Automatic Invention of Fitness Functions with Application to Scene Generation

We investigate the automatic construction of visual scenes via a hybrid evolutionary/hill-climbing approach using a correlation-based fitness function. This forms part of The Painting Fool system, an automated artist which is able to render the scenes using simulated art materials. We further describe a novel method for inventing fitness functions using the HR descriptive machine learning system, and we combine this with The Painting Fool to generate and artistically render novel scenes. We demonstrate the potential of this approach with applications to cityscape and flower arrangement scene generation.