Abstract
AbstractThis paper examines and showcases a framework to generate artworks using evolutionary algorithms. Based on the idea of an incremental abstract artistic process stylized images are generated from different input images without human supervision. After explaining the underlying concept, the solution space of different styles is explored and its properties for style consistency and style variety are discussed. A first step towards better control of the outcome is implemented through masking, followed by a discussion about potential improvements and further research.
Funder
Otto-von-Guericke-Universität Magdeburg
Publisher
Springer Science and Business Media LLC
Subject
Computer Science Applications,Hardware and Architecture,Theoretical Computer Science,Software
Reference46 articles.
1. R. Dawkins, The Blind Watchmaker - Evidence of Evolution Reveals a Universe without Design (WW Norton & Company, 1986)
2. K. Sims, Artificial evolution for computer graphics, in Proceedings of the 18th Annual Conference on Computer Graphics and Interactive Techniques. SIGGRAPH ’91, Association for Computing Machinery, New York, NY, USA (1991), p. 319-328 https://doi.org/10.1145/122718.122752http://www.karlsims.com/papers/siggraph91.html
3. S. Todd, W. Latham, Evolutionary art and computers. Academic Press, Inc., USA (1992), http://portal.acm.org/citation.cfm?id=561831
4. P. Haeberli, Paint by numbers: abstract image representations. Comput. Gr. (ACM) 24(4), 207–214 (1990). https://doi.org/10.1145/97880.97902
5. M. Valstar, S. Colton, M. Pantic, Emotionally aware automated portrait painting. Belgian/Netherlands Artificial Intelligence Conference (2008), pp. 407–408