An Indirect Fitness Scheme for Automated Evolution of Aesthetic Images

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche



Referenz

Gary Greenfield: An Indirect Fitness Scheme for Automated Evolution of Aesthetic Images. In: EvoMUSART 2014, S. 85-94.

DOI

http://link.springer.com/10.1007/978-3-662-44335-4_8

Abstract

This paper presents the results of two experiments comparing the functioning of a computational system and a group of humans when performing tasks related to art and aesthetics. The first experiment consists of the identification of a painting, while the second one uses the Maitland Graves’s aesthetic appreciation test. The proposed system employs a series of metrics based on complexity estimators and low level features. These metrics feed a learning system using neural networks. The computational approach achieves similar results to those achieved by humans, thus suggesting that the system captures some of the artistic style and aesthetics features which are relevant to the experiments performed.

Extended Abstract

Bibtex

Links

Full Text

[extern file]

intern file

Sonstige Links