Local Linear Regression (LLR) for Pose Invariant Face Recognition

Authors:
Xiujuan Chai;Shiguang Shan;Xilin Chen;Wen Gao
Affiliations:
Harbin Institute of Technology, China;Institute of Computing Technology, China;Institute of Computing Technology, China;Harbin Institute of Technology, China
Venue:
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Year:
2006

Citing 0
Cited 7

Expression-invariant face recognition with constrained optical flow warping

IEEE Transactions on Multimedia
Discrete sine transform and alternative local linear regression for face recognition

SPPRA '08 Proceedings of the Fifth IASTED International Conference on Signal Processing, Pattern Recognition and Applications
Pose manifold curvature is typically less near frontal face views

BTAS'09 Proceedings of the 3rd IEEE international conference on Biometrics: Theory, applications and systems
An evaluation of video-to-video face verification

IEEE Transactions on Information Forensics and Security
3D model-based face recognition in video

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Pose-robust face recognition via sparse representation

Pattern Recognition
Multi-resolution feature fusion for face recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The variation of facial appearance due to the viewpoint (/pose) degrades face recognition systems considerably, which is well known as one of the bottlenecks in face recognition. One of the possible solutions is generating virtual frontal view from any given non-frontal view to obtain a virtual gallery / probe face. By formulating this kind of solutions as a prediction problem, this paper proposes a simple but efficient novel Local Linear Regression (LLR) method, which can generate the virtual frontal view from a given non-frontal face image. The proposed LLR inspires from the observation that the corresponding local facial regions of the frontal and non-frontal view pair satisfy linear assumption much better than the whole face region. This can be explained easily by the fact that a 3D face shape is composed of many local planar surfaces, which satisfy naturally linear model under imaging projection. In LLR, we simply partition the whole non-frontal face image into multiple local patches and apply linear regression to each patch for the prediction of its virtual frontal patch. Comparing with other methods, the experimental results on CMU PIE database show distinct advantage of the proposed method.