Real-Time Fatigue Analysis of Driver through Iris Recognition

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 7, No. 6, December 2017, pp. 3306~3312
ISSN: 2088-8708, DOI: 10.11591/ijece.v7i6.pp3306-3312  3306
Journal homepage: http://iaesjournal.com/online/index.php/IJECE
Real-Time Fatigue Analysis of Driver through Iris Recognition
Gopalakrishna K1
, Hariprasad S. A.2
Departement of Electronics and Communication Engineering, Jain University, India
Article Info ABSTRACT
Article history:
Received May 13, 2017
Revised Aug 21, 2017
Accepted Sep 5, 2017
In recent days, the driver’s fault accounted for about 77.5% of the total road
accidents that are happening every day. There are several methods for the
driver’s fatigue detection. These are based on the movement of the eye ball
using eye blinking sensor, heart beat measurement using Electro Cardio
Gram, mental status analysis using ElectroEncephaloGram, muscle cramping
detection, etc. However the above said methods are more complicated and
create inconvenience for the driver to drive the vehicle. Also, these methods
are less accurate. In this work, an accurate method is adopted to detect the
driver’s fatigue based on status of the eyes using Iris recognition and the
results shows that the proposed method is more accurate (about 80%)
compared to the existing methods such as Eye blink Sensor method.
Keyword:
Iris recognition
Eye blinking
Electrocardiogram
Electroencephalograms
Copyright © 2017 Institute of Advanced Engineering and Science.
All rights reserved.
Corresponding Author:
Gopalakrishna K.,
Departement of Electronics and Communication Engineering,
School of Engineering and Technology, Jain University,
Jakkasandra (Post), Kanakapura Road, Ramanagara (District), Karnataka.
Email: k.gopalakrishna@jainuniversity.ac.in
1. INTRODUCTION
According to ministry of Road Transport and Highways, Government of India, Transport Research
Wing Report-2015, Road accidents are recognized as serious global health problem. Nearly 5, 00,000 road
accidents caused nearly 1, 46,000 deaths and left more than thrice that number injured in India in 2015 [3].
National Crime Records Bureau, Ministry of Road Transport & Highway, Law commission of India, 1214
road crashes occur every day in India, 377 people die every day. Driver’s fault accounted for a whopping
77.5% of the total road accidents while pedestrian and cyclist’s fault accounted for a mere 3.7% and Defect
in road condition just 1.5% and remaining is due to technical issues in the vehicles. According to Road
Traffic Injuries (RTI) data, in India, half million accidents happen in a year and as per the RTI survey reports,
the road accidents ranked fourth among the causes of death around the world. Around 1.3 million people die
every year on the roads throughout the world and around 40 million people suffer non-fatal injuries and many
of them become physically disabled. Due to this, to monitor the driver’s vigilance level and to avoid fatigue
driving, it is necessary for the intelligent transport system (ITS).
These high rates of accidents are due to the driver’s drowsiness which leads to take correct timely
actions. The different methods used to find the driver’s fatigue are; Mr.Narender Kuamr and
Dr. N.C. Barwar [4] describes that, Yawning is detected by monitoring the changes in the geometrical
features of the mouth. This method uses eye Blinking Sensor to monitor the eye status and the limitation of
this method is that, there are several chances of false alarming and hence this is not an accurate
method.Mr.Anwesha Sengupta et al [5], in their paper says that, the Analysis of fatigue due to sleep
deprivation using EEG synchronization is a promising field of research and they have analysed the level of
fatigue in drivers due to sleep-deprivation by studying the synchronization between EEG data recorded from
various brain areas by employing the state-space analysis.This method gives better results but it is
complicated, if used practically, while driving.WANG He [6], describes in his paper that, the heart rate

