Feature selection and novelty in computational aesthetics
Ver/ abrir
Use este enlace para citar
http://hdl.handle.net/2183/20785Coleccións
Metadatos
Mostrar o rexistro completo do ítemTítulo
Feature selection and novelty in computational aestheticsData
2013Cita bibliográfica
Correia J, Machado P, Romero J, Carballal A. Feature selection and novelty in computational aesthetics. En: Machado P, McDermott J, Carballal A, editors. Evolutionary and biologically inspired music, sound, art and design. Ponencias del 2nd International Conference EvoMUSART; 2013 Abr 3-5; Viena, Austria. Berlin: Springer; 2013. p.133-144 (Lesture Notes in Computer Science; 7834)
Resumo
[Abstract] An approach for exploring novelty in expression-based evolutionary art systems is presented. The framework is composed of a feature extractor, a classifier, an evolutionary engine and a supervisor. The evolutionary engine exploits shortcomings of the classifier, generating misclassified instances. These instances update the training set and the classifier is re-trained. This iterative process forces the evolutionary algorithm to explore new paths leading to the creation of novel imagery. The experiments presented and analyzed herein explore different feature selection methods and indicate the validity of the approach.
Palabras chave
Feature selection
Feature extractor
Feature selection method
Content base image retrieval
Evolutionary engine
Feature extractor
Feature selection method
Content base image retrieval
Evolutionary engine
Versión do editor
Dereitos
The final publication is avaliable at Springer Link
ISSN
0302-9743
1611-3349
1611-3349
ISBN
978-3-642-36954-4 978-3-642-36955-1