Arabic-L:Arabic OCR

[Dilworth Parkinson]

------------------------------------------------------------------------
Arabic-L: Thu 01 Nov 2012
Moderator: Dilworth Parkinson <dilworth_parkinson at byu.edu>
[To post messages to the list, send them to arabic-l at byu.edu]
[To unsubscribe, send message from same address you subscribed from to
listserv at byu.edu with first line reading:
           unsubscribe arabic-l                                      ]

-------------------------Directory------------------------------------

1) Subject:GEN:Arabic OCR

-------------------------Messages-----------------------------------
1)
Date: 01 Nov 2012
From:Saqer Almarri <saqer.almarri at gmail.com>
Subject:Arabic OCR

I recently found out that Tesseract-OCR (which Google uses) supports
Arabic. See here: http://code.google.com/p/tesseract-ocr/ However,
this is just the engine, you can use it with OCRFeeder as a frontend
(available on Linux only, not available on Windows or Mac)
https://live.gnome.org/OCRFeeder

Tesseract works really well with English, but is still buggy with
Arabic. It's a step into the right direction, and considering both
Tesseract-OCR & OCRFeeder are opensource, those of you who work with
computational linguistics can contribute.

Regards,
Saqer

--------------------------------------------------------------------------
End of Arabic-L: 01 Nov 2012
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/arabic-l/attachments/20121101/492597de/attachment.htm>