On Aug 2, 2006, at 12:12 AM, Benny Pedersen wrote:

On Wed, August 2, 2006 06:11, John Rudd wrote:

white will produce (assuming 24bit color) f0,f0,f0  and black will
produce 00,00,00. Thus, you get a nice high-contrast image for feeding

just for clearness white is ff, ff, ff

yes, white is ff,ff,ff ... but after you drop the lower 4 bits, it's f0,f0,f0. That was what I was saying.


will it not be much faster just to make a md5 sum on the image file without
thinking if it a appel or orange ? :-)

Yes, but just taking a straight sum will be sensitive to all of those small pixels which are changed by the spammers so that they have different sums, but the differences aren't visible to the human eye.

That's my point. If you drop out the lower bits of the colors, then you mostly retain what is perceptible (in color ranges) to the human, while losing those parts that a) the human wouldn't have noticed anyway, and b) throw off your sum of the image for comparison to known spam images.

Reply via email to