|
From: | Antonio Diaz Diaz |
Subject: | Re: [Bug-ocrad] German OCR, etc. |
Date: | Wed, 18 Jan 2006 17:17:50 +0100 |
User-agent: | Mozilla/5.0 (X11; U; Linux i586; en-US; rv:1.7.3) Gecko/20040913 |
Hello Ray.I have no plans to support the eszet (ß) anytime soon, but perhaps a German programmer could contribute the code to recognize it.
On the other hand, ocrad does recognize umlauts (dieresis, look the examples/test.pbm file). If you have a document with umlauts that ocrad is unable to recognize, please, send it to me (no to the list), and I'll try to fix the problem.
Best regards, Antonio Diaz. Ray wrote:
I am a student seeking to OCR some German documents. Although ocrad has excellent recognition for English characters (with the exception of W, 1, and 7 in my document) it is unable to recognize eszets (ß) or characters with umlauts. Could support for the ß, ä, ö, and ü be added?
[Prev in Thread] | Current Thread | [Next in Thread] |