Color dependent computational aesthetics for evolving expressions

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Greenfield, G.: Color dependent computational aesthetics for evolving expressions. In: Sarhangi, R. (ed.) Bridges 2002 Conference Proceedings, pp. 9–16. Central Plains Book Manufacturing, Winfield KS (2002).



A well-known method for generating computer art is based on the paradigm of user-guided evolution, a method whereby "artists" interactively search through populations of images in order to select, and subsequently breed, those images which show aesthetic promise. This can be a time consuming endeavor, lacking well-defined principles for controlling evolution and for obtaining images with desired aesthetic characteristics. One way to improve upon this situation is to develop computational criteria for selecting images that conform to user specified aesthetics. We consider a non-interactive evolutionary method that contributes to this field of computational aesthetics by: (1) color segmenting the digital images that we breed so that their color organization can be used to influence aesthetic decision making, and (2) investigating mathematical models for assigning aesthetic fitness to images based on geometric quantities obtained following color segmentation. We provide examples of the aesthetic imagery we obtain.

Extended Abstract


Used References

[1] Baluja, S., D. Pommerleau, and T. Jochem, Towards automated artificial evolution for computer-generated images, Connection Science, Volume 6, Numbers 2 & 3, 1994, 325-354.

[2] Boden, M., Agents and creativity, Comm. of the ACM, Volume 37, Number 7,1994,117-121.

[3] Comaniciu, D., and P. Meer, Robust analysis of feature spaces: color image segmentation, Proceedings of CVPR '91, 1997, 750-755.

[4] Dawkins, R., The evolution of evolvability, Artificial Life (ed. C. Langton), Addison Wesley, Reading, MA, 1989, 201-220.

[5] Y. Deng, B. Manjunath, and H. Shin, Color image segmentation, Proceedings of CVPR '99, 1999.

[6] Elliot, C., Functional image synthesis, 2001 Bridges Conference Proceedings (ed. R. Sarhangi and S. Jablan), 2001, 139-158.

[7] Greenfield, G., Art and artificial life - a coevolutionary approach, Artificial Liv~ VII Confer- ence Proceedings (ed. M. Bedau et al), MIT Press, Cambridge, MA, 2000, 529-536.

[8] Greenfield, G., Mathematical building blocks for evolving expressions, 2000 Bridges Conference Proceedings (ed. R. Sarhangi), 2000, 61-70.

[9] Greenfield, G., New directions for evolving expressions, 1998 Bridges Conference Proceedings (ed. R. Sarhangi), 1998, 29-36.

[10] Hitchcock, N., Painting pictures through time, Computer Artist, December/January 1996, 9-9.

[11] Ibrahim, A., GenShade, Ph.D. Dissertation, Texas A&M University, 1998.

[12] Lund, H., L. Pagliarini, and O. Miglino, Artificial painter, Abstract Book of the Third European Conference on Artificial Life (Ecal '95), 1995.

[13] Machado, P. and A. Cardoso, Computing aesthetics, in Proceedings XIV-th Brazilian Sym- posium on Artificial Intelligence SBIA '98, Porto Allegre, Brazil (ed. F. Oleiveira), Springer- Verlag, LNAI Series, New York, NY, 1998, 219-229.

[14] Machado, P. and A. Cardoso, NEvAr - the assessment of an evolutionary art tool, in Pro- ceedings of the AISB '00 Symposium & Cultural Aspects and Applications of AI & Cognitive Science (ed. G. Wiggins), Birmingham, UK, 2000.

[15] Maeda, J., Design by Numbers, MIT Press, Cambridge, MA, 1999.

[16] Sims, K., Artificial evolution for computer graphics, Computer Graphics, 25 (1991) 319-328.

[17] Todd, S., and W. Latham, Evolutionary Art and Computers, Academic Press, San Diego, CA, 1992.

[18] Unemi, T., SBART -Interactive Art Using Artificial Evolution, User's Manual, 1994.

[19] Voss, D., Sex is best, WIRED, December, 1995, 156-157.

[20] Witbrock, M., and S. Neil-Reilly, Evolving genetic art, in Evolutionary Design by Computers (ed. P. Bentley), Morgan Kaufmann, San Francisco, CA, 1999, 251-259.


Full Text

intern file

Sonstige Links