Automated eye blink detection and tracking using template matching

Muhammad Awais; Nasreen Badruddin; Micheal Drieberg

doi:10.1109/scored.2013.7002546

Automated eye blink detection and tracking using template matching

Muhammad Awais, Nasreen Badruddin, Micheal Drieberg

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

13 Citations (Scopus)

Abstract

Eye blink detection is considered to be one of the most reliable sources of communication in modern human computer interaction (HCI) systems. This paper proposes a new method for eye blink detection using template matching and similarity measure. In order to minimize the false detection due to changing background in the video frame, face detection is applied before extraction of the eye template. Golden ratio concept is introduced for robust eye detection and is followed by eye template creation for tracking. Eye tracking is performed by template matching between template image and surrounding region. The normalized correlation coefficient is computed for successful eye tracking. Eye blink detection is performed based upon the correlation score as the score changes significantly whenever a blink occurs. The proposed system provides an overall precision of 92.8% and overall accuracy of 99.6% with 0.1% false positive rate in different experimental conditions.

Original language	English
Title of host publication	2013 IEEE Student Conference on Research and Developement
Publisher	The Institute of Electrical and Electronics Engineers (IEEE)
ISBN (Print)	9781479926565
DOIs	https://doi.org/10.1109/scored.2013.7002546
Publication status	Published - Dec 2013

Access to Document

10.1109/scored.2013.7002546

Cite this

@inproceedings{c2a24b9a2a0c4baf82e4d78ab6e1f72f,

title = "Automated eye blink detection and tracking using template matching",

abstract = "Eye blink detection is considered to be one of the most reliable sources of communication in modern human computer interaction (HCI) systems. This paper proposes a new method for eye blink detection using template matching and similarity measure. In order to minimize the false detection due to changing background in the video frame, face detection is applied before extraction of the eye template. Golden ratio concept is introduced for robust eye detection and is followed by eye template creation for tracking. Eye tracking is performed by template matching between template image and surrounding region. The normalized correlation coefficient is computed for successful eye tracking. Eye blink detection is performed based upon the correlation score as the score changes significantly whenever a blink occurs. The proposed system provides an overall precision of 92.8% and overall accuracy of 99.6% with 0.1% false positive rate in different experimental conditions.",

author = "Muhammad Awais and Nasreen Badruddin and Micheal Drieberg",

year = "2013",

month = dec,

doi = "10.1109/scored.2013.7002546",

language = "English",

isbn = "9781479926565",

booktitle = "2013 IEEE Student Conference on Research and Developement",

publisher = "The Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

TY - GEN

T1 - Automated eye blink detection and tracking using template matching

AU - Awais, Muhammad

AU - Badruddin, Nasreen

AU - Drieberg, Micheal

PY - 2013/12

Y1 - 2013/12

N2 - Eye blink detection is considered to be one of the most reliable sources of communication in modern human computer interaction (HCI) systems. This paper proposes a new method for eye blink detection using template matching and similarity measure. In order to minimize the false detection due to changing background in the video frame, face detection is applied before extraction of the eye template. Golden ratio concept is introduced for robust eye detection and is followed by eye template creation for tracking. Eye tracking is performed by template matching between template image and surrounding region. The normalized correlation coefficient is computed for successful eye tracking. Eye blink detection is performed based upon the correlation score as the score changes significantly whenever a blink occurs. The proposed system provides an overall precision of 92.8% and overall accuracy of 99.6% with 0.1% false positive rate in different experimental conditions.

AB - Eye blink detection is considered to be one of the most reliable sources of communication in modern human computer interaction (HCI) systems. This paper proposes a new method for eye blink detection using template matching and similarity measure. In order to minimize the false detection due to changing background in the video frame, face detection is applied before extraction of the eye template. Golden ratio concept is introduced for robust eye detection and is followed by eye template creation for tracking. Eye tracking is performed by template matching between template image and surrounding region. The normalized correlation coefficient is computed for successful eye tracking. Eye blink detection is performed based upon the correlation score as the score changes significantly whenever a blink occurs. The proposed system provides an overall precision of 92.8% and overall accuracy of 99.6% with 0.1% false positive rate in different experimental conditions.

U2 - 10.1109/scored.2013.7002546

DO - 10.1109/scored.2013.7002546

M3 - Conference contribution

SN - 9781479926565

BT - 2013 IEEE Student Conference on Research and Developement

PB - The Institute of Electrical and Electronics Engineers (IEEE)

ER -