DocumentCode :
3152514
Title :
Effective head pose estimation using Lie Algebrized Gaussians
Author :
Chunlong Hu ; Liyu Gong ; Tianjiang Wang ; Qi Feng
Author_Institution :
Sch. of Comput. Sci. & Technol., Huazhong Univ. of Sci. & Technol., Wuhan, China
fYear :
2013
fDate :
15-19 July 2013
Firstpage :
1
Lastpage :
6
Abstract :
Accurate head pose estimation is significant for many applications such as face recognition and human-computer interaction. In this paper, we treat the head pose estimation as a classification problem and employ the Lie Algebrized Gaussians (LAG) feature as the representation approach for head image. The LAG feature, which is built on Gausssian Mixture Model (GMM), has the capability to preserve the structure of Gaussian components in the original Lie group manifold. Moreover, to keep more spatial structure information of the image, LAG is operated on many subregions of the image. As a result, these properties of LAG enable it to reflect the pose characteristic of the head image well and possess powerful discriminative ability in pose classification. Experiments on CMU Pose, Illumination, and Expression (PIE) and Pointing´04 benchmarks show state-of-the-art performance and demonstrate that LAG represents the head pose characteristic well.
Keywords :
Gaussian processes; Lie algebras; feature extraction; image classification; image representation; pose estimation; CMU pose-illumination-expression; GMM; Gaussian components; Gaussian mixture model; LAG feature; Lie algebrized Gaussian feature; Lie group manifold; head image representation approach; head pose estimation; pose characteristic; pose classification; spatial structure information; Databases; Estimation; Face; Feature extraction; Kernel; Magnetic heads; GMM; LAG; classification; head pose estimation; image representation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo (ICME), 2013 IEEE International Conference on
Conference_Location :
San Jose, CA
ISSN :
1945-7871
Type :
conf
DOI :
10.1109/ICME.2013.6607533
Filename :
6607533
Link To Document :
بازگشت