Maximizing intra-individual correlations for face recognition across pose differences

The variations of pose lead to significant performance decline in face recognition systems, which is a bottleneck in face recognition. A key problem is how to measure the similarity between two image vectors of unequal length that viewed from different pose. In this paper, we propose a novel approac...

Full description

Saved in:
Bibliographic Details
Published in2009 IEEE Conference on Computer Vision and Pattern Recognition pp. 605 - 611
Main Authors Annan Li, Shiguang Shan, Xilin Chen, Wen Gao
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2009
Subjects
Computers
Content addressable storage
Ellipsoids
Face recognition
Geometry
Information processing
Length measurement
Robustness
Shape
Online AccessGet full text

Cover

More Information
Summary:The variations of pose lead to significant performance decline in face recognition systems, which is a bottleneck in face recognition. A key problem is how to measure the similarity between two image vectors of unequal length that viewed from different pose. In this paper, we propose a novel approach for pose robust face recognition, in which the similarity is measured by correlations in a media subspace between different poses on patch level. The media subspace is constructed by canonical correlation analysis, such that the intra-individual correlations are maximized. Based on the media subspace two recognition approaches are developed. In the first, we transform non-frontal face into frontal for recognition. And in the second, we perform recognition in the media subspace with probabilistic modeling. The experimental results on FERET database demonstrate the efficiency of our approach.
ISBN:1424439922
9781424439928
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2009.5206659