VisualFlamenco: Faceted Browsing for Visual Features

Faceted search as a method for explorative search is a search interface technique for Boolean retrieval that provides a good compromise between the wish to guide the user and the need to give freedom to the user. Both guidance and freedom are needed order to enable him or her accomplish his or her search goal as quickly and efficiently as possible. The search goal can be both a target image (lookup search) or to get an overview of a collection as the basis for accomplishing complex search tasks (exploratory search). The topic of this demo is bringing content-based im- age retrieval and faceted search together. While there is some preexisting work towards faceted search based on automatically extracted metadata, the base innova- tion of our work is to visualize the meaning of facets and let the user pick visualized facets directly. We feel that this way of search gives the user the opportunity to choose the features important for the search. The user sees intuitively which features are available. The present prototype is based on the original Fla- menco prototype for text-based faceted search from Berkeley.