Compensating for ensemble-specific effects when building facial models

When attempting to code faces for modelling or recognition, estimates of dimensions are typically obtained from an ensemble. These tend to be significantly sub-optimal. Firstly, ensembles are rarely balanced with regard to identity and expression. This can be overcome by dividing the ensemble by typ...

Full description

Saved in:
Bibliographic Details
Published in:Image and vision computing 2002-08, Vol.20 (9), p.673-682
Main Authors: Costen, N.P., Cootes, T.F., Taylor, C.J.
Format: Article
Language:English
Subjects:
Appearance models
Dimensionality estimation
Face recognition
PCA
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:When attempting to code faces for modelling or recognition, estimates of dimensions are typically obtained from an ensemble. These tend to be significantly sub-optimal. Firstly, ensembles are rarely balanced with regard to identity and expression. This can be overcome by dividing the ensemble by type of variation and rotating sub-spaces relative to one another. Secondly, each face contains both predictable and non-predictable qualities; only the predictable aspects are useful for defining coding systems for other faces. Variance-based methods of defining codes (PCA) will provide eigenvectors, which are themselves potential faces. Predictable aspects will induce eigenvectors with comparable levels of spatial redundancy to the ensemble. We show that this gives relatively short and consistent codes, and allows fast and accurate fitting of codes to faces.
ISSN:0262-8856
1872-8138
DOI:10.1016/S0262-8856(02)00057-4