Finding Image Features Associated with High Aesthetic Value by Machine Learning

  • Vic Ciesielski
  • Perry Barile
  • Karen Trist
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7834)


A major goal of evolutionary art is to get images of high aesthetic value. We assume that some features of images are associated with high aesthetic value and want to find them. We have taken two image databases that have been rated by humans, a photographic database and one of abstract images generated by evolutionary art software. We have computed 55 features for each database. We have extracted two categories of rankings, the lowest and the highest. Using feature extraction methods from machine learning we have identified the features most associated with differences. For the photographic images the key features are wavelet and texture features. For the abstract images the features are colour based features.


Evolutionary Art Genetic Art Feature Extraction Feature Selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    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)Google Scholar
  2. 2.
    Datta, R., Joshi, D., Li, J., Wang, J.: Studying Aesthetics in Photographic Images Using a Computational Approach. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 288–301. Springer, Heidelberg (2006), CrossRefGoogle Scholar
  3. 3.
    Galanter, P.: Complexism and the Role of Evolutionary Art. In: Romero, J., Machado, P. (eds.) The Art of Artificial Evolution. Natural Computing Series, pp. 311–332. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  4. 4.
    Machado, P., Romero, J., Manaris, B.: Experiments in Computational Aesthetics. In: Romero, J., Machado, P. (eds.) The Art of Artificial Evolution. Natural Computing Series, pp. 381–415. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    McCormack, J.: Open Problems in Evolutionary Music and Art. In: Rothlauf, F., Branke, J., Cagnoni, S., Corne, D.W., Drechsler, R., Jin, Y., Machado, P., Marchiori, E., Romero, J., Smith, G.D., Squillero, G. (eds.) EvoWorkshops 2005. LNCS, vol. 3449, pp. 428–436. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Nadal, M., Pearce, M.: The Copenhagen Neuroaesthetics Conference: Prospects and Pitfalls for an Emerging Field. Brain and Cognition 76(1), 172–183 (2011)CrossRefGoogle Scholar
  7. 7.
    Neufeld, C., Ross, B., Ralph, W.: The evolution of artistic filters. In: Romero, J., Machado, P. (eds.) The Art of Artificial Evolution: A Handbook on Evolutionary Art and Music, pp. 335–356. Springer, Heidelberg (2007)Google Scholar
  8. 8.
    Newall, M.: What is a Picture?: Depiction, Realism, Abstraction. Palgrave Macmillan (2011)Google Scholar
  9. 9.
    Spehar, B., Clifford, C.W.G., Newell, B.R., Taylor, R.P.: Universal Aesthetic of Fractals. Computers & Graphics 27(5), 813–820 (2003)CrossRefGoogle Scholar
  10. 10.
    Taylor, R.P., Spehar, B., Clifford, C.W.G., Newell, B.R.: The Visual Complexity of Pollock’s Dripped Fractals. In: Minai, A.A., Bar-Yam, Y. (eds.) Unifying Themes in Complex Systems IV, pp. 175–182. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Tooby, J., Cosmides, L.: Does Beauty Build Adapted Minds? Toward an Evolutionary Theory of Aesthetics, Fictions, and the Arts. Substance 30(1), 6–27 (2001)CrossRefGoogle Scholar
  12. 12.
    Welsch, W.: On the Universal Appreciation of Beauty. International Yearbook of Aesthetics 12, 6–32 (2008)Google Scholar
  13. 13.
    Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Francisco (2000)Google Scholar
  14. 14.
    Xu, Q., D’Souza, D., Ciesielski, V.: Evolving images for entertainment. In: Proceedings of the 2007 Australasian Conference on Interactive Entertainment, December 3-5, pp. 1–8. ACM (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Vic Ciesielski
    • 1
  • Perry Barile
    • 1
  • Karen Trist
    • 2
  1. 1.School of Computer Science and Information TechnologyRMIT UniversityMelbourneAustralia
  2. 2.School of Media and CommunicationRMIT UniversityMelbourneAustralia

Personalised recommendations