Abstract
We describe the building of a library of 10,000 distinct abstract art images, and how these can be interpreted as describing the placement of objects in a scene for generative painting projects. Building the library to contain only markedly distinct images necessitated a machine learning approach, whereby two decision trees were derived to predict visual similarity in pairs of images. The first tree uses genotypical information to predict before image generation whether two images will be too similar. The second tree uses phenotypical information, namely how pairs of images differ when segmented using various distance thresholds. Taken together, the trees are highly effective at quickly predicting when two images are similar, and we used this in an evolutionary search where non-unique individuals are pruned, to build up the library. We show how the pruning approach can be used alongside a fitness function to increase the yield of images with certain properties, such as low/high colour variety, symmetry and contrast.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Arthur, D., Vassilvitskii, S.: K-means++: The advantages of careful seeding. In: Proc. of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms (2007)
Colton, S.: Automatic invention of fitness functions, with application to scene generation. In: Proceedings of the EvoMusArt Workshop (2008)
Colton, S.: Experiments in constraint-based automated scene generation. In: Proceedings of the 5th Int. Joint Workshop on Computational Creativity (2008)
Colton, S.: Seven catchy phrases for computational creativity research. In: Proceedings of the Dagstuhl Seminar on Computational Creativity (2009)
Colton, S.: The Painting Fool: Stories from building an automated artist. In: McCormack, J., d’Inverno, M. (eds.) Computers and Creativity. Springer (2012)
Colton, S., Cook, M., Raad, A.: Ludic considerations of tablet-based Evo-art. In: Proceedings of the EvoMusArt Workshop (2011)
Datta, R., Joshi, D., Li, J., Wang, J.: Image retrieval: Ideas, influences, and trends of the new age. ACM Computing Surveys 40(2) (2008)
den Heijer, E., Eiben, A.: Comparing aesthetic measures for evolutionary art. In: Proceedings of the EvoMusArt Workshop (2010)
Ekárt, A., Sharma, D., Chalakov, S.: Modelling human preference in evolutionary art. In: Proceedings of the EvoMusArt Workshop (2011)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.: The WEKA data mining software: An update. SIGKDD Explorations 11(1) (2009)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes - Active contour models. International Journal of Computer Vision 1(4) (1987)
Li, Y., Hu, C.: Aesthetic learning in an interactive evolutionary art system. In: Proceedings of the EvoMusArt Workshop (2010)
Macedo, L., Cardoso, A.: Assessing creativity: The importance of unexpected novelty. In: Proceedings of the 2nd Workshop on Creative Systems (2002)
Machado, P., Cardoso, A.: Computing Aesthetics. In: de Oliveira, F.M. (ed.) SBIA 1998. LNCS (LNAI), vol. 1515, pp. 219–228. Springer, Heidelberg (1998)
Machado, P., Romero, J., Manaris, B.: Experiments in computational aesthetics – an iterative approach to stylistic change in evolutionary art. In: The Art of Artificial Evolution. Springer (2007)
McCorduck, P.: AARON’s Code: Meta-Art, Artificial Intelligence, and the Work of Harold Cohen. W. H. Freeman and Company (1991)
Saunders, R., Grace, K.: Extending context free to teach interactive evolutionary design systems. In: Proceedings of the EvoMusArt Workshop (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Colton, S. (2012). Evolving a Library of Artistic Scene Descriptors. In: Machado, P., Romero, J., Carballal, A. (eds) Evolutionary and Biologically Inspired Music, Sound, Art and Design. EvoMUSART 2012. Lecture Notes in Computer Science, vol 7247. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29142-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-29142-5_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29141-8
Online ISBN: 978-3-642-29142-5
eBook Packages: Computer ScienceComputer Science (R0)