An Image Based Feature Space and Mapping for Linking Regions and Words
An Image Based Feature Space and Mapping for Linking Regions and Words
We propose an image based feature space and define a mapping of both image regions and textual labels into that space. We believe the embedding of both image regions and labels into the same space in this way is novel, and makes object recognition more straightforward. Each dimension of the space corresponds to an image from the database. The coordinates of an image segment(region) are calculated based on its distance to the closest segment within each of the images, while the coordinates of a label are generated based on their association with the images. As a result, similar image segments associated with the same objects are clustered together in this feature space, and should also be close to the labels representing the object. The link between image regions and words can be discovered from their separation in the feature space. The algorithm is applied to an image collection and preliminary results are encouraging.
Object Recognition, Image Auto-Annotation
29-35
Tang, Jiayu
4f9409ac-830d-4937-867d-e06c76b8a4e1
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
2007
Tang, Jiayu
4f9409ac-830d-4937-867d-e06c76b8a4e1
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Tang, Jiayu and Lewis, Paul H.
(2007)
An Image Based Feature Space and Mapping for Linking Regions and Words.
2nd International Conference on Computer Vision Theory and Applications (VISAPP), Barcelona, Spain.
08 - 11 Mar 2007.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
We propose an image based feature space and define a mapping of both image regions and textual labels into that space. We believe the embedding of both image regions and labels into the same space in this way is novel, and makes object recognition more straightforward. Each dimension of the space corresponds to an image from the database. The coordinates of an image segment(region) are calculated based on its distance to the closest segment within each of the images, while the coordinates of a label are generated based on their association with the images. As a result, similar image segments associated with the same objects are clustered together in this feature space, and should also be close to the labels representing the object. The link between image regions and words can be discovered from their separation in the feature space. The algorithm is applied to an image collection and preliminary results are encouraging.
Text
129_Tang.pdf
- Other
More information
Published date: 2007
Additional Information:
Event Dates: March 8-11
Venue - Dates:
2nd International Conference on Computer Vision Theory and Applications (VISAPP), Barcelona, Spain, 2007-03-08 - 2007-03-11
Keywords:
Object Recognition, Image Auto-Annotation
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 263691
URI: http://eprints.soton.ac.uk/id/eprint/263691
PURE UUID: 81d13350-004b-4bc7-86c3-c561b83f83ce
Catalogue record
Date deposited: 13 Mar 2007
Last modified: 14 Mar 2024 07:36
Export record
Contributors
Author:
Jiayu Tang
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