Power to the Critics – A Framework for the Development of Artificial Art Critics

Abstract

In this paper we propose a framework for the development of artificial art critics, consisting of an architecture and a validation methodology. The architecture includes two modules: a feature extractor, which performs a pre-processing of the artwork, extracting several measurements and characteristics; and an evaluator, which, based on the output of the feature extractor, classifies the artwork according to a certain criteria. The validation methodology comprises several stages, ranging from author and style discrimination to the integration of the artificial art critic in a dynamic multi-agent environment, which includes human agents. Finally, we present experimental results obtained by the implementation of the proposed framework.

5 Figures and Tables

Cite this paper

@inproceedings{Machado2003PowerTT, title={Power to the Critics – A Framework for the Development of Artificial Art Critics}, author={Penousal Machado and Juan Romero and Bill Z. Manaris and Antonino Santos and Am{\'i}lcar Cardoso}, year={2003} }