Performance evaluation of Euclidean/correlation-based relevance feedback algorithms in content-based image retrieval systems

Doulamis, A; Doulamis, N

dc.contributor.author	Doulamis, A	en
dc.contributor.author	Doulamis, N	en
dc.date.accessioned	2014-03-01T02:42:19Z
dc.date.available	2014-03-01T02:42:19Z
dc.date.issued	2003	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30938
dc.subject	Content Based Image Retrieval	en
dc.subject	Cross Correlation	en
dc.subject	Euclidean Distance	en
dc.subject	Feature Vector	en
dc.subject	Optimization Technique	en
dc.subject	Performance Evaluation	en
dc.subject	Relevance Feedback	en
dc.subject	Selective Sampling	en
dc.subject	Similarity Metric	en
dc.subject	Average Normalized Modified Retrieval Rank	en
dc.subject.other	Algorithms	en
dc.subject.other	Correlation methods	en
dc.subject.other	Feedback	en
dc.subject.other	Heuristic methods	en
dc.subject.other	Motion estimation	en
dc.subject.other	Performance	en
dc.subject.other	Probability	en
dc.subject.other	Semantics	en
dc.subject.other	Relevance feedback (RF)	en
dc.subject.other	Support vector machines (SVM)	en
dc.subject.other	Content based retrieval	en
dc.title	Performance evaluation of Euclidean/correlation-based relevance feedback algorithms in content-based image retrieval systems	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2003.1247067	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2003.1247067	en
heal.publicationDate	2003	en
heal.abstract	In this paper, we evaluate and investigate two main types of relevance feedback algorithms; the Euclidean and the correlation - based approaches. In the first case, we examine heuristic and optimal techniques, which exploit either on the weighted or the generalized Euclidean distance. In the second type, two different ways for parametrizing the cross-correlation similarity metric are proposed. The first scales only the elements of the query feature vector, while the second scales both the query and the selected samples. All the examined algorithms are evaluated using objective criteria, such as the precision -recall curve and the average normalized modified retrieval rank (ANMRR). Discussions and comparisons of all the aforementioned relevance feedback algorithms are presented.	en
heal.journalName	IEEE International Conference on Image Processing	en
dc.identifier.doi	10.1109/ICIP.2003.1247067	en
dc.identifier.volume	1	en
dc.identifier.spage	737	en
dc.identifier.epage	740	en