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 proceedingConference contribution

133 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 languageEnglish
Title of host publicationProceedings of the 2015 International Conference on Machine Learning and Cybernetics (ICMLC)
PublisherIEEE
Pages759-764
ISBN (Electronic)978-1-4673-7221-3
DOIs
Publication statusPublished - 3 Dec 2015
Event14th International Conference on Machine Learning and Cybernetics - Holiday Inn Guangzhou Shifu, Guangzhou, China
Duration: 11 Jul 201514 Jul 2015
http://www.icmlc.com/ICMLC/formerICMLC_2015.html
http://www.icmlc.com/ICMLC/formerICMLC.html

Conference

Conference14th International Conference on Machine Learning and Cybernetics
Abbreviated titleICMLC 2015
Country/TerritoryChina
CityGuangzhou
Period11/07/1514/07/15
Internet address

Fingerprint

Dive into the research topics of 'Convolution-based means of gradient for fast eye center localization'. Together they form a unique fingerprint.

Cite this