Home // SOCIETY TRENDS 2024, International Conference on Technical Advances and Human Consequences // View article

Painting with Evolutionary Algorithms: the Effects of Brush Stroke Sparsity

Authors:
Karim Nasr
Okke van Eck
Daan van den Berg

Keywords: Evolutionary Algorithms; Evolutionary Art; Painting; Computational Creativity

Abstract:
This paper investigates the use of hill climbing, simulated annealing, and tabu search algorithms for approximating target paintings with low number of brush strokes. The resulting paintings are obviously of lower resolution, but surprisingly enough, the distribution of brush strokes also changed. Whereas denser constellations have roughly uniform distributions of brush strokes, sparse constellations show clear brush stroke preference in non-trivial distributions. Furthermore, the algorithmic trajectory of just one painting consistently deviated from all the others. Its brush stroke sizes shrunk where all others grew. From an optimization perspective, it tells us that optimization metaheuristics can behave substantially different on sparse instances. Moreover, with a bit of fantasy and goodwill, the results can give an aspiring painter a bit of advise as wel

Pages: 1 to 5

Copyright: Copyright (c) IARIA, 2024

Publication date: November 3, 2024

Published in: conference

ISBN: 978-1-68558-213-5

Location: Nice, France

Dates: from November 3, 2024 to November 7, 2024