Computerized Analysis of Paintings

James Z. Wang, Baris Kandemir, Jia Li
The Pennsylvania State University, USA
Abstract:

As hundreds of thousands of paintings, including many of the most significant historical works, have been digitized in high resolution and made available to the public, scientists have started to utilize some of the latest image analysis and artificial intelligence tools to study these paintings. Such computerized analyses can provide valuable insights to art historians regarding attribution, dating, cataloging, and comparative analysis, and recent advancements in computerized analysis of artistic paintings have branched out to employ novel approaches and to do so for various purposes. For example, computerized analysis based on statistical learning and modeling has the potential to predict emotions evoked from visual arts. In a similar vein, interest in art may be increased by automated personalization of art experiences in museums and on the Web. Moreover, the analysis of a large volume of historical paintings may shed light on important topics such as aesthetics, composition, and emotions. Finally, we present our vision for the future of the field, including the anticipated impact of painting analysis to the development of artificial intelligence.


Full Paper in Color

(PDF, 15MB)

On-line Info on the Research


Citation: James Z. Wang, Baris Kandemir and Jia Li, ``Computerized Analysis of Paintings,'' The Routledge Companion to Digital Humanities and Art History, Kathryn Brown (editor), Routledge, Chapter 22, pp. 299-312, 2020.

Copyright 2020 Routledge, Taylor & Francis Group, London. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the Routledge, Taylor & Francis Group, London.

Last Modified: April 18, 2019
© 2019