Creating invariance to "nuisance parameters" in face recognition

Advanced search
Browse by:

Department | Year

UCL Theses | Latest

Deposit your research

Creating invariance to "nuisance parameters" in face recognition

Prince, S.J.D.; Elder, J.H.; (2005) Creating invariance to "nuisance parameters" in face recognition. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 05). (pp. pp. 446-453). IEEE Green open access

Preview

PDF
13425.pdf
Download (587kB)

Abstract

A major goal for face recognition is to identify faces where the pose of the probe is different from the stored face. Typical feature vectors vary more with pose than with identity, leading to very poor recognition performance. We propose a non-linear many-to-one mapping from a conventional feature space to a new space constructed so that each individual has a unique feature vector regardless of pose. Training data is used to implicitly parameterize the position of the multi-dimensional face manifold by pose. We introduce a co-ordinate transform, which depends on the position on the manifold. This transform is chosen so that different poses of the same face are mapped to the same feature vector. The same approach is applied to illumination changes. We investigate different methods for creating features, which are invariant to both pose and illumination. We provide a metric to assess the discriminability of the resulting features. Our technique increases the discriminability of faces under unknown pose and lighting compared to contemporary methods.

Type:	Proceedings paper
Title:	Creating invariance to "nuisance parameters" in face recognition
Open access status:	An open access version is available from UCL Discovery
DOI:	10.1109/CVPR.2005.116
Publisher version:	http://dx.doi.org/10.1109/CVPR.2005.116
Language:	English
Additional information:	©2005 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
URI:	https://discovery.ucl.ac.uk/id/eprint/13425