DocumentCode
3003947
Title
Evolving aesthetic images using multiobjective optimization
Author
Greenfield, G.R.
Author_Institution
Dept. of Comput. Sci., Richmond Univ., VA, USA
Volume
3
fYear
2003
fDate
8-12 Dec. 2003
Firstpage
1903
Abstract
We consider the problem of using evolutionary multiobjective optimization to evolve visual imagery. In our method, images (phenomes) are generated from expressions (genomes), and then color segmented so that they can be evaluated under a number of different aesthetic criteria. Our principal task is to formulate fitness functions that make the best use of these elementary aesthetic components. We demonstrate the benefits obtained from using more than one objective function. We also discuss technical issues that arose as a consequence of treating our computational aesthetics problem as a "real-world" application of evolutionary multiobjective optimization.
Keywords
evolutionary computation; image processing; optimisation; aesthetic images; color segmentation; computational aesthetics; evolutionary optimization; image evolution; multiobjective optimization; visual imagery; Bioinformatics; Computer science; Decision making; Genetic algorithms; Genomics; Image generation; Image segmentation; Mathematics; Neural networks; Organisms;
fLanguage
English
Publisher
ieee
Conference_Titel
Evolutionary Computation, 2003. CEC '03. The 2003 Congress on
Print_ISBN
0-7803-7804-0
Type
conf
DOI
10.1109/CEC.2003.1299906
Filename
1299906
Link To Document