•  
  •  
 

Abstract

Image catalogs containing several million reproductions of artworks still pose a costly or computationally intensive challenge if one tries to categorize them adequately, either in a manual or automatic way. Using crowdsourced annotations assigned by laypersons, this article proposes the application of a clustering algorithm to segment artworks into groups. It is shown that the resulting clusters allow for a consistent reclassification extending the traditional categories (history, genre, portrait, still life, landscape), and thus enable a finely-grained differentiation which can be used to search in and filter image inventories, among other things.

Share

COinS
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.