RMIT University
Browse

File(s) not publicly available

Content-based image retrieval using image regions as query examples

conference contribution
posted on 2024-10-30, 22:32 authored by Dayang Nurfatimah Awg Iskandar, James Thom, Seyed Tahaghoghi
A common approach to content-based image retrieval is to use example images as queries; images in the collection that have low-level features similar to the query examples are returned in response to the query. In this paper, we explore the use of image regions as query examples. We compare the retrieval e ectiveness of using whole images, single regions, and multiple regions as examples. We also compare two approaches for combining shape features: an equalweight linear combination, and classi cation using machine learning algorithms. We show that using image regions as query examples leads to higher e ectiveness than using whole images, and that an equalweight linear combination of shape features is simpler and at least as e ective as using a machine learning algorithm.

History

Start page

38

End page

46

Total pages

9

Outlet

Proceedings of Nineteenth Australasian Database Conference (ADC 2008)

Editors

A Fekete, X. Lin

Name of conference

Nineteenth Australasian Database Conference (ADC 2008)

Publisher

Australian Computer Society

Place published

Australia

Start date

2008-01-22

End date

2008-01-25

Language

English

Copyright

©2008, Australian Computer Society, Inc.

Former Identifier

2006009237

Esploro creation date

2020-06-22

Fedora creation date

2011-09-23

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC