A Pixel-Based Framework Proposal for Evolutionary Art

Beyond being used as optimization methods, evolutionary approaches are also a tool for creative production. It reveals what humans cannot see and think. Evolutionary algorithms, which we can consider as both the origin and the product of computational creativity, have an important role in the production of art. Concepts such as selection, mutation and crossover support the search of the unexpected, surprising and impressive in art. In this direction, a pixel-based framework was proposed for the production of evolutionary art, focusing on the possibilities of evolutionary approaches in terms of creativity. The pixel-based approach was produced and tested in Grasshopper. Two different works of art were selected and processed for the fitness function, one for contrast and the other for color values. The algorithm was created upon the convergence of each cell of the randomly generated initial image to the images selected for the fitness function. In line with the separate experiments carried out for a single cell and four cells, it was seen that it was necessary to wait for a very long time to reach a meaningful result. It has been proven in single and four cell trials that the algorithm achieves accurate and acceptable results despite the waiting duration limit. In the later stages of the study, different approaches will be experimented with in order to reduce the processing time.