Estimating Head Orientation Using a Combination of Multiple Cues

Bima Sena Bayu DEWANTARA; Jun MIURA

doi:10.1587/transinf.2015EDP7375

Estimating Head Orientation Using a Combination of Multiple Cues

Bima Sena Bayu DEWANTARA, Jun MIURA

Full Text Views

0

Cite this

Summary :

This paper proposes an appearance-based novel descriptor for estimating head orientation. Our descriptor is inspired by the Weber-based feature, which has been successfully implemented for robust texture analysis, and the gradient which performs well for shape analysis. To further enhance the orientation differences, we combine them with an analysis of the intensity deviation. The position of a pixel and its intrinsic intensity are also considered. All features are then composed as a feature vector of a pixel. The information carried by each pixel is combined using a covariance matrix to alleviate the influence caused by rotations and illumination. As the result, our descriptor is compact and works at high speed. We also apply a weighting scheme, called Block Importance Feature using Genetic Algorithm (BIF-GA), to improve the performance of our descriptor by selecting and accentuating the important blocks. Experiments on three head pose databases demonstrate that the proposed method outperforms the current state-of-the-art methods. Also, we can extend the proposed method by combining it with a head detection and tracking system to enable it to estimate human head orientation in real applications.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.6 pp.1603-1614

Publication Date: 2016/06/01

Publicized: 2016/03/03

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDP7375

Type of Manuscript: PAPER

Category: Human-computer Interaction

Authors

Bima Sena Bayu DEWANTARA
Toyohashi University of Technology
Jun MIURA
Toyohashi University of Technology

Keyword

human head orientation, Weber feature, gradient, intensity deviation, covariance, block importance feature, head detection and tracking

Cite this

Copy

Bima Sena Bayu DEWANTARA, Jun MIURA, "Estimating Head Orientation Using a Combination of Multiple Cues" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 6, pp. 1603-1614, June 2016, doi: 10.1587/transinf.2015EDP7375.
Abstract: This paper proposes an appearance-based novel descriptor for estimating head orientation. Our descriptor is inspired by the Weber-based feature, which has been successfully implemented for robust texture analysis, and the gradient which performs well for shape analysis. To further enhance the orientation differences, we combine them with an analysis of the intensity deviation. The position of a pixel and its intrinsic intensity are also considered. All features are then composed as a feature vector of a pixel. The information carried by each pixel is combined using a covariance matrix to alleviate the influence caused by rotations and illumination. As the result, our descriptor is compact and works at high speed. We also apply a weighting scheme, called Block Importance Feature using Genetic Algorithm (BIF-GA), to improve the performance of our descriptor by selecting and accentuating the important blocks. Experiments on three head pose databases demonstrate that the proposed method outperforms the current state-of-the-art methods. Also, we can extend the proposed method by combining it with a head detection and tracking system to enable it to estimate human head orientation in real applications.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7375/_p

Copy

@ARTICLE{e99-d_6_1603,
author={Bima Sena Bayu DEWANTARA, Jun MIURA, },
journal={IEICE TRANSACTIONS on Information},
title={Estimating Head Orientation Using a Combination of Multiple Cues},
year={2016},
volume={E99-D},
number={6},
pages={1603-1614},
abstract={This paper proposes an appearance-based novel descriptor for estimating head orientation. Our descriptor is inspired by the Weber-based feature, which has been successfully implemented for robust texture analysis, and the gradient which performs well for shape analysis. To further enhance the orientation differences, we combine them with an analysis of the intensity deviation. The position of a pixel and its intrinsic intensity are also considered. All features are then composed as a feature vector of a pixel. The information carried by each pixel is combined using a covariance matrix to alleviate the influence caused by rotations and illumination. As the result, our descriptor is compact and works at high speed. We also apply a weighting scheme, called Block Importance Feature using Genetic Algorithm (BIF-GA), to improve the performance of our descriptor by selecting and accentuating the important blocks. Experiments on three head pose databases demonstrate that the proposed method outperforms the current state-of-the-art methods. Also, we can extend the proposed method by combining it with a head detection and tracking system to enable it to estimate human head orientation in real applications.},
keywords={},
doi={10.1587/transinf.2015EDP7375},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Estimating Head Orientation Using a Combination of Multiple Cues
T2 - IEICE TRANSACTIONS on Information
SP - 1603
EP - 1614
AU - Bima Sena Bayu DEWANTARA
AU - Jun MIURA
PY - 2016
DO - 10.1587/transinf.2015EDP7375
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2016
AB - This paper proposes an appearance-based novel descriptor for estimating head orientation. Our descriptor is inspired by the Weber-based feature, which has been successfully implemented for robust texture analysis, and the gradient which performs well for shape analysis. To further enhance the orientation differences, we combine them with an analysis of the intensity deviation. The position of a pixel and its intrinsic intensity are also considered. All features are then composed as a feature vector of a pixel. The information carried by each pixel is combined using a covariance matrix to alleviate the influence caused by rotations and illumination. As the result, our descriptor is compact and works at high speed. We also apply a weighting scheme, called Block Importance Feature using Genetic Algorithm (BIF-GA), to improve the performance of our descriptor by selecting and accentuating the important blocks. Experiments on three head pose databases demonstrate that the proposed method outperforms the current state-of-the-art methods. Also, we can extend the proposed method by combining it with a head detection and tracking system to enable it to estimate human head orientation in real applications.
ER -