IJECE ISSN: 2088-8708 
Real Time Fatique Analysis of Driver through Iris Recognition (Gopalakrishna K.)
3307
variability detection provides the details about the tiredness of the driver. This method is quite complicated as
it needs an electrode to be connected to the heart of the driver. Hence, it makes the driver uncomfortable to
drive the vehicle. M. Mischi, C. Rabotti, and M.Cardinale [7] describes about the, Electromyography (EMG)
analysis and vibration analysis related to fatigue. This is method is also quite complicated and creates
problem for driving.
The major limitations in the face detection are the uncontrolled illumination and the variations in the
pose. To address this, Mr.Venkatarama Phani Kumar [1] describes the Modular two-dimensional Principle
Component Analysis in which, the image is partitioned into four four equal segments and then the Histogram
equalization is applied to reduce the illumination impact due to the varing conditions. However the accuracy
of Ires recognition in presence of the noise can be improved as described by Mr.Vineet Kumar et al [2], in
their paper describe about the Iris localization using edge map genetration and adaptive circular
Houghtransform for less constrained Iris images.
2. PROPOSED METHOD
2.1. Block Diagram
Figure 1 shows the block diagram of the proposed system. It uses ARM 7 based LPC2148 processor,
for which a camera is interfaced through the Laptop or a PC. LCD is interfaced to the ARM processor to
display the status and a Buzzer is used to give the alert signal to the driver.
Figure 1. Block diagram
2.2. Iris Recognition Concept
This research is basically on an electronic device which can be used in emergency to prevent the
accident. The main idea behind this is to develop a system which can detect fatigue of the driver and issue a
timely warning so as to avoid the accident. According to the survey, large number of road accidents occur
due to the driver drowsiness, hence this system will be helpful in preventing the accidents, and consequently
reduce personal sufferings. This system will monitor the driver eyes using a camera and with the help of an
algorithm developed, it can detect symptoms of driver fatigue early enough to avoid an accident. So this will
be helpful in detecting driver fatigue in advance and will give warning output in the form of sound.
Here the Iris recognition is used to detect the driver drowsiness. Driver drowsiness is one of the
main causes for the road accidents. The driver’s drowsiness detection can reduce accidents. In this paper, an
algorithm is proposed to determine open or closed state of the driver’s eye, based on the iris area of the eye in
open or close state. In the proposed method, the state of the eye is being monitored throughout. The result
shows that the proposed algorithm has sufficient speed, accuracy, and less complexity, so it can be used in
the real time.
ARM
(LPC2148)
(Micro Processor)
Laptop/PC
Power
Supply
UART
Signal
(Character)
Relay
Camera
Buzzer
LCD
Displ
ay

 ISSN: 2088-8708
IJECE Vol. 7, No. 6, December 2017 : 3306 – 3312
3308
3. RESEARCH METHOD
3.1. Hardware
A hardware model has been developed to implement the above scheme. A web camera with IR
illuminators has been employed for focusing the face region of the driver to acquire the images of the face.
The acquired image signal is fed to Data Acquisition Card and subsequently to ARM Processor.
The ARM Processor analyses the images and detects the iris characteristics. If the eye is closed
continuously for four seconds, it may be assumed that the driver is under drowsiness and the alarm is
activated by the ARM Processor. ARM Processor LPC2148 is employed here in association with voltage
regulator IC 7805 and driver IC L2930 for the buzzer. To find the position of iris, the eye region must be
separated from the rest of the image using rectangle function, which is a process of segmentation. This will
cause the images background to be non-effective. This will results in decreasing the computational
complexity. Finally in the proposed method, circles selected as the driver’s eye condition using Hough
transformation function. The iris region is well detected. If eye is open, then the next frame is simulated and
if the eye is closed for continuously for four seconds, then a signal is passed to the ARM Processor for
raising the alarm. This is how the system can awake the driver in long drive or in fatigue condition.
4. FLOW CHART
Figure 2. Flow chart for the Eye detection
4.1. Face Detection
Numerous approaches have been proposed for detecting face. Face detection based on mat lab,
Viola-Jone algorithm and skin colour detection method are most commonly used and famous approaches for
face detection neural network based method is most accurate. It consists of learning and performing stages. In
the former stage the system is learned from a huge set of training images to identify skin and non-skin

