Abstract
Computational aesthetics is an area of research which attempts to develop computational methods that can perform human-like aesthetic judgements. Aesthetic judgements are often subjective, as such the development of computational models of aesthetics is highly challenging. This article summarises the advancements in the area of computational aesthetics and how computational intelligence techniques are applied in art and aesthetics ranging from simple classification problems to more advanced problems such as automatic generation of art artefacts, stories and simulations. The article concludes summarising major challenges that need to be addressed, and future directions that need to be undertaken in order to make significant advancements in the area of computational aesthetics and its applications.
TopBackground
Aesthetics
The study of aesthetics is chiefly a branch of philosophy with links to other disciplines such as psychology. The term aesthetics was derived from the Greek word aisthanesthai (to perceive (by the senses or by the mind)) and introduced into the philosophical terminology in the eighteenth century (Saw & Osborne, 1960). The definition of aesthetics is a long standing debate. Early definitions of aesthetics are related to art or beauty (Santayana, 1904). Later attempts to define aesthetics discuss that aesthetics mean more than just art and natural beauty (Walton, 2007), (Palmer, Schloss, & Sammartino, 2013). Therefore more contemporary definitions are woven around human mental processes involved in making aesthetic judgements; for example:
- •
The study of human minds and emotions in relation to the sense of beauty (Palmer et al., 2013).
- •
Psychological mechanisms that allow humans to experience and appreciate a broad variety of objects and phenomena, including utensils, commodities, designs, other people, or nature, in aesthetic terms (beautiful, attractive, ugly, sublime, picturesque, and so on) (Leder & Nadal, 2014).
Key Terms in this Chapter
Aesthetic Classification: Categorising objects, situations or phenomena into several aesthetic classes based on their quality.
Computational Aesthetics: An area of research focused on developing computational models and techniques that are capable of making human-like aesthetic decisions.
Evolutionary Art: An area of research focused on utilising evolutionary computing techniques to automatically create art.
Aesthetics: Study of human mental processes involved in appreciating a subjective experience and its quality in a wide variety of objects, situations and phenomena. An aesthetic experience can be positive, negative or more subtly nuanced.
Computational Intelligence: The application and development of adaptive computational techniques focused on making systems that can demonstrate intelligent behaviour in complex and changing environments.
Evolutionary Computing: A computational intelligence technique inspired by the evolution of biological species in nature and utilise the underlying abstract concepts of Darwinian evolution: natural selection and survival of the fittest to perform a stochastic search for solutions to a problem.
Aesthetic Scoring: Rating objects, situations or phenomena for their aesthetic quality in a discrete or a continuous range.