Coupled Bias–Variance Tradeoff for Cross-Pose Face Recognition

Authors:
Annan Li;Shiguang Shan;Wen Gao
Affiliations:
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Institute of Digital Media, Peking University, Beijing, China
Venue:
IEEE Transactions on Image Processing
Year:
2012

Citing 0
Cited 4

Orthogonal discriminant vector for face recognition across pose

Pattern Recognition
Robust pose invariant face recognition using coupled latent space discriminant analysis

Computer Vision and Image Understanding
A sparse representation method of bimodal biometrics and palmprint recognition experiments

Neurocomputing
Regularized latent least square regression for cross pose face recognition

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence

Quantified Score

Hi-index	0.01

Visualization

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.