Our system generates abstract images from music that serve as inspiration for the creative process. We developed one of many possible approaches for a cross-domain association between the musical and visual domains, by extracting features from MIDI music files and associating them to visual characteristics. The associations were led by the authors' aesthetic preferences and some experimentation. Three different approaches were pursued, two with direct or random associations and a third using a genetic algorithm that considers music and color theory while searching for better results. The resulting images were evaluated through online surveys, which confirmed that not only they were abstract, but also that there was a relationship with the music that served as the basis for the association process. Moreover, the majority of the participants ranked highest the images improved with the genetic algorithm. This newsletter contribution summarizes the full version of the article, which was presented at EvoMUSART 2021 (the 10th International Conference on Artificial Intelligence in Music, Sound, Art and Design).
The Ubiquity of Cross-Domain Thinking in the Early Phase of the Creative Process
