DMCA
Coupled bias-variance tradeoff for crosspose face recognition (2012)
| Venue: | IEEE Transactions on Image Processing |
| Citations: | 13 - 0 self |
BibTeX
@ARTICLE{Li12coupledbias-variance,
author = {Annan Li and Shiguang Shan and Wen Gao},
title = {Coupled bias-variance tradeoff for crosspose face recognition},
journal = {IEEE Transactions on Image Processing},
year = {2012},
pages = {305--315}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—Subspace-based face representation can be looked as a regression problem. From this viewpoint, we first revisited the problem of recognizing faces across pose differences, which is a bottleneck in face recognition. Then, we propose a new approach for cross-pose face recognition using a regressor with a coupled bias–variance tradeoff. We found that striking a coupled balance between bias and variance in regression for different poses could improve the regressor-based cross-pose face representation, i.e., the regressor can be more stable against a pose difference. With the basic idea, ridge regression and lasso regression are explored. Experimental results on CMU PIE, the FERET, and the Multi-PIE face databases show that the proposed bias–variance tradeoff can achieve considerable reinforcement in recognition performance. Index Terms—Bias–variance tradeoff, face recognition, LASSO regression, pose differences, ridge regression.
Keyphrases
pose difference crosspose face recognition bias-variance tradeoff face recognition lasso regression regressor-based cross-pose face representation recognition performance cross-pose face recognition cmu pie coupled bias variance tradeoff bias variance tradeoff considerable reinforcement abstract subspace-based face representation new approach ridge regression basic idea index term bias variance tradeoff different pose experimental result multi-pie face regression problem
