Re: language options for hebrew

On Tue, May 29, 2012 at 6:56 AM, stephen234 wrote: > I have noticed after installing Tesseract 3.01 in Windows (with > the .msi installer) can you send me link to .msi installer? > that there are three .traineddata files for > Hebrew: heb.traineddata, heb-ras.traineddata, heb-seg.traineddata. A

Re: Different results for v3.01 and current code line

On Mon, May 28, 2012 at 8:18 PM, steve8918 wrote: > Hi, I'm finding a discrepancy between the results I get from version 3.01 > and the most current code in svn. > > I'm working on WinXP SP3 32-bit, and using Visual Studio 2008 (regular > version, not express). > > Using the tesseract-ocr-setup-3

language options for hebrew

I have noticed after installing Tesseract 3.01 in Windows (with the .msi installer) that there are three .traineddata files for Hebrew: heb.traineddata, heb-ras.traineddata, heb-seg.traineddata. All three of them seem to work as language options (i.e. "-l heb", "-l heb- ras", "-l heb-seg"). Can any

When will the tesseract-ocr v3.02 offical release ?

Hi all, I check out the v3.02 r729 from the svn trunk and build it, but I found that there are some new files in the build directory ex. ambiguous_words.exe & classifier_tester.exe, current now I'm very confused with these files, will the v3.02 training processing change ? I used my v3.01 tra

Different results for v3.01 and current code line

Hi, I'm finding a discrepancy between the results I get from version 3.01 and the most current code in svn. I'm working on WinXP SP3 32-bit, and using Visual Studio 2008 (regular version, not express). Using the tesseract-ocr-setup-3.01-1.exe from the main Tesseract page, I was able to install

Need help in html

Hi not sure this is the right place but it was all i could find, so i'm trying to use tesseract in webpage using javascript and html but i'm not sure what to use or how to call in that language. I was hopping if someone could help me, referal a tutorial or tell me what code to use to call tesseract

hindi ocr output comparison

hi, I am trying to figure out a way to see until what range the output i get from the ocr wen i give hindi text images. for instance यल: सब this is the output i get for this राष्ट्रपति चुनाव as input. i am stuck here and unable to move forward. how can i improve my output?? someone who has worked

Re: Tess3.01 hocr output not working with pdfbeads

Dn(a 26.05.2012 23:09, Galt wrote / napísal(a): > Worderful news, Zdenko! > >> Yesterday David Eger commit patch that should fix tesseract-ocr hOCR output >> to follow hOCR spec. > I wonder what he did? see [1] and [2]. And I did today r729... We tested output with pdfbeads (1.0.9) and ExactImage

Re: tesseract to handle images from the scanned document.

This is the way tesseract is used normally. We might be able to provide more help if you could post a specific image, what you tried to do with it and what happened. On May 28, 2012 12:11 PM, "christy" wrote: Is there a way tesseract can handle images from a scanned document? -- You received th

tesseract to handle images from the scanned document.

Is there a way tesseract can handle images from a scanned document? -- 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 tesseract-ocr+u