Computational Inference of Aesthetics
Since about 2005, computer scientists have attempted to develop automated methods to infer aesthetic quality of images. Typically, these approaches follow a machine learning approach, where large numbers of manually rated photographs are used to "teach" a computer about what visual properties are of relevance to aesthetic quality. The Acquine engine, developed at Penn State University, rates natural photographs uploaded by users.
Notable in this area is Michael Leyton, professor of psychology at Rutgers University. Leyton is the president of the International Society for Mathematical and Computational Aesthetics and the International Society for Group Theory in Cognitive Science and has developed a generative theory of shape.
There have also been relatively successful attempts with regard to chess and music.
Read more about this topic: Being Beautiful In Spirit
Famous quotes containing the words inference and/or aesthetics:
“Rules and particular inferences alike are justified by being brought into agreement with each other. A rule is amended if it yields an inference we are unwilling to accept; an inference is rejected if it violates a rule we are unwilling to amend. The process of justification is the delicate one of making mutual adjustments between rules and accepted inferences; and in the agreement achieved lies the only justification needed for either.”
—Nelson Goodman (b. 1906)
“What is the use of aesthetics if they can neither teach how to produce beauty nor how to appreciate it in good taste? It exists because it behooves rational human beings to provide reasons for their actions and assessments. Even if aesthetics are not the mathematics of beauty, they are the proof of the calculation.”
—Franz Grillparzer (1791–1872)