IJECE ISSN: 2088-8708 
3309
coloured pixels. This knowledge is used when an unknown image is given. Accuracy is appreciable for this
method but it is time consuming. Viola-Jones algorithm overcomes this difficulty.
4.2. Eye Detection
The next step is eye detection from the detected face region. Here a new method is suggested for eye
detection. It is based on the assumption that, the left eye is at the left upper corner of face and right eye is at
the right upper corner of face region. After detecting the face, crop the face as a rectangular region. The left
and right eyes are located in a rectangular region having width 1/3width of face region. By knowing the
coordinates of face region, eye region coordinates can be calculated by the following equations.
Equation for left eye:
𝑒𝑦𝑒 1, : = 𝑜𝑢𝑡 1,1 + 𝑠𝑖𝑧 ∗ 0.58, 𝑜𝑢𝑡 1,2 + 𝑠𝑖𝑧 ∗ 0.28, 𝑠𝑖𝑧∗ 0.22, 𝑠𝑖𝑧 ∗ 0.22 (2)
Equation for Right eye:
𝑒𝑦𝑒 2, : = 𝑜𝑢𝑡 1,1 + 𝑠𝑖𝑧 ∗ 0.2, 𝑜𝑢𝑡 1,2 + 𝑠𝑖𝑧 ∗ 0.28, 𝑠𝑖𝑧∗ 0.22, 𝑠𝑖𝑧 ∗ 0.22
where, eye[] is a 2×4 matrix, in which first row will store left eye corner coordinates and second row contains
right eye coordinates , out[] is 1×4 matrix which contains face region corner coordinates and “siz” is the
width of face region extracted.
4.3. IRIS Recognition
Iris detection is the major phase in drowsiness detection. So this phase must have appreciable
accuracy. Here circular Hough transform is choosen for this purpose. The voting procedure is carried out in a
parameter space, from which object candidates are obtained as a local maxima in an accumulator space that is
explicitly constructed by the algorithm for computing the Hough transform.
In this system, cropped eye image and maximum and minimum radius of iris is given as input for
taking circular Hough transform. For an adult human, average radius of iris is between 5mm and 7mm. So,
10 and 25 pixel points as maximum and minimum radius of iris is used here. As an initial step, edge detection
is performed. Canny edge detection is used because it detects strong and weak edges and includes the weak
edges in the output only if they are connected to strong edges.
Hough transform can be used to find any geometrical figure in an image. More complex shapes are
described using parameters. A circle might seem easy to represent using three parameters. The equation of a
circle is r2
= (x-a) 2
+ (y-b) 2
and it has three parameters r, a and b where, r is the radius of circle, a and b are
the centre in X and Y direction. The parameter space of a circle belongs to R3
. Now we need to convert the
edge detected binary image to the parameter space. This is easy since the pixel coordinate can be directly
translated to a and b in the parameter space. If the radius is known, a constant radius may be used to simplify
the computation. Otherwise a finite list of radii must be evaluated. Radius of iris is different from person to
person, but it is in a specified range.
This paper suggests the second method. For each radius find out the coordinate positions, which
have non zero value in both edge image and circle with that radius. If such a pixel position is detected,
increment the value corresponding to that position in accumulator space. After complete voting, find out the
maximal points and number of non-zero valued pixels in the circumference of the circle with the maximal
point as centre. The circle having larger number of such points in its circumference is the iris. Figure 3 shows
the detected iris.
Figure 3. Detected iris
4.4. Drowsiness detection
Drowsiness can be detected based on the visibility ratio of iris. Iris is not visible completely in two
situations, ie, during blinking of eye and in drowsy condition. Differentiate these two is the next task.
Here, if the iris visible ratio is less than 60%, then that frame will be considered for further analysis. ie, to

