A Pre-filter Enabling Fast Frontal Face Detection
A Pre-filter Enabling Fast Frontal Face Detection
We present a novel pre-filtering technique that identifies probable frontal illuminated face regions in colour images regardless of translation, orientation, and scale. The face candidate regions are normalised and provide the basis for face verification using published face detection algorithms. The technique focuses on a fast search strategy to locate potential eye-pairs in an image or video frame. The eye-pair candidates indicate areas that may contain faces. Scale and orientation is inferred from the eye-pairs, and a neural network is used to confirm the normalised face candidates.
3-540-66079-8
777-84
Chan, Stephen C. Y.
ba1d8a6c-0bde-4597-b868-06b585af5172
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Huijsmans, Dionysius P.
4a536059-b90c-4273-8378-9f357d9b1a25
Smeulders, Arnold W. M.
549f269a-b55e-46a3-af05-959b051f3917
June 1999
Chan, Stephen C. Y.
ba1d8a6c-0bde-4597-b868-06b585af5172
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Huijsmans, Dionysius P.
4a536059-b90c-4273-8378-9f357d9b1a25
Smeulders, Arnold W. M.
549f269a-b55e-46a3-af05-959b051f3917
Chan, Stephen C. Y. and Lewis, Paul H.
(1999)
A Pre-filter Enabling Fast Frontal Face Detection.
Huijsmans, Dionysius P. and Smeulders, Arnold W. M.
(eds.)
Visual Information and Information Systems (VISUAL'99).
.
Record type:
Conference or Workshop Item
(Other)
Abstract
We present a novel pre-filtering technique that identifies probable frontal illuminated face regions in colour images regardless of translation, orientation, and scale. The face candidate regions are normalised and provide the basis for face verification using published face detection algorithms. The technique focuses on a fast search strategy to locate potential eye-pairs in an image or video frame. The eye-pair candidates indicate areas that may contain faces. Scale and orientation is inferred from the eye-pairs, and a neural network is used to confirm the normalised face candidates.
Archive
vis99.ps.gz
- Other
More information
Published date: June 1999
Additional Information:
Address: Berlin
Venue - Dates:
Visual Information and Information Systems (VISUAL'99), 1999-06-01
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 252540
URI: http://eprints.soton.ac.uk/id/eprint/252540
ISBN: 3-540-66079-8
PURE UUID: 3a1d0722-d65b-4594-aaa4-0f214d172000
Catalogue record
Date deposited: 16 Feb 2000
Last modified: 14 Mar 2024 05:19
Export record
Contributors
Author:
Stephen C. Y. Chan
Author:
Paul H. Lewis
Editor:
Dionysius P. Huijsmans
Editor:
Arnold W. M. Smeulders
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