Hypercomplex Fractal Shapes Evolution via Computer Vision Aesthetic Evaluation. The aim of this research project is to generate and evolve, via GPU rendering, hypercomplex fractals, such as Mandelbrot and Julia Sets, following evolutionary techniques, thus to explore their imagery variations. The evolution of the population is driven by some user-defined computational aesthetic evaluations of the generated renders, defining a fitting function via computer vision techniques, which selects a single individual from which create a new generation. The evolutionary data is stored a tree-structure and can acta as a family tree, given a the mathematical expression that represent a certain fractal.
