Evolution of Aesthetically Pleasing Images Without Human-In-The-Loop

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Atkins, D., Klapaukh, R., Browne, W., Mengjie, M.: Evolution of Aesthetically Pleasing Images Without Human-In-The-Loop. In: 2010 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8 (2010).




Evolutionary Art is a sub-field of Evolutionary Computing that involves creating interesting images using Evolutionary Techniques. Previously Genetic Programming has been used to create such images autonomously - that is, without a human in the loop. However, this work did not explore alternative fitness measures, consider colour in fitness or provide independent validation of results. Four fitness functions based on the concept that the pleasingness of an image is based on the ratio of image complexity to processing complexity are explored. We introduce the use of Shannon Entropy as a measure of image complexity to compare with Jpeg Compression. Similarly, we introduce Run Length Encoding to compare with Fractal Compression as a measure of processing complexity. A survey of 100 participants showed that it is possible to generate aesthetically pleasing graphics using each fitness function. Importantly, it was the introduction of colour that separated the aesthetic effects of the fitness measures.

Extended Abstract


Used References

J. Romero and P. Machado, Eds., The Art of Artificial Evolution: A Handbook on Evolutionary Art and Music. Springer, 2008.

M. A. Boden, "Computer models of creativity," in Handbook of creativity, R. J. Sternberg, Ed. Cambridge, UK: Cambridge University Press, 1999, ch. 18, pp. 351-372.

P. Machado and A. Cardoso, "All the truth about nevar," Applied Intelligence, vol. 16, no. 2, pp. 101-118, 2002.

R. Dawkins, The Blind Watchmaker. New York, NY, USA: W. W. Norton & Company, Inc., September 1986.

K. Sims, "Artificial evolution for computer graphics," in SIGGRAPH '91 Proceedings, vol. 25, no. 4. ACM Press, July 1991, pp. 319-328. Full Text: http://ieeexplore.ieee.org/xpl/abstractReferences.jsp?arnumber=5586283#

V. Ciesielski, M. Berry, K. Trist, and D. D'Souza, "Evolution of animated photomosaics," in Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog. Berlin, Heidelberg: Springer-Verlag, 2007, pp. 498-507. http://dx.doi.org/10.1007/978-3-540-71805-5_55

P. Barile, V. Ciesielski, and K. Trist, "Non-photorealistic rendering using genetic programming," in SEAL '08: Proceedings of the 7th International Conference on Simulated Evolution and Learning. Berlin, Heidelberg: Springer-Verlag, 2008, pp. 299-308.

P. Machado and A. Cardoso, "Computing aesthetics," in Proceedings of the Brazilian Symposium on Artificial Intelligence, SBIA'98. Springer-Verlag, 1998, pp. 219-229.

B. Ross, W. Ralph, and H. Zong, "Evolutionary image synthesis using a model of aesthetics," in Evolutionary Computation, 2006. CEC 2006. IEEE Congress on, 0-0 2006, pp. 1087-1094. Abstract http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=1688430&navigation=1

S. Baluja, D. Pomerleau, and T. Jochem, Towards Automated Artificial Evolution for Computer-generated Images, vol. 6, no. 1, pp. 325-354, 1994.

G. R. Greenfield, "Computational aesthetics as a tool for creativity," in C&C '05: Proceedings of the 5th conference on Creativity & cognition. New York, NY, USA: ACM, 2005, pp. 232-235. http://dx.doi.org/10.1145/1056224.1056259

A. Jacquin, "Image coding based on a fractal theory of iterated contractiveimage transformations," Image Processing, IEEE Transactions on, vol. 1, no. 1, pp. 18-30, 1992. Abstract http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=128028&navigation=1

R. P. Taylor, B. Spehar, J. A. Wise, C. W. G. Clifford, B. R. Newell, and T. P. Martin, "Perceptual and physiological responses to visual complexity of pollocks dripped fractal patterns," in Nonlinear Dynamics, Psychology, and Life Sciences, 2003, pp. 89-114.


Full Text

[extern file]

intern file

Sonstige Links