Expression-Based Evolution of Faces

Authors

Abstract

The combination of a classier system with an evolutionary image generation engine is explored. The framework is instantiated using an o-the-shelf face detection system and a general purpose, expressionbased, genetic programming engine. By default, the classier returns a binary output, which is inadequate to guide evolution. By retrieving information provided by intermediate results of the classication task, it became possible to develop a suitable tness function. The experimental results show the ability of the system to evolve images that are classied as faces. A subjective analysis also reveals the unexpected nature and artistic potential of the evolved images.

Keywords

Evolutionary Computation, Evolutionary Art, Automatic Fitness Assignment, Face Detection

Subject

Artificial Intelligence

Conference

Proceedings of the 1st International Conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design, EvoMUSART 2012, Malaga, Spain, 2012. Spri, April 2012