2 responses to ““It turns out color theory has a way of measuring interestingness: saturation.””

  1. Risukun says:

    That’s quite slick feature. I hadn’t thought explicitly about saturation as a measure of interestingness, but it’s certainly true much of the time. There should be a use for this knowledge in selecting interesting photos to present to a user (although I’d better that someone is already doing this). Although if it gets taken too far, we’ll have a flood of advertisers posting pictures with maximized saturation…

  2. kellan says:

    You’d want to use saturation orthogonally to other forms of interestigness, but I it would be interesting to see how closely they tracked, and which colors individuals perferred.