Re: Open Source OCR

[Bill Haneman <Bill Haneman Sun COM>]

Hi Folks:

I just downloaded, built, and tested this OCR engine.

It is really pretty good, and it was very easy to build.  At the moment 
it is a bit limited (requires TIFF format, 8 bit depth, and doesn't 
understand columns etc.) but the limitations don't seem to be in the 
engine, only in the bells and whistles.

I think it could prove to be very useful for certain accessibility 
applications.  Of course in a more perfect world we would not need to do 
OCR at all...

best regards,

Bill

Steve Lee wrote:
> It was noted at the Accessibility Summit, http://tinyurl.com/uqen3,
> that a high quality FOSS OCR is needed and I remember reading earlier
> that Google have OSed Tesseract.
>
> http://www.linux.com/article.pl?sid=06/09/18/191251
>
> It's on a Apache 2.0 License.
>
> -- Steve Lee
> www.oatsoft.org
> www.fullmeasure.co.uk
> _______________________________________________
> gnome-accessibility-list mailing list
> gnome-accessibility-list gnome org
> http://mail.gnome.org/mailman/listinfo/gnome-accessibility-list
>