Learning Patch Dependencies for Improved Pose Mismatched Face Verification

Authors:
Simon Lucey;Tsuhan Chen
Affiliations:
Carnegie Mellon University;Carnegie Mellon University
Venue:
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Year:
2006

Citing 0
Cited 8

Patch-based representation of visual speech

VisHCI '06 Proceedings of the HCSNet workshop on Use of vision in human-computer interaction - Volume 56
Face recognition using adaptively weighted patch PZM array from a single exemplar image per person

Pattern Recognition
A Viewpoint Invariant, Sparsely Registered, Patch Based, Face Verifier

International Journal of Computer Vision
Recognizing faces using Adaptively Weighted Sub-Gabor Array from a single sample image per enrolled subject

Image and Vision Computing
Probabilistic learning for fully automatic face recognition across pose

Image and Vision Computing
Towards pose-invariant 2D face classification for surveillance

AMFG'07 Proceedings of the 3rd international conference on Analysis and modeling of faces and gestures
Bayesian prior models for vehicle make and model recognition

Proceedings of the 7th International Conference on Frontiers of Information Technology
Cross-pose face recognition based on partial least squares

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Most pose robust face verification algorithms, which employ 2D appearance, rely heavily on statistics gathered from offline databases containing ample facial appearance variation across many views. Due to the high dimensionality of the face images being employed, the validity of the assumptions employed in obtaining these statistics are essential for good performance. In this paper we assess three common approaches in 2D appearance pose mismatched face recognition literature. In our experiments we demonstrate where these approaches work and fail. As a result of this analysis, we additionally propose a new algorithm that attempts to learn the statistical dependency between gallery patches (i.e. local regions of pixels) and the whole appearance of the probe image. We demonstrate improved performance over a number of leading 2D appearance face recognition algorithms.