Digital Commons Network^™

The Computer As Filter Machine: A Clustering Approach To Categorize Artworks Based On A Social Tagging Network, Stefanie Schneider, Hubertus Kohle

Artl@s Bulletin

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.