Using a Contextual Focus Model for an Automatic Creativity Algorithm to Generate Art Work

摘要: Abstract We sought to implement and determine whether incorporating cognitive based contextual focus into a genetic programming fitness function would play crucial role in enabling the computer system generate art that humans find “creative” (i.e. possessing qualities of novelty aesthetic value typically ascribed output creative artistic process). implemented evolutionary algorithm by giving program capacity vary its level fluidity functional triggered dynamic control over different phases process. The domain portrait painting was chosen because it requires both focused attention (analytical thought) accomplish primary goal creating sitter resemblance as well defocused (associative creativity deviate from i.e., meet broad often conflicting criteria art. Since judging is subjective, rather than use quantitative analysis, representative subset automatically produced art-work this selected submitted many peer reviewed commissioned shows, thereby allowing be judged positively or negatively human curators, reviewers gallery going public.