Robust eye center localization based on an improved SVR method

Zhiyong Wang; Haibin Cai; Honghai Liu

doi:10.1007/978-3-030-04239-4_56

Robust eye center localization based on an improved SVR method

Zhiyong Wang, Haibin Cai, Honghai Liu^*

^*Corresponding author for this work

School of Computing

Shanghai Jiao Tong University

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

187 Downloads (Pure)

Abstract

Eye center localization is an important technique in gaze estimation, human computer interaction, virtual reality, etc., which attracts a lot of attention. Although a great deal of progress has been achieved over the past few years, the accuracy declines dramatically due to the low input image resolution, poor lighting conditions, side face, and eyes status such as closed or covered. To handle this issue, this paper proposes an improved support vector regression (SVR) method to detect the eye center based on the facial feature localization. Several image processing techniques were tried to improve the accuracy, and results showed that the SVR combining a Gaussian filter could get a better accuracy.

Original language	English
Title of host publication	Neural Information Processing - 25th International Conference, ICONIP 2018, Proceedings
Editors	Seiichi Ozawa, Andrew Chi Sing Leung, Long Cheng
Publisher	Springer
Pages	623-634
Number of pages	12
ISBN (Electronic)	978-3-030-04239-4
ISBN (Print)	978-3-030-04238-7
DOIs	https://doi.org/10.1007/978-3-030-04239-4_56
Publication status	Published - 18 Nov 2018
Event	25th International Conference on Neural Information Processing - Siem Reap, Cambodia Duration: 13 Dec 2018 → 16 Dec 2018

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	11307
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	25th International Conference on Neural Information Processing
Abbreviated title	ICONIP 2018
Country/Territory	Cambodia
City	Siem Reap
Period	13/12/18 → 16/12/18

Keywords

Eye center localization
Gaussian filter
SVR

Access to Document

10.1007/978-3-030-04239-4_56

Robust Eye Center Localization Based on An Improved SVR Method
The final authenticated version is available online at: http://dx.doi.org/10.1007%2F978-3-030-04239-4_56.
Accepted author manuscript (Post-print), 26.1 MB

Cite this

@inproceedings{b929b466405b45248be0e09523ad0204,

title = "Robust eye center localization based on an improved SVR method",

abstract = "Eye center localization is an important technique in gaze estimation, human computer interaction, virtual reality, etc., which attracts a lot of attention. Although a great deal of progress has been achieved over the past few years, the accuracy declines dramatically due to the low input image resolution, poor lighting conditions, side face, and eyes status such as closed or covered. To handle this issue, this paper proposes an improved support vector regression (SVR) method to detect the eye center based on the facial feature localization. Several image processing techniques were tried to improve the accuracy, and results showed that the SVR combining a Gaussian filter could get a better accuracy.",

keywords = "Eye center localization, Gaussian filter, SVR",

author = "Zhiyong Wang and Haibin Cai and Honghai Liu",

year = "2018",

month = nov,

day = "18",

doi = "10.1007/978-3-030-04239-4_56",

language = "English",

isbn = "978-3-030-04238-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "623--634",

editor = "Seiichi Ozawa and Leung, {Andrew Chi Sing} and Long Cheng",

booktitle = "Neural Information Processing - 25th International Conference, ICONIP 2018, Proceedings",

address = "Netherlands",

note = "25th International Conference on Neural Information Processing, ICONIP 2018 ; Conference date: 13-12-2018 Through 16-12-2018",

}

Wang, Z, Cai, H & Liu, H 2018, Robust eye center localization based on an improved SVR method. in S Ozawa, ACS Leung & L Cheng (eds), Neural Information Processing - 25th International Conference, ICONIP 2018, Proceedings. Lecture Notes in Computer Science, vol. 11307, Springer, pp. 623-634, 25th International Conference on Neural Information Processing, Siem Reap, Cambodia, 13/12/18. https://doi.org/10.1007/978-3-030-04239-4_56

Robust eye center localization based on an improved SVR method. / Wang, Zhiyong; Cai, Haibin; Liu, Honghai.
Neural Information Processing - 25th International Conference, ICONIP 2018, Proceedings. ed. / Seiichi Ozawa; Andrew Chi Sing Leung; Long Cheng. Springer, 2018. p. 623-634 (Lecture Notes in Computer Science; Vol. 11307).

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

TY - GEN

T1 - Robust eye center localization based on an improved SVR method

AU - Wang, Zhiyong

AU - Cai, Haibin

AU - Liu, Honghai

PY - 2018/11/18

Y1 - 2018/11/18

N2 - Eye center localization is an important technique in gaze estimation, human computer interaction, virtual reality, etc., which attracts a lot of attention. Although a great deal of progress has been achieved over the past few years, the accuracy declines dramatically due to the low input image resolution, poor lighting conditions, side face, and eyes status such as closed or covered. To handle this issue, this paper proposes an improved support vector regression (SVR) method to detect the eye center based on the facial feature localization. Several image processing techniques were tried to improve the accuracy, and results showed that the SVR combining a Gaussian filter could get a better accuracy.

AB - Eye center localization is an important technique in gaze estimation, human computer interaction, virtual reality, etc., which attracts a lot of attention. Although a great deal of progress has been achieved over the past few years, the accuracy declines dramatically due to the low input image resolution, poor lighting conditions, side face, and eyes status such as closed or covered. To handle this issue, this paper proposes an improved support vector regression (SVR) method to detect the eye center based on the facial feature localization. Several image processing techniques were tried to improve the accuracy, and results showed that the SVR combining a Gaussian filter could get a better accuracy.

KW - Eye center localization

KW - Gaussian filter

KW - SVR

UR - http://www.scopus.com/inward/record.url?scp=85059040211&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-04239-4_56

DO - 10.1007/978-3-030-04239-4_56

M3 - Conference contribution

AN - SCOPUS:85059040211

SN - 978-3-030-04238-7

T3 - Lecture Notes in Computer Science

SP - 623

EP - 634

BT - Neural Information Processing - 25th International Conference, ICONIP 2018, Proceedings

A2 - Ozawa, Seiichi

A2 - Leung, Andrew Chi Sing

A2 - Cheng, Long

PB - Springer

T2 - 25th International Conference on Neural Information Processing

Y2 - 13 December 2018 through 16 December 2018

ER -

Robust eye center localization based on an improved SVR method

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this