Content-Based Image Retrieval (CBIR) has attracted much attention of the research community. As exact matching is not possible with image retrieval, the approach is to use similarity-based matching using the global features of the entire image to compute a similarity score between two images. Equally important is the use of salient-objects: objects in an image that are of particular interest, as the basis of similarity-based computation. However, the current works on CBIR do not address very well the issues related to salient-objects. In this work, we propose a data repository model so that spatial features of salient objects are captured. Moreover, we propose an extension to the similaritybased selection operator defined earlier to allow salient object based selection. We also propose spatial operators that can be used to compute spatial relations between an image and its contained salient objects. To demonstrate the viability of our proposals, we extend a previous system named EMIMS, to develop EMIMS-S (Extended Medical Image Management System to support Salient objects). We also experimentally evaluate the retrieval effectiveness of salient-objects-based image queries.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.