DMCA
Maximizing Intraindividual Correlations for Face Recognition Across Pose Differences
| Venue: | IEEE CVPR |
| Citations: | 14 - 3 self |
BibTeX
@ARTICLE{Li_maximizingintraindividual,
author = {Annan Li and Shiguang Shan and Xilin Chen and Wen Gao},
title = {Maximizing Intraindividual Correlations for Face Recognition Across Pose Differences},
journal = {IEEE CVPR},
year = {},
pages = {605--611}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
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. 1.
Keyphrases
face recognition across pose difference medium subspace intraindividual correlation different pose image vector pose robust face recognition face recognition patch level key problem intra-individual correlation significant performance decline probabilistic modeling feret database face recognition system non-frontal face novel approach canonical correlation analysis experimental result unequal length pose lead recognition approach
