Evolutionary Search for the Artistic Rendering of Photographs
Collomosse, John: Evolutionary Search for the Artistic Rendering of Photographs. In: Romero, Juan; Machado, Penousal: The Art of Artificial Evolution. Springer, Berlin, 2007, S. 39-62. DOI:
This chapter explores algorithms for the artistic stylization (transformation) of photographs into digital artwork, complementing techniques discussed so far in this book that focus on image generation. Most artistic stylization algorithms operate by placing atomic rendering primitives “strokes” on a virtual canvas, guided by automated artistic heuristics. In many cases the stroke placement process can be phrased as an optimization problem, demanding guided exploration of a high dimensional and turbulent search space to produce aesthetically pleasing renderings. Evolutionary search algorithms can offer attractive solutions to such problems.
This chapter begins with a brief review of artistic stylization algorithms, in particular algorithms for producing painterly renderings from two-dimensional sources. It then discusses how genetic algorithms may be harnessed both to increase control over level of detail when painting (so improving aesthetics) and to enhance usability of parameterized painterly rendering algorithms.