Convolution-based means of gradient for fast eye center localization

Haibin Cai; Hui Yu; C. Y. Yao; S. Y. Chen; Honghai Liu

doi:10.1109/ICMLC.2015.7340650

Convolution-based means of gradient for fast eye center localization

Haibin Cai, Hui Yu, C. Y. Yao, S. Y. Chen, Honghai Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

188 Downloads (Pure)

Abstract

Localizing eye center is primary challenge for application-s involving gaze estimation, face recognition and human machine interaction. The challenge is caused by significant variability of eye appearance in illumination, shape, color, viewing angle and dynamics, and computation related issues. In this paper, we propose a convolution-based means of gradient method to efficiently and accurately locate the eye center in low resolution images. Priority of enhancing its computation is achieved by the use of FFT transform and fewer identified pixels of circular boundary of potential eye centres. The proposed algorithm is validated in the research database platform of BioID face database. The experimental results confirm that the proposed outperforms the-state-of-art methods and its potential in real-time eye gaze tracking related applications.

Original language	English
Title of host publication	Proceedings of the 2015 International Conference on Machine Learning and Cybernetics (ICMLC)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	759-764
ISBN (Electronic)	978-1-4673-7221-3
DOIs	https://doi.org/10.1109/ICMLC.2015.7340650
Publication status	Published - 3 Dec 2015
Event	14th International Conference on Machine Learning and Cybernetics - Holiday Inn Guangzhou Shifu, Guangzhou, China Duration: 11 Jul 2015 → 14 Jul 2015 http://www.icmlc.com/ICMLC/formerICMLC_2015.html http://www.icmlc.com/ICMLC/formerICMLC.html

Conference

Conference	14th International Conference on Machine Learning and Cybernetics
Abbreviated title	ICMLC 2015
Country/Territory	China
City	Guangzhou
Period	11/07/15 → 14/07/15
Internet address	http://www.icmlc.com/ICMLC/formerICMLC_2015.html http://www.icmlc.com/ICMLC/formerICMLC.html

Access to Document

10.1109/ICMLC.2015.7340650

convolution-based means of gradient for gast eye center localization
© © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 897 KB

http://ieeexplore.ieee.org/abstract/document/7340650/

Cite this

@inproceedings{c5eba029571d42e4a3f0c5b14e5b39a3,

title = "Convolution-based means of gradient for fast eye center localization",

abstract = "Localizing eye center is primary challenge for application-s involving gaze estimation, face recognition and human machine interaction. The challenge is caused by significant variability of eye appearance in illumination, shape, color, viewing angle and dynamics, and computation related issues. In this paper, we propose a convolution-based means of gradient method to efficiently and accurately locate the eye center in low resolution images. Priority of enhancing its computation is achieved by the use of FFT transform and fewer identified pixels of circular boundary of potential eye centres. The proposed algorithm is validated in the research database platform of BioID face database. The experimental results confirm that the proposed outperforms the-state-of-art methods and its potential in real-time eye gaze tracking related applications.",

author = "Haibin Cai and Hui Yu and Yao, {C. Y.} and Chen, {S. Y.} and Honghai Liu",

year = "2015",

month = dec,

day = "3",

doi = "10.1109/ICMLC.2015.7340650",

language = "English",

pages = "759--764",

booktitle = "Proceedings of the 2015 International Conference on Machine Learning and Cybernetics (ICMLC)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "14th International Conference on Machine Learning and Cybernetics, ICMLC 2015 ; Conference date: 11-07-2015 Through 14-07-2015",

url = "http://www.icmlc.com/ICMLC/formerICMLC_2015.html, http://www.icmlc.com/ICMLC/formerICMLC.html",

}

Cai, H, Yu, H, Yao, CY, Chen, SY & Liu, H 2015, Convolution-based means of gradient for fast eye center localization. in Proceedings of the 2015 International Conference on Machine Learning and Cybernetics (ICMLC). Institute of Electrical and Electronics Engineers Inc., pp. 759-764, 14th International Conference on Machine Learning and Cybernetics, Guangzhou, China, 11/07/15. https://doi.org/10.1109/ICMLC.2015.7340650

TY - GEN

T1 - Convolution-based means of gradient for fast eye center localization

AU - Cai, Haibin

AU - Yu, Hui

AU - Yao, C. Y.

AU - Chen, S. Y.

AU - Liu, Honghai

PY - 2015/12/3

Y1 - 2015/12/3

N2 - Localizing eye center is primary challenge for application-s involving gaze estimation, face recognition and human machine interaction. The challenge is caused by significant variability of eye appearance in illumination, shape, color, viewing angle and dynamics, and computation related issues. In this paper, we propose a convolution-based means of gradient method to efficiently and accurately locate the eye center in low resolution images. Priority of enhancing its computation is achieved by the use of FFT transform and fewer identified pixels of circular boundary of potential eye centres. The proposed algorithm is validated in the research database platform of BioID face database. The experimental results confirm that the proposed outperforms the-state-of-art methods and its potential in real-time eye gaze tracking related applications.

AB - Localizing eye center is primary challenge for application-s involving gaze estimation, face recognition and human machine interaction. The challenge is caused by significant variability of eye appearance in illumination, shape, color, viewing angle and dynamics, and computation related issues. In this paper, we propose a convolution-based means of gradient method to efficiently and accurately locate the eye center in low resolution images. Priority of enhancing its computation is achieved by the use of FFT transform and fewer identified pixels of circular boundary of potential eye centres. The proposed algorithm is validated in the research database platform of BioID face database. The experimental results confirm that the proposed outperforms the-state-of-art methods and its potential in real-time eye gaze tracking related applications.

U2 - 10.1109/ICMLC.2015.7340650

DO - 10.1109/ICMLC.2015.7340650

M3 - Conference contribution

SP - 759

EP - 764

BT - Proceedings of the 2015 International Conference on Machine Learning and Cybernetics (ICMLC)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Machine Learning and Cybernetics

Y2 - 11 July 2015 through 14 July 2015

ER -

Convolution-based means of gradient for fast eye center localization

Abstract

Conference

Access to Document

Fingerprint

Cite this