6533b831fe1ef96bd1298d48

RESEARCH PRODUCT

An improved distance-based relevance feedback strategy for image retrieval

Miguel Arevalillo-herráezFrancesc J. Ferri

subject

Computer sciencebusiness.industryFeature vectorRelevance feedbackMachine learningcomputer.software_genreContent-based image retrievalk-nearest neighbors algorithmSignal ProcessingRelevance (information retrieval)Computer Vision and Pattern RecognitionArtificial intelligencebusinesscomputerImage retrievalDistance based

description

Most CBIR (content based image retrieval) systems use relevance feedback as a mechanism to improve retrieval results. NN (nearest neighbor) approaches provide an efficient method to compute relevance scores, by using estimated densities of relevant and non-relevant samples in a particular feature space. In this paper, particularities of the CBIR problem are exploited to propose an improved relevance feedback algorithm based on the NN approach. The resulting method has been tested in a number of different situations and compared to the standard NN approach and other existing relevance feedback mechanisms. Experimental results evidence significant improvements in most cases.

yearjournalcountryeditionlanguage
2013-10-01Image and Vision Computing
https://doi.org/10.1016/j.imavis.2013.07.004