Combined retrieval strategies for images with and without distinct objects

Hong FU, Zheru CHI, Dagan FENG

Research output: Chapter in Book/Report/Conference proceedingChapters

Abstract

This paper presents the design of an all-season image retrieval system. The system handles the images with and without distinct object(s) using different retrieval strategies. Firstly, based on the visual contrasts and spatial information of an image, a neural network is trained to pre-classify an image as distinct-object or no-distinct-object category by using the Back Propagation Through Structure (BPTS) algorithm. In the second step, an image with distinct object(s) is processed by an attention-driven retrieval strategy emphasizing distinct objects. On the other hand, an image without distinct object(s) (e.g., a scenery images) is processed by a fusing-all retrieval strategy. An improved performance can be obtained by using this combined approach. Copyright © 2010 Springer-Verlag Berlin Heidelberg.
Original languageEnglish
Title of host publicationAdvanced concepts for intelligent vision systems: 12th International Conference, ACIVS 2010, Sydney, Australia, December 13-16, 2010, proceedings, part I
EditorsJacques BLANC-TALON, Don BONE, Wilfried PHILIPS, Dan POPESCU, Paul SCHEUNDERS
Place of PublicationBerlin, Heidelberg
PublisherSpringer
Pages72-79
ISBN (Electronic)9783642176883
ISBN (Print)9783642176876
DOIs
Publication statusPublished - 2010

Citation

Fu, H., Chi, Z., & Feng, D. (2010). Combined retrieval strategies for images with and without distinct objects. In J. Blanc-Talon, D. Bone, W. Philips, D. Popescu, & P. Scheunders (Eds.), Advanced concepts for intelligent vision systems: 12th International Conference, ACIVS 2010, Sydney, Australia, December 13-16, 2010, proceedings, part I (pp. 72-79). Berlin, Heidelberg: Springer.

Fingerprint Dive into the research topics of 'Combined retrieval strategies for images with and without distinct objects'. Together they form a unique fingerprint.