Robust 2D Ear Registration and Recognition Based on SIFT Point Matching
Robust 2D Ear Registration and Recognition Based on SIFT Point Matching
Significant recent progress has shown ear recognition to be a viable biometric. Good recognition rates have been demonstrated under controlled conditions, using manual registration or with specialised equipment. This paper describes a new technique which improves the robustness of ear registration and recognition, addressing issues of pose variation, background clutter and occlusion. By treating the ear as a planar surface and creating a homography transform using SIFT feature matches, ears can be registered accurately. The feature matches reduce the gallery size and enable a precise ranking using a simple 2D distance algorithm. When applied to the XM2VTS database it gives results comparable to PCA with manual registration. Further analysis on more challenging datasets demonstrates the technique to be robust to background clutter, viewing angles up to ±13 degrees and with over 20% occlusion.
Bustard, John D.
887e9ccd-fbc1-4f39-8d99-209c3c7386a3
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
29 September 2008
Bustard, John D.
887e9ccd-fbc1-4f39-8d99-209c3c7386a3
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Bustard, John D. and Nixon, Mark
(2008)
Robust 2D Ear Registration and Recognition Based on SIFT Point Matching.
BTAS 2008.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Significant recent progress has shown ear recognition to be a viable biometric. Good recognition rates have been demonstrated under controlled conditions, using manual registration or with specialised equipment. This paper describes a new technique which improves the robustness of ear registration and recognition, addressing issues of pose variation, background clutter and occlusion. By treating the ear as a planar surface and creating a homography transform using SIFT feature matches, ears can be registered accurately. The feature matches reduce the gallery size and enable a precise ranking using a simple 2D distance algorithm. When applied to the XM2VTS database it gives results comparable to PCA with manual registration. Further analysis on more challenging datasets demonstrates the technique to be robust to background clutter, viewing angles up to ±13 degrees and with over 20% occlusion.
Text
Robust2DEarRegistrationAndRecognition.pdf
- Version of Record
More information
Published date: 29 September 2008
Venue - Dates:
BTAS 2008, 2008-09-29
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 266782
URI: http://eprints.soton.ac.uk/id/eprint/266782
PURE UUID: 1f65c3bb-cbea-4ab2-a202-550d23afa328
Catalogue record
Date deposited: 13 Oct 2008 10:20
Last modified: 15 Mar 2024 02:35
Export record
Contributors
Author:
John D. Bustard
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
