Please contact Quan Nguyen "nguyenq" , developer of
viet softwares. http://vietocr.sourceforge.net/developers.html
cheers,
sriranga(78yrs)
On Fri, Apr 15, 2011 at 6:58 AM, Max Cantor wrote:
> I see that there seems to be a lot of interest in tesseract in vietnam. I
> am close by in singapore an
I see that there seems to be a lot of interest in tesseract in vietnam. I am
close by in singapore and make heavy use of it too. I was wondering, do you
have a users group there? Is there a group of engineers sitting around looking
for freelance jobs perhaps? In any case, I think we should at
It is a trained data. You can try to use it to recognize the document.
You need to train the system if the performance is not satisfied.
On Apr 14, 3:37 am, Justin Woo wrote:
> Dear fellows of group tesseract:
> I'm a beginner using tesseract, and I've noticed that the
> tesseract 3.0 are
I now code the image as raw binary image and the error disappear.
However, the output is totally wrong. Strangely, if I directly call
"tesseract image.tif result -l eng" from command line, the result is
correct.
Here is my few lines of code:
tesseract::TessBaseAPI api;
api.Init(NULL, "eng");
//co
Hi All,
Pursuing my ongoing work on trying to develop a postal
address recognizer , I was excited to discover the implementation of
CUBE mode and especially the thought that it might be used to
incorporate some language modelling techniques along with tesseract.
I believe that one
Version 0.2 Release:
- Add a provision to set font for the Box Coordinates table
- Incorporate a pangram into the Font dialog
http://sourceforge.net/projects/vietocr/files/
On Apr 10, 8:01 am, Quan Nguyen wrote:
> jTessBoxEditor is a box editor for Tesseract OCR data, providing
> editing of box
I noticed it is in TessBaseAPI::Recognize
int TessBaseAPI::Recognize(struct ETEXT_STRUCT* monitor) {
//...
if (thresholder_ == NULL || thresholder_->IsEmpty()) {
tprintf("Please call SetImage before attempting recognition.");
return -1;
}
//...
}
My input image is coded binary, sing
I block the Recognize but still get the same error. Other comments?
On Apr 14, 5:23 am, Leonardo Gomes wrote:
> I'm a newbie with Tesseract, but I know that api.GetUTF8Text() calls
> Recognize for you. Try removing the call to Recognize to see what happens.
>
> Cheers,
> Leo.
>
>
>
>
>
>
>
> On T
zdenko podobny wrote:
> On Wed, Apr 13, 2011 at 2:31 AM, caudex wrote:
>
>> After using regedit and pointing tessdata_prefix to the right place
>> and running again I got an error that referred to unicharset. The
>> entire contents of my tessdata subdirectory is:
>>
>> Directory of C:\tesseract\
I'm a newbie with Tesseract, but I know that api.GetUTF8Text() calls
Recognize for you. Try removing the call to Recognize to see what happens.
Cheers,
Leo.
On Thu, Apr 14, 2011 at 7:58 AM, zl2k wrote:
> hi, all
>
> I have composed a Pix image and here are the 4 lines of code to
> recognize the
hi, all
I have composed a Pix image and here are the 4 lines of code to
recognize the input image (I am using tesseract 3.00)
tesseract::TessBaseAPI api;
// construct pix_image
api.SetImage(pix_image);
api.SetRectangle(0, 0, pixGetWidth(pix_image),
pixGetHeight(pix_image));
api.Recognize(NULL);
s
Dear fellows of group tesseract:
I'm a beginner using tesseract, and I've noticed that the
tesseract 3.0 are much more languages supportable including Chinese.
But it seems that for recognizing new language, I must train it myself
using Box Files and blabla which is a really tough task for
On Wed, Apr 13, 2011 at 2:31 AM, caudex wrote:
> After using regedit and pointing tessdata_prefix to the right place
> and running again I got an error that referred to unicharset. The
> entire contents of my tessdata subdirectory is:
>
> Directory of C:\tesseract\Tesseract-OCR\tessdata
>
> 04/0
13 matches
Mail list logo
