Expression-Based evolution of faces

Authors:
Penousal Machado;João Correia;Juan Romero
Affiliations:
CISUC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal;CISUC, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal;Faculty of Computer Science, University of A Coruña, Coruña, Spain
Venue:
EvoMUSART'12 Proceedings of the First international conference on Evolutionary and Biologically Inspired Music, Sound, Art and Design
Year:
2012

Citing 8
Cited 0

Artificial evolution for computer graphics

Proceedings of the 18th annual conference on Computer graphics and interactive techniques
Criticism, culture, and the automatic generation of artworks

AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
All the Truth About NEvAr

Applied Intelligence
Aesthetic Selection: The Evolutionary Art of Steven Rooke

IEEE Computer Graphics and Applications
A General Framework for Object Detection

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Incorporating characteristics of human creativity into an evolutionary art algorithm

Genetic Programming and Evolvable Machines
On the development of critics in evolutionary computation artists

EvoWorkshops'03 Proceedings of the 2003 international conference on Applications of evolutionary computing
Self portraits with mandelbrot genetics

SG'10 Proceedings of the 10th international conference on Smart graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

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