Re: Pattern recognition

From: Stephen Reed (
Date: Tue Oct 07 2003 - 12:09:29 MDT

On 7 Oct 2003, Perry E. Metzger wrote:

> Stephen Reed <> writes:
> > Cyc has three separate vocabularies for representing color, addressing the
> > issues raised by Ferrer i Concho and Sol. At one extreme is the concise
> > notions of ChristmasColors and HalloweenColors color schemes that utilize
> > fuzzy sets RedColor/GreenColor and OrangeColor/BlackColor. On the
> > other extreme is the RGB color vocabulary that defines a color in
> > terms of its measurements of Red, Green and Blue light.
> For most colors perceived by humans, there are two ways to generate
> the perceived color -- either by the use of varying intensities of
> red, green and blue light, or by using a single light of some given
> frequency. Thus, Cyc does not unambiguously describe colors even given
> what you are describing. :)

I do not understand your point. Is the color phenomenon ambiguous simply
because there are two methods of generation? Or if that is not the case
then I say that one of Cyc's RGB color representations is unambiguous
given its vocabulary for stating the intensity of the red, green, and
blue light that make up the perceived color.


Stephen L. Reed                  phone:  512.342.4036
Cycorp, Suite 100                  fax:  512.342.4040
3721 Executive Center Drive      email:
Austin, TX 78731                   web:
         download OpenCyc at

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:43 MDT