International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (ISSN 2250-2459, Volume 2, Issue 4, April 2012)

363

Drowsy Detection On Eye Blink Duration Using Algorithm
Mandeep Singh
1
, Gagandeep Kaur
2
1
Student, M.tech Electronics and Communication Section, YCOE, Talwandi Sabo, Guru Kashi Punjabi University Campus, Patiala
2
Asst Prof., Electronics and Communication Section, YCOE, Talwandi Sabo, Guru Kashi Punjabi University Campus, Patiala
1
mandeep.dandiwal89@gmail.com


2
ergagan84@gmail.com

Abstract this paper presents an automatic drowsy
driver monitoring and accident prevention system that is
based on monitoring the changes in the eye blink duration.
Our proposed method detects the drowsiness in eyes using
the proposed mean sift algorithm. Our new method detects
eye blinks via a standard webcam in real-time
YUY2_640x480 resolution. Experimental results in the eye-
blink database showed that the proposed system detects eye
blinks with 99.4% accuracy with a 1% false positive rate.

Keywords - Eye blinks detection, eye symmetry, and
drowsiness detection.

I. INTRODUCTION
In physiology fatigue is to perform reasonable and
necessary physical or mental activity. When the
metabolic reserves of the body are exhausted and the
waste products increased, as for example after prolonged
exertion, the body finds it difficult to continue its
function and activity.

The ever increasing numbers of traffic accidents all over
the world are due to the drowsiness of driver. Drowsy
driving is a factor in one in every six road accidents and
one in three heavy vehicle accidents.

The annual financial toll is estimated to be at least $2
billion in health and insurance costs in Australia and $56
billion in the U.S. A 2009 survey by the National
Transport Commission found that at least 45 per cent of
heavy vehicle drivers were impaired by fatigue during
their last shift. It found 52 per cent of major crash
insurance claims were fatigue related. The survey also
revealed 50 per cent of all long distance truck drivers had
nodded off while driving more than once.

According to the National Sleep Foundations 2010
Sleep in America poll, 60% of adult drivers have driven a
vehicle while feeling drowsy in the past year, and more
than one-third have actually fallen asleep at the wheel.


II. FLOW CHART





















Interfacing a camera
through MATLAB
Start the camera in
back round by
trigger method
Cut the eye area from
real Image
Make the origin to
eyebrows and take a
box which covers the
eyes
Calculate the
percentage of eyes
opening
If eye opening
percentage decreases
from desired value
ALARM
STARTS

International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, Volume 2, Issue 4, April 2012)
364


The focus of this paper is on last category of alertness
monitoring technologies. Those technologies monitor in
real time. In this paper take only the eye parameters in
real time image taken by trigger method because it takes
less time than the preview method to check the
drowsiness level of the driver. To become it practical and
useful we use the warning system, this is a real world
driving environment. The objective of this paper is to
measure the current activity of the eyes of the driver
which is visualized by the camera and we can check the
drowsiness of the driver. In this we give the value of the
eye closure percentage value and the time for which
alarm blown, this is changed according to every person, it
set in the program. When the alarm blown it continuously
checks the eye pattern of eye closure if percentage
increases then the alarm goes off. This is done in the
while loop because it goes continuous, it do not break
until we do not want.

III. IMAGE PROCESSING
This approach analyzes the images captured by camera
to detect physical changes of drivers, such as eyelid
movement, using MATLAB Software. Using image
processing technique to measure the percentage of eyelid
closure over the pupil over time... In addition this
approach requires the camera to focus on a relative small
area (around the drivers eyes). It thus requires relative
precise camera focus adjustment for every driver.

IV. OUTPUT/WARNING UNIT
For indication of warning we will use two approaches
one by blowing alarm and second is the graphical method
to take a record.

V. DROWSINESS DETECTION
We define three states for the driver drowsiness as
seen in TABLE I. The typical eye blink duration is less
than 400ms on average and 75ms for minimum. For this
reason, we use the time of eye closure as explained in
TABLE 1.







Drowsiness Description
Awake Eye closure time measured
value
drowsy Eye closure time measured
value and Eye closure time
measured value
sleeping Eye closure time measured
value

TABLE 1-Drowsiness VS description

VI. CONCLUSION
We proposed a new method to detect eye blinks using
the algorithm. The proposed system is independent from
the eye blinks duration as it works within the same frame.
Therefore, it has an advantage over the other systems that
retains information of the past frames. In addition, it runs
at a 640480 resolution which is acceptable for real-time
scenarios.
The proposed system detects eye blinks with 99%
accuracy and a 1% false positive rate. Our experiments
showed that the proposed system produces fast and
accurate results for the detection of drowsiness.
According to the real world experiments eye detection
and symmetry is taken in the experiment in real time.

REFRENCES
[1] S. Jane, W. Jean, V. Bradley. 1999. Why Do People Have Drowsy
Driving Crashes, Input From People Who Just Did. AAA
Foundation for Traffic Safety.
[2] M.H Sigari. 2009. Driver Hypo-Vigilance Detection based on
Eyelid Behavior. In Proceedings of the Seventh International
Conference of Advances in Pattern Recognition, IEEE Computer
Society, pp. 426-429,2009.
[3] C. Shan, S. Gong, and P. W. McOwan. 2005. Robust facial
expression recognition using local binary patterns. In IEEE ICIP.
[4] P. Viola and M. J. Jones. 2004. Robust real-time object
detection. International Journal of Computer Vision.

International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, Volume 2, Issue 4, April 2012)
365

[5] L. Yunqi, Y. Meiling, S. Xiaobing, L. Xiuxia, O. Jiangfan.
2009. Recognition of Eye States in Real Time Video. Computer
Engineering and Technology, IEEE Computer Society.
[6] S. Jin , S.-Y. Park J.-J. Lee. 2006. Driver Fatigue Detection
using Genetic Algorithm. 11th International Symposium on
Artificial Life and Robotics, Oita, Japan.
[7] Sullivan, J. J. Fighting, 2003, Fatigue Public Roads.
Federal Highway Administration, U.S. Department of
Transportation.
[8] S.Y. Zhao, and R.R. Grigat. 2006. Robust eye detection under
active infrared illumination. Proceedings of International
Conference on Pattern Recognition.
[9] E. Vural, M. Cetin, G. Littlewort, M. Bartlett and J. Movellan.
2007. Drowsy Driver Detection Through Facial Movement
Analysis. Lecture Notes in Computer Science.
[10] T.F. Cootes, G.J. Edwards and C.J. Taylor. 1998. Active
appearance models. In H.Burkhardt and B. Neumann, editors, 5th
European Conference on Computer Vision, Springer, Berlin.
[11] T. Kawaguchi, and M. Rizon. 2003. Iris detection using intensity
and edge information. Pattern Recognition.