Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface

In this paper, a real time, user independent eyeball tracking approach is presented. The system is implemented by using a low cost webcam. The robustness of the system is measured by several criteria such as users of different age where some of the users are wearing glasses under varying lighting co...

Full description

Bibliographic Details
Main Authors: Mokhtar, Norrima, Arof, Hamzah, Iwahashi, Masahiro
Format: Article
Published: ICIC International 2011
Subjects:
_version_ 1825718615887839232
author Mokhtar, Norrima
Arof, Hamzah
Iwahashi, Masahiro
author_facet Mokhtar, Norrima
Arof, Hamzah
Iwahashi, Masahiro
author_sort Mokhtar, Norrima
collection UM
description In this paper, a real time, user independent eyeball tracking approach is presented. The system is implemented by using a low cost webcam. The robustness of the system is measured by several criteria such as users of different age where some of the users are wearing glasses under varying lighting condition, pose, eye orientation and distance from camera. The size and location of the region of interest which contains both eyes are made adaptive. Derivative Dynamic Time Warping is chosen as the classifier for this experiment since it can match patterns from data sequences with different lengths. Finally, the results, advantages, limitations and future works of the proposed method are reported. The online eye tracking procedure shows good accuracy and robustness when processing online image sequences at 50 frames/s on a 253 GHz Pavilion DV4 HP notebook.
first_indexed 2024-03-06T05:07:08Z
format Article
id um.eprints-2057
institution Universiti Malaya
last_indexed 2024-03-06T05:07:08Z
publishDate 2011
publisher ICIC International
record_format dspace
spelling um.eprints-20572019-11-15T07:11:29Z http://eprints.um.edu.my/2057/ Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface Mokhtar, Norrima Arof, Hamzah Iwahashi, Masahiro TK Electrical engineering. Electronics Nuclear engineering In this paper, a real time, user independent eyeball tracking approach is presented. The system is implemented by using a low cost webcam. The robustness of the system is measured by several criteria such as users of different age where some of the users are wearing glasses under varying lighting condition, pose, eye orientation and distance from camera. The size and location of the region of interest which contains both eyes are made adaptive. Derivative Dynamic Time Warping is chosen as the classifier for this experiment since it can match patterns from data sequences with different lengths. Finally, the results, advantages, limitations and future works of the proposed method are reported. The online eye tracking procedure shows good accuracy and robustness when processing online image sequences at 50 frames/s on a 253 GHz Pavilion DV4 HP notebook. ICIC International 2011-07 Article PeerReviewed Mokhtar, Norrima and Arof, Hamzah and Iwahashi, Masahiro (2011) Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface. International Journal of InnovativeComputing, Information and Control, 7 (7B). pp. 4335-4346. ISSN 1349-4198, http://www.ijicic.org/contents.htm
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Mokhtar, Norrima
Arof, Hamzah
Iwahashi, Masahiro
Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface
title Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface
title_full Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface
title_fullStr Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface
title_full_unstemmed Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface
title_short Real Time Eyeball Tracking via Derivative Dynamic Time Warping for Human-Machine Interface
title_sort real time eyeball tracking via derivative dynamic time warping for human machine interface
topic TK Electrical engineering. Electronics Nuclear engineering
work_keys_str_mv AT mokhtarnorrima realtimeeyeballtrackingviaderivativedynamictimewarpingforhumanmachineinterface
AT arofhamzah realtimeeyeballtrackingviaderivativedynamictimewarpingforhumanmachineinterface
AT iwahashimasahiro realtimeeyeballtrackingviaderivativedynamictimewarpingforhumanmachineinterface