 ISSN: 2088-8708
3310
detect it is blink or drowsiness. For that, analyse the previous frame. If it also in the same condition, consider
the situation as drowsy otherwise it is just a blink. Figure 4 shows the Drowsiness detection.
Figure 4. Drowsiness detection
5. RESULTS AND PERFORMANCE EVALUATION
5.1. Initial Condition
Figure 5 shows the initial condition picture captured by web camera when eye is open, it shows no
problem on matlab command.
Figure 5. Initial Condition
5.2. Second condition
Figure 6 shows the condition when eyes closed for 1st
count (one Second) When eye is closed, it
starts to count for few seconds. For the first count, the status of eyes is” eye closed” but the result shows no
problem in first condition, we cannot predict it as danger so it will take more picture or frames.
Figure 6. When eyes closed for 1st
count
5.3. Third Condition
In the third condition, when eyes are closed for 4th
count (Eye is closed continuously for four
Seconds), as shown in Figure 7, it shows as danger and will send a signal to the Processor to give warning
message.

IJECE ISSN: 2088-8708 
3311
Figure 7. When eyes closed for 4th
count
6. CONCLUSION
The analysis and design of real time driver fatigue detection system is carried out. The proposed
system provides the detection of driver fatigue. It is used to avoid the road accidents caused by drowsy
driving and it can also help drivers to be awake while driving, by giving a warning when the driver is sleepy.
And also this system can be used for security purpose of a driver.
During the monitoring, the system is able to decide if the eyes are open or closed. When the eyes
have been closed continuously for four seconds, a warning signal is issued. Image processing achieves highly
accurate and reliable detection of drowsiness. This is achieved by interfacing a web camera to a PC and
recording test videos and frame database under different lighting conditions. The calculation speed, accuracy
and robustness will be influenced by using algorithm and hardware part.
ACKNOWLEDGEMENTS
I would like to take this opportunity to express my sincere gratitude to Mr.Aswathnarayana P,
Mr.Sagar N, Ms.Bharathi C and Ms.Shilpa Rani, the students of BMSIT, Bangalore for helping me in
carrying out this project. Also, I would like to thank Jain University for providing me the overall support in
my academic and research activities.
REFERENCES
[1] V. Phanikumar S., et al., “Face recognition with modular two dimensional PCA under Uncontrolled illumination
varitions,” International journal of Electrical and Computer Engineering, vol/issue: 6(4), pp. 1610-1616, 2016.
[2] V. Kumar, et al., “Accurate iris localization using edge map generation and adaptive circular Hough transform for
less constrained iris images,” International journal of Electrical and Computer Engineering (IJECE), vol/issue:
6(4), pp. 1637-1646, 2016.
[3] Secretary, Government of India, Ministry of Road Transport and High Ways, “Road Accidents in India-2015,”
Transport Research Wing Report, 2015.
[4] N. Kuamr and N. C. Barwar, “Analysis of Real Time Driver Fatigue Detection Based on Eye and Yawning,”
International Journal of Computer Science and Information Technologies, vol/issue: 5(6), pp. 7821-7826, 2014.
[5] A. Sengupta, et al., “Analysis of Fatigue using EEG State-Space Analysis,” Annual IEEE India Conference
(INDICON), 2014.
[6] W. He, “Research on Heart Rate Variability to Driver Fatigue Detection of Dangerous Chemicals Vehicles Based
on simulation analysis,” 7th International Conference on Intelligent Computation Technology and Automation,
Changsha, Hunan, China, 2014.
[7] M. Mischi, et al., “Analysis of muscle fatigue induced by isometric vibration exercise at varying frequencies,” 34th
Annual International Conference of the IEEE EMBS San Diego, California USA, 2012.
[8] B. G. Patil, et al., “Iris feature extraction and classification using FPGA,” International journal of Electrical and
Computer Engineering (IJECE), vol/issue: 2(2), pp. 214-222, 2012.
[9] M. M. Bundele and R. Banerjee, “ROC Analysis of a Fatigue Classifier for Vehicular Drivers,” Intelligent Systems
(IS), 5th IEEE International Conference, 2010.
[10] K. Sekar, et al., “Dynamically configurable bus topologies for high-performance on-chip communication,” IEEE
Trans. Very Large Scale Integr. (VLSI) Syst., vol/issue: 16(10), pp. 1413–1426, 2008.
[11] J. Shen and P. Hsiung, “Dynamic Reconfigurable Network-on-Chip Design: Innovations for Computational
Processing and Communication,” J. Shen and P. Hsiung, Eds. Hershey, PA, USA: IGI Global, 2010.
[12] G. M. Chiu, “The odd-even turn model for adaptive routing,” IEEE Trans. Parallel Distrib. Syst., vol/issue: 11(7),
pp. 729–738, 2000.
[13] S. Jovanovic, et al., “A new deadlock-free fault-tolerant routing algorithm for NoC interconnections,” in Proc. Int.
Conf. Field Program. Logic Appl., pp. 326–331, 2009.

