Skip to Main content Skip to Navigation
New interface
Conference papers

Salient-Object-Based Image Query by Visual Content

Abstract : 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 similarity-based 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.
Document type :
Conference papers
Complete list of metadata
Contributor : Équipe gestionnaire des publications SI LIRIS Connect in order to contact the contributor
Submitted on : Wednesday, April 26, 2017 - 3:22:48 PM
Last modification on : Friday, September 30, 2022 - 11:34:15 AM


  • HAL Id : hal-01514671, version 1


Solomon Atnafu, David Coquil, Lionel Brunie, Richard Chbeir, Dawit Bulcha. Salient-Object-Based Image Query by Visual Content. IEEE International Conference on Signal-Image Technology & Internet–Based Systems (SITIS'05), Nov 2005, Yaoundé, Cameroon. ⟨hal-01514671⟩



Record views