A MODEL OF ABSTRACTION IN VISUAL PERCEPTION

In artificial intelligence, abstraction has been mainly studied as a mapping between languages in relation to problem-solving, with the aim of reducing the complexity of the task. However, abstraction has a much larger scope in reasoning; we are investigating, in this article, how abstraction can be used in concept representation. To this aim, we propose a novel, perception-based model of abstraction, which originates from the observation that conceptualization of a domain, even though involving entities belonging to several epistemological levels, is nevertheless primarily based on perception. This view has been recently advocated by Goldstone and Barsalou in cognitive science. A model of representation/abstraction is then proposed and its application to a real-world problem of robot visual perception and categorization is presented.