Saliency-based Models of Image Content and their Application to Auto-Annotation by Semantic Propagation
Hare, Jonathon S. and Lewis, Paul H. (2005) Saliency-based Models of Image Content and their Application to Auto-Annotation by Semantic Propagation. At Multimedia and the Semantic Web / European Semantic Web Conference 2005, Heraklion, Crete,
Download
![[img]](http://eprints.soton.ac.uk/style/images/fileicons/application_pdf.png) |
PDF
Download (311Kb) |
Description/Abstract
In this paper, we propose a model of automatic image annotation based on propagation of keywords. The model works on the premise that visually similar image content is likely to have similar semantic content. Image content is extracted using local descriptors at salient points within the image and quantising the feature-vectors into visual terms. The visual terms for each image are modelled using techniques taken from the information retrieval community. The modelled information from an unlabelled query image is compared to the models of a corpus of labelled images and labels are propagated from the most similar labelled images to the query image.
| Item Type: | Conference or Workshop Item (Speech) |
|---|---|
| Additional Information: | Event Dates: 29/5/2005 |
| Related URLs: | |
| Keywords: | Saliency, auto-annotation, vector-space, latent semantic indexing |
| Divisions: | Faculty of Physical and Applied Science > Electronics and Computer Science > Web & Internet Science |
| Item ID: | 260954 |
| Date Deposited: | 24 Jun 2005 |
| Last Modified: | 02 Mar 2012 00:57 |
| Contributors: | Hare, Jonathon S. (Author) Lewis, Paul H. (Author) |
| Date: | 2005 |
| Additional Information: | Event Dates: 29/5/2005 |
| Status: | Published |
| Further Information: | Google Scholar |
| URI: | http://eprints.soton.ac.uk/id/eprint/260954 |
Actions (login required)
 |
View Item |
