ARABIC Language support to OCR Tesseract plugin.

Discussions about machine vision support in GdPicture.
Post Reply
britnis
Posts: 18
Joined: Tue Sep 02, 2008 12:47 pm

ARABIC Language support to OCR Tesseract plugin.

Post by britnis » Mon Feb 22, 2010 1:24 pm

Hello Loic,

We are in the event of evaluating the Gd Picture Pro OCR tesseract plugin. We have performed evaluation on recognizing images and documents in English. We are very much pleased with the engines performance.

But our business requirement is that, support to Arabic language is mandatory as we focus on the Middle-East for future projects. Can you please inform me, if Arabic language support is available for OCR recognition using Gd Picture Pro OCR tesseract plugin.

If support to Arabic is not available, can you please suggest me with a work around to this.

Regards,
Nirmal Lawrence

User avatar
Loïc
Site Admin
Posts: 5881
Joined: Tue Oct 17, 2006 10:48 pm
Location: France
Contact:

Re: ARABIC Language support to OCR Tesseract plugin.

Post by Loïc » Wed Feb 24, 2010 1:13 pm

Hi we don't yet support Arabic language .
We have plans to introduce it but today i am unable to give a date of release.

With best regards,

Loïc

punitharaj
Posts: 2
Joined: Mon Jun 11, 2012 4:32 pm

Re: ARABIC Language support to OCR Tesseract plugin.

Post by punitharaj » Mon Jun 11, 2012 6:33 pm

hi
I am Using GDPicture V 8.5.0.32 . Could you kindly inform me whether this version will Support Arabic OCR or not.

Regards
Punith

User avatar
Loïc
Site Admin
Posts: 5881
Joined: Tue Oct 17, 2006 10:48 pm
Location: France
Contact:

Re: ARABIC Language support to OCR Tesseract plugin.

Post by Loïc » Mon Jun 11, 2012 6:35 pm

Yes it is now supported.

Regards,

Loïc

punitharaj
Posts: 2
Joined: Mon Jun 11, 2012 4:32 pm

Re: ARABIC Language support to OCR Tesseract plugin.

Post by punitharaj » Tue Jun 12, 2012 8:48 am

Thanks for your reply. My problem is when I use arabic traineddata in my c# coding I get
an error which says " An unhandled Exception of type 'System.AccessViolationException' Occured in GdPicture.NET.dll".

I use the below code to create searchable pdf using gdpicture method

oGdPictureImaging.PdfOCRCreateFromMultipageTIFF(MultiPageID, "ara", GlobalVaribles.gGDPOCRPath, "", gpath.ToUpper().Replace(".TIF", ".PDF"), false, "a", "b", "c", "d", "e");

The same coding works fine for other languages. kindly guide me to come out from this issue.
Attachments
arab_error.jpg
Error Screen Shot attached for your reference ...

User avatar
Loïc
Site Admin
Posts: 5881
Joined: Tue Oct 17, 2006 10:48 pm
Location: France
Contact:

Re: ARABIC Language support to OCR Tesseract plugin.

Post by Loïc » Tue Jun 12, 2012 10:08 pm

Hello,

Please send the input image to the support team through the helpdesk located here: https://www.gdpicture.com/support/getting-support-from-our-team

we are doing investigation about the Arabic language support of the OCR.

Kind regards,

Loïc

lguijarro
Posts: 4
Joined: Fri Mar 05, 2010 1:42 pm

Re: ARABIC Language support to OCR Tesseract plugin.

Post by lguijarro » Fri Oct 19, 2012 11:15 am

Hello,
I'm trying to use Arabic OCR on some images but the results of OCR are always blank text. What i'm doing wrong?

I'm using the sample project of vb.net to OCR extraction and i put "ara" on the language textbox. I have the OCR language pack downloaded from https://www.gdpicture.com/download/ocr_language_pack.zip.

thanks in advance

User avatar
Loïc
Site Admin
Posts: 5881
Joined: Tue Oct 17, 2006 10:48 pm
Location: France
Contact:

Re: ARABIC Language support to OCR Tesseract plugin.

Post by Loïc » Sun Oct 21, 2012 9:56 pm

Hello,

Are you using the latest release?


Kind regards,

Loïc

lguijarro
Posts: 4
Joined: Fri Mar 05, 2010 1:42 pm

Re: ARABIC Language support to OCR Tesseract plugin.

Post by lguijarro » Wed Oct 24, 2012 9:10 am

Hello Loïc.
I'm using the 8.5.0.33 release version.

regards.

Post Reply

Who is online

Users browsing this forum: No registered users and 1 guest