Robust Eye Centre Extraction using the Hough Transform
Robust Eye Centre Extraction using the Hough Transform
Finding the eyes is an important stage of feature extraction in automatic face recognition. Current approaches include standard feature extraction techniques using heuristic methods specifically developed for human eyes. We present a new method for finding eye centres using a gradient decomposed Hough Transform (HT) which embodies the natural concentricity of the eye region in a peak reinforcement scheme to improve accuracy and robustness. This enhances a standard feature extraction technique with an analytic approach, which can be applied to the whole face without priming of estimates of eye position and size. In a database of 54 eyes this new method is shown to be less constrained, more robust and resulted in a three-fold improvement in accuracy over using the standard HT.
3--9
Benn, D.E.
db256e1d-07c4-4f78-aafe-86a2e52c0df4
Nixon, M.S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, J.N.
e05be2f9-991d-4476-bb50-ae91606389da
Bigun, J.
426f3c4f-8e71-419e-9a5d-bd42a3d1ae42
Chollet, G.
d2b8b544-e1c2-4378-a35a-36adb111bdf9
Borgefors, G.
c6fe8668-ca25-4585-a6a0-d97f24567ddf
March 1997
Benn, D.E.
db256e1d-07c4-4f78-aafe-86a2e52c0df4
Nixon, M.S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Carter, J.N.
e05be2f9-991d-4476-bb50-ae91606389da
Bigun, J.
426f3c4f-8e71-419e-9a5d-bd42a3d1ae42
Chollet, G.
d2b8b544-e1c2-4378-a35a-36adb111bdf9
Borgefors, G.
c6fe8668-ca25-4585-a6a0-d97f24567ddf
Benn, D.E., Nixon, M.S. and Carter, J.N.
(1997)
Robust Eye Centre Extraction using the Hough Transform.
Bigun, J., Chollet, G. and Borgefors, G.
(eds.)
Proceedings of 1st Int. Conf. on Audio- and Video-Based Biometric Person Authentication.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
Finding the eyes is an important stage of feature extraction in automatic face recognition. Current approaches include standard feature extraction techniques using heuristic methods specifically developed for human eyes. We present a new method for finding eye centres using a gradient decomposed Hough Transform (HT) which embodies the natural concentricity of the eye region in a peak reinforcement scheme to improve accuracy and robustness. This enhances a standard feature extraction technique with an analytic approach, which can be applied to the whole face without priming of estimates of eye position and size. In a database of 54 eyes this new method is shown to be less constrained, more robust and resulted in a three-fold improvement in accuracy over using the standard HT.
Text
benneyet.pdf
- Other
More information
Published date: March 1997
Additional Information:
Organisation: IAPR Address: Berlin
Venue - Dates:
Proceedings of 1st Int. Conf. on Audio- and Video-Based Biometric Person Authentication, 1997-03-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 250039
URI: http://eprints.soton.ac.uk/id/eprint/250039
PURE UUID: 13db16c9-3b4e-48a1-96b5-2b063e17e3b4
Catalogue record
Date deposited: 04 May 1999
Last modified: 15 Mar 2024 02:34
Export record
Contributors
Author:
D.E. Benn
Author:
J.N. Carter
Editor:
J. Bigun
Editor:
G. Chollet
Editor:
G. Borgefors
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
