Phase space for face pose estimation

Authors:
Jacob Foytik;Vijayan K. Asari;R. Cortland Tompkins;Menatoallah Youssef
Affiliations:
Computer Vision and Wide Area Surveillance Laboratory, Department of Electrical and Computer Engineering, University of Dayton, Dayton, Ohio;Computer Vision and Wide Area Surveillance Laboratory, Department of Electrical and Computer Engineering, University of Dayton, Dayton, Ohio;Computer Vision and Wide Area Surveillance Laboratory, Department of Electrical and Computer Engineering, University of Dayton, Dayton, Ohio;Computer Vision and Wide Area Surveillance Laboratory, Department of Electrical and Computer Engineering, University of Dayton, Dayton, Ohio
Venue:
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
Year:
2010

Citing 5
Cited 1

Head Pose Estimation using Fisher Manifold Learning

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Robust Head Pose Estimation Using LGBP

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Head Pose Estimation in Computer Vision: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Facial recognition using multisensor images based on localized kernel eigen spaces

IEEE Transactions on Image Processing

A Two-Layer Framework for Piecewise Linear Manifold-Based Head Pose Estimation

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Face pose estimation from standard imagery remains a complex computer vision problemthat requires identifying the primary modes of variance directly corresponding to pose variation, while ignoring variance due to face identity and other noise factors. Conventional methods either fail to extract the salient pose defining features, or require complex embedding operations. We propose a new method for pose estimation that exploits oriented Phase Congruency (PC) features and Canonical Correlation Analysis (CCA) to define a latent pose-sensitive subspace. The oriented PC features serve to mitigate illumination and identity features present in the imagery, while highlighting alignment and pose features necessary for estimation. The proposed system is tested using the Pointing'04 face database and is shown to provide better estimation accuracy than similar methods including Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and conventional CCA.