Content-based Image Retrieval (CBIR) involvesretrieving images similar to an example query image in terms of some features extracted from the image. However, inherent subjectivity in user perception of an image results in retrieved images that are largely irrelevant to the user. We propose a novel methodology for efficient understanding of user perception from the query image itself. Our system automatically generates a set of modified images, after the user selects object(s) of interest from the segmented query image. Our goal is to learn the retrieval parameters by modifying the segment-level description of the query image. Segment-level description includes individual segment properties as well as the inter-segment relationships. The user perception is then learnt on the basis of user feedback on this set of modified images. We demonstrate the feasibility and advantages of the proposed approach with examples. The proposed methodology of intra-query learning saves the cost of repeated database search incurred in existing relevance feedback based approaches.
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.