Head pose estimation via background removal

Authors:
Bingpeng Ma;Xu Yang;Shiguang Shan
Affiliations:
GREYC --- CNRS UMR 6072, University of Caen Basse-Normandie, Caen, France;School of Computer Science and Technology, Huazhong University of Science and Technology, China;Visual Information Processing and Learning (VIPL) Group, Institute of Computing Technology, Chinese Academy of Sciences (CAS), China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 9
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Head Pose Estimation using Fisher Manifold Learning

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Head Pose Estimation in Computer Vision: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-PIE

Image and Vision Computing
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Head Yaw Estimation From Asymmetry of Facial Appearance

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.00

Visualization

Abstract

In many applications, head pose estimation plays a very important role. Images with the large pose angle usually contain a proportion of the background which degenerate the performance of head pose estimation. In this paper, we propose a novel method to eliminate the influence of the background. An additional dataset with labeled background is introduced to benefit the head pose estimation. For the input image, several neighbors are first determined from the additional dataset, and then the background of this image can be estimated from the background of these neighbors. After determining the background of each image, the face region will be re-cropped. By this way, the background can be reduced greatly. The proposed method is evaluated on three datasets, MultiPIE, CAS-PEAL and our own database Multi-Pose. The promising results show that our method can improve the performance of head pose estimation significantly.