The University of Southampton
University of Southampton Institutional Repository

Image Auto-annotation using a Statistical Model with Salient Regions

Image Auto-annotation using a Statistical Model with Salient Regions
Image Auto-annotation using a Statistical Model with Salient Regions
Traditionally, statistical models for image auto-annotation have been coupled with image segmentation. Considering the performance of the current segmentation algorithms, it can be meaningful to avoid a segmentation stage. In this paper, we propose a new approach to image auto-annotation using statistical models. In this approach, segmentation is avoided through the use of salient regions. The use of the statistical model results in an annotation performance which improves upon our previously proposed saliency-based word propagation technique. We also show that the use of salient regions achieves better results than the use of general image regions or segments.
1-4244-0367-7
Tang, Jiayu
4f9409ac-830d-4937-867d-e06c76b8a4e1
Hare, Jonathon S.
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Tang, Jiayu
4f9409ac-830d-4937-867d-e06c76b8a4e1
Hare, Jonathon S.
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020

Tang, Jiayu, Hare, Jonathon S. and Lewis, Paul H. (2006) Image Auto-annotation using a Statistical Model with Salient Regions. IEEE International Conference on Multimedia & Expo (ICME), Hilton Toronto, Toronto, Ontario, Canada. 09 - 12 Jul 2006.

Record type: Conference or Workshop Item (Paper)

Abstract

Traditionally, statistical models for image auto-annotation have been coupled with image segmentation. Considering the performance of the current segmentation algorithms, it can be meaningful to avoid a segmentation stage. In this paper, we propose a new approach to image auto-annotation using statistical models. In this approach, segmentation is avoided through the use of salient regions. The use of the statistical model results in an annotation performance which improves upon our previously proposed saliency-based word propagation technique. We also show that the use of salient regions achieves better results than the use of general image regions or segments.

Text
tang.pdf - Other
Download (142kB)

More information

Published date: 2006
Additional Information: Event Dates: 9-12 July
Venue - Dates: IEEE International Conference on Multimedia & Expo (ICME), Hilton Toronto, Toronto, Ontario, Canada, 2006-07-09 - 2006-07-12
Organisations: Web & Internet Science

Identifiers

Local EPrints ID: 262826
URI: http://eprints.soton.ac.uk/id/eprint/262826
ISBN: 1-4244-0367-7
PURE UUID: e6ee57d9-b800-4dd8-a045-db6883713860
ORCID for Jonathon S. Hare: ORCID iD orcid.org/0000-0003-2921-4283

Catalogue record

Date deposited: 10 Jul 2006
Last modified: 15 Mar 2024 03:25

Export record

Contributors

Author: Jiayu Tang
Author: Jonathon S. Hare ORCID iD
Author: Paul H. Lewis

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×