[Spambayes] date for new release to handle image spam?

David Abrahams dave at boost-consulting.com
Fri Jan 5 16:21:50 CET 2007

"Seth Goodman" <sethg at goodmanassociates.com> writes:

> David Abrahams wrote on Thursday, January 04, 2007 11:46 AM -0600:
>> I've got the OCR stuff enabled on Unix.  It definitely works some of
>> the time; in X-SpamBayes-Evidence I can see spam words picked out of
>> the image that don't appear elsewhere in the message.  There is a
>> category of those stock advertisements that seems to be getting past
>> the OCR completely; one example is enclosed.  I wish I knew what to do
>> to get around that problem.
> Image spam is gradually moving in the direction of a captcha:  images
> that people can identify but computers can't.  How far they can go
> before it becomes so annoying that no one will look at it is anyone's
> guess.  As long as people can design effective captcha's, it will be
> possible to construct image spam that OCR will not detect.

Yes, I understand the principle.  Of course, the effectiveness of
captchas depends on the ineffectiveness of OCR.  On the other hand,
most OCR is built to deal with reasonably legible text, so we may need
spam-specific OCR tools.

Dave Abrahams
Boost Consulting

More information about the SpamBayes mailing list