Evolved Art with Transparent, Overlapping, and Geometric Shapes
MetadataVis full innførsel
OriginalversjonBerg J, Berggren NGA, Borgeteien S, Jahren C, Sajid A, Nichele S: Evolved Art with Transparent, Overlapping, and Geometric Shapes. In: Bach K, Ruocco M. Nordic Artificial Intelligence Research and Development: Porc. of Third Symposium of the Norwegian AI Society, NAIS 2019, 2019. Springer p. 3-15 http://dx.doi.org/10.1007/978-3-030-35664-4_1
In this work, an evolutionary art project is presented where images are approximated by transparent, overlapping and geometric shapes of diﬀerent types, e.g., polygons, circles, lines. Genotypes representing features and order of the geometric shapes are evolved with a ﬁtness function that has the corresponding pixels of an input image as a target goal. A genotype-to-phenotype mapping is therefore applied to render images, as the chosen genetic representation is indirect, i.e., genotypes do not include pixels but a combination of shapes with their properties. Diﬀerent combinations of shapes, quantity of shapes, mutation types and populations are tested. The goal of the work herein is twofold: (1) to approximate images as precisely as possible with evolved indirect encodings, (2) to produce visually appealing results and novel artistic styles.