 ISSN: 2088-8708
3312
[14] W. Dally and C. Seitz, “Deadlock-free message routing in multiprocessor interconnection networks,” IEEE Trans.
Comput., vol/issue: C-36(5), pp. 547–553, 1987.
[15] C. Bobda, et al., “DyNoC: A dynamic infrastructure for communication in dynamically reconfigurable devices,” in
Proc. Int. Conf. Field Program. Logic Appl., pp. 153–158, 2005.
[16] T. Pionteck, et al., “Applying partial reconfiguration to networks-on-chip,” in Proc. Field Program. Logic Appl.
Int. Conf., pp. 1–6, 2006.
[17] S. Jovanovic, et al., “A new high-performance scalable dynamic interconnection for fpga-based reconfigurable
systems,” in Proc. Int. Conf. Appl.-Specific Syst., Archit. Process., pp. 61–66, 2008.
[18] S. Jovanovic, et al., “CuNoC: A dynamic scalable communication structure for dynamically reconfigurable
FPGAs,” Microprocess. Microsyst, vol/issue: 33(1), pp. 24–36, 2009.
BIOGRAPHIES OF AUTHORS
Gopalakrishna K has awarded the B.E degree in Electronics from Bangalore University, M.Tech
degree in VLSI Design and Embedded Systems from VTU, M. Phil degree in Computer Science
from M.S.University, Tirunelveli, Tamil Nadu and pursuing PhD. from Jain University. He has
23 years of teaching experience. He is currently working as Associate Professor, Dept. of
Electronics & Communication Engineering, School of Engineering & Technology, Jain
University. His field of interests includes Advance microprocessors, Microcontrollers,
Embedded Systems, VLSI Technology and VLSI Designing.
Dr. Hariprasad obtained B.E degree in the year 1991 and M.E in the year 2000.He has completed
Ph.D. degree in the year 2011 and two additional highest degrees, Doctor of science degrees in
the year 2013 and 2014 for the post-doctoral research work on communication and embedded
systems. He has published 60 papers in International and National Journals/conferences and a
text book on "Advanced microprocessors". Dr. Hariprasad has 22 years of teaching experience
and 09 years of research experience. He held key posts, like Director for Cognitive science,
RVCE, Vice-principal, BMSIT, Pro-vice-Chancellor-Dayananda Sagar University, Academic
mentor for DSCE and DSATM. Dr. Hariprasad established industry supported labs and served as
visiting professor to various reputed colleges in Bangalore. Currently he is working as Director,
School of Engineering Technology, Jain University.

Real-Time Fatigue Analysis of Driver through Iris Recognition

More Related Content

What's hot (20)

Similar to Real-Time Fatigue Analysis of Driver through Iris Recognition (20)

More from IJECEIAES (20)

Recently uploaded (20)

Real-Time Fatigue Analysis of Driver through Iris Recognition