Toward Greater Artistic Control for Interactive Evolution of Images and Animation

We present several practical improvements to the interactive evolution of 2D images, some of which are also applicable to more general genetic programming problems. We introduce tree alignments to improve the animation of evolved images when using genetic cross dissolves. The goal of these improvements is to strengthen the interactive evolution toolset and give the artist greater control and expressive power. 1 Evolving Images There have been many studies using different kinds of genotypes for evolutionary image synthesis and design. [2–4,6, 7, 10, 11]. Perhaps the most well known image synthesis technique using interactive evolution was explored in Sims’ seminal paper “Artificial Evolution for Computer Graphics” [10]. Sims used symbolic functions as genotypes, and simply evaluated the evolved functions at every pixel to express the genotypes into rendered image phenotypes. Symbolic functions are naturally represented as parse trees, with variables and constants at the leaf n...

• Type: Conference
• Year: 2007
• Where: EVOW
• Authors: David A. Hart
• Keywords: Artificial Intelligence, EVOW 2007, Genotypes, Interactive Evolution, Tree Structured Genotypes