Title
Efficiently support concurrent queries in multiuser CBIR systems
Abbreviated Journal Title
Multimed. Tools Appl.
Keywords
Content-based image retrieval; Relevance feedback; Target search; Category search; Index structures; IMAGE RETRIEVAL-SYSTEM; RELEVANCE FEEDBACK; PERFORMANCE; Computer Science, Information Systems; Computer Science, Software; Engineering; Computer Science, Theory & Methods; Engineering, Electrical; & Electronic
Abstract
Various techniques have been developed for different query types in content-based image retrieval systems such as sampling queries, constrained sampling queries, multiple constrained sampling queries, k-NN queries, constrained k-NN queries, and multiple localized k-NN queries. In this paper, we propose a generalized query model suitable for expressing queries of different types, and investigate efficient processing techniques for this new framework. We exploit sequential access and data sharing by developing new storage and query processing techniques to leverage inter-query concurrency. Our experimental results, based on the Corel dataset, indicate that the proposed optimization can significantly reduce average response time in a multiuser environment, and achieve better retrieval precision and recall compared to two recent techniques.
Journal Title
Multimedia Tools and Applications
Volume
42
Issue/Number
3
Publication Date
1-1-2009
Document Type
Article
Language
English
First Page
273
Last Page
293
WOS Identifier
ISSN
1380-7501
Recommended Citation
"Efficiently support concurrent queries in multiuser CBIR systems" (2009). Faculty Bibliography 2000s. 1810.
https://stars.library.ucf.edu/facultybib2000/1810
Comments
Authors: contact us about adding a copy of your work at STARS@ucf.edu