This is a program that, given an image of a skin lesion, can calculate the number of perceptually significant colors in the skin lesion through autonomous clustering and various cluster validity measures.
It was applied with a data set and a symbolic regression algorithm in order to determine an equation for calculating whether a lesion is cancerous based on the number of colors as given by the various cluster validity indexes that were programmed. The equation developed, when implemented with this system had an accuracy of 72%