Information Technology Reference
In-Depth Information
uncertainty in moving; furthermore, smoothing contributes to harmonious and
moderate coloring.
5 Conclusions
This study proposes using visual quality as the fitness evaluation criterion to
address the issues of fatigue and decreasing sensitivity at interactive EAs for
computational creativity. The proposed fitness function is based on two mea-
sures of visual quality, i.e., edge distribution and line intersection. The edge
distribution considers the ratio of bounding box area to the whole area. The line
intersection reflects the interaction level of agents.
Simulations are conducted on the EvoEco system to investigate the effects of
the proposed method. The simulation results show that smoothing among neigh-
bors helps to bring about harmonious coloring. In addition, the uncertainty in
moving directions leads to fewer straight lines and thus increases the variety and
diversity of generated patterns. In general, these two factors and the proposed fit-
ness function based on visual quality achieve satisfactory patterns, which validate
the effectiveness of EAs and aesthetic evaluation on computational creativity.
Future work includes some directions. First, the fitness function can consider
more aesthetic evaluation metrics. Second, design of genetic operators based on
aesthetic evaluation is promising for EAs to generate satisfactory artworks.
References
1. Baluja, S., Pomerleau, D., Jochem, T.: Towards automated artificial evolution for
computer-generated images. Connection Science 6(2), 325-354 (1994)
2. Boden, M.A.: The Creative Mind: Myths and Mechanisms. Basic Books (1991)
3. Dorin, A., Korb, K.B.: Improbable creativity. In: Proceedings of the Dagstuhl
International Seminar on Computational Creativity (2009)
4. Fernandes, C.M., Mora, A.M., Merelo, J.J., Rosa, A.C.: Kants: A stigmergic ant
algorithm for cluster analysis and swarm art. IEEE Transactions on Evolutionary
Computation 44(6), 843-856 (2013)
5. Greenfield, G.: Co-evolutionary methods in evolutionary art. In: The Art of Arti-
ficial Evolution, pp. 357-380 (2008)
6. Holland, J.: Adaptation in Natural and Artificial Systems. University of Michigan
Press (1975)
7. Kowaliw, T., Dorin, A., McCormack, J.: Promoting creative design in interactive
evolutionary computation. IEEE Transactions on Evolutionary Computation 16(4),
523-536 (2012)
8. Li, C., Chen, T.: Aesthetic visual quality assessment of paintings. IEEE Journal of
Selected Topics in Singal Processing 3(2), 236-252 (2009)
9. Liu, C.-H., Ting, C.-K.: Polyphonic accompaniment using genetic algorithm
with music theory. In: Proceedings of the 2012 IEEE Congress on Evolutionary
Computation (2012)
10. Liu, C.-H., Ting, C.-K.: Evolutionary composition using music theory and charts.
In: Proceedings of the 2013 Computational Intelligence for Creativity and Affective
Computing (2013)
Search WWH ::
Custom Search