.02.
Yes, that guess was correct. unicharambigs used to be called DangAmbigs
before Tesseract 3. That is mentioned at:
http://code.google.com/
Hi,
I am trying to get scrollview to show up on win7. I am getting the error:
Starting java -Xms512m -Xmx1024m -Djava.library.path=C:\Program Files
(x86)\Tesseract-OCR\java -cp C:\Program Files (x86)\Tesseract-
OCR\java/ScrollView.jar;C:\Program Files
(x86)\Tesseract-OCR\java/piccolo-1.2.jar;C:\
Andres,
Your code seems to be correct. I personally use a few more lines right
after the call to GetIterator():
it->Begin();
if(it->IsAtFinalElement(RIL_BLOCK, RIL_SYMBOL))
return;
if(!it->IsAtBeginningOf(RIL_SYMBOL))
return;
But this shouldn't bother you if you rely on
8 matches
Mail list logo