IntroductionThe retrieval performance of content-based image retrieval (CBIR) systems still leaves much to be desired, especially when the system is serving as an interface to an image colleclion covering many different topics. The problem of missing jemantical information about the images leads to great numbers offalse matches because o f misleading similiirities in the visual primitives that are retrieved. This paper introduces an approach called GIVBAC, that tries to reduce the number of false matches in query result sets. It relies heavily on user feedback on retrieval results with regard to user-definable thematic groups. Feedback is used globally, i.e. the feedback of one riser has influences on the behaviour of the whole system. The weight of irzdividiial votes is a param.eter of GIVBAC so that it can be adjusted to the level of trust the riser base is given, i.e. higher values in a closed user group and lower values in an open group with anonymoics users.The paper presents results of an evaluation comparing the performance of an rmmodijied CBIR system with a system that is modified so that it uses GIVBAC as an interface to the users.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.