Visualflamenco: Dependable, interactive image browsing based on visual properties

Abstract

Faceted search as a method for exploratory 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 in order to enable him (or her) to accomplish his search goal as quickly and efficiently as possible. The search goal can be both, to retrieve a target image (lookup search) or to get an overview of a collection as the basis for accomplishing complex search tasks (exploratory search).VisualFlamenco is about bringing content-based image retrieval and faceted search together. While there is some preexisting work towards faceted search based on automatically extracted metadata, the base innovation of our work is to visualize the meaning of facets and let the user pick visualized facets directly.The main point is this research is to give the user the right expectations about what the system can achieve. We see this as a step towards dependable multimedia search, search interfaces that do not promise more than they can achieve. A mismatch of expectations and possibilities has been denoted by some as one of the main problems in current research about multimedia search.Within this paper we present a visual faceted search tool that seeks to provide dependable image search. We describe its base idea, the features used, as well as user experiments done using the system.

Interactive Search Processes in Complex Work Situations : a Retrieval Framework

“…Although mostly text-based facets are found in faceted search engines, an interesting approach is taken by Müller et al [2008] for the domain of Content-Based Image Retrieval (CBIR). The authors extracted visual features of images such as the dominant color of a region or the coarseness level and used them as facets in the VisualFlamenco prototype.…”

“…Hearst [2006b] gives additional design recommendations for hierarchical faceted search interfaces which were derived by studying several revisions of the Flamenco user interface. Müller et al [2008] enhanced the Flamenco search engine to be applicable for CBIR where they used visual features of images as facets and represented them in an adapted Flamenco user interface.…”

Fine-grained Visual Faceted Search

“…Facets are typically derived from pre-existing fields in the item's metadata or manually built from the analysis of the items. Using visual facets complementary to textual ones has already been addressed in a few previous works [2,1,9]. The principle is to automatically compute the facets by image clustering techniques and to display image links rather than textual links in the graphical user interface.…”

“…The first one attempts to visually illustrate pre-existing expert facets in the data whereas the other one attempts to discover new facets from the visual contents. Both rely on the offline construction and clustering of a dense visual matching graph computed at the region level (contrary to previous visual faceted search proposals [2,1,9] that relied on image-centric clustering and global visual features).…”