Exeley Inc.

WIDZISZ-PRONOBIS, Sylwia

INVOLVING PUBLIC SPACE USERS TO DESIGN CHANGES BASED ON THE REDEVELOPMENT OF THE SQUARE IN GORZÓW WIELKOPOLSKI (POLAND). CASE STUDY

HULIMKA, Jacek

KAŁUŻA, Marta

TECHNICAL CONDITIONS OF THE UNIQUE STRUCTURE OF INVERTED SIPHON – HISTORY &amp; PRESENT

OSZCZAPIŃSKA, Katarzyna

THE INVESTMENT EXPENDITURES ON ENVIRONMENT PROTECTION AND WATER MANAGEMENT IN POLAND IN 2003–2017

Zaman, Shah

Gilani, Syed Amir

Bacha, Raham

Manzoor, Iqra

Ul Hasan, Zain

Correlation between portal vein diameter and craniocaudal length of the spleen

Migda, Michał

Migda, Marian Stanisław

Migda, Bartosz

Maleńczyk, Marek

The usefulness of high-frequency ultrasonography in the preoperative evaluation of vulvar cancer – a case series

Mlosek, Robert Krzysztof

The utility of high-frequency ultrasonography in preoperative assessment of vulvar Paget’s disease – a case report

Chao, Lei

Changyuan, Wang

Guang, Li

Lu, Shi

International Journal of Advanced Network, Monitoring and Controls         Volume 04, No.04, 2019 
DOI: 10.21307/ijanmc-2019-067                            24 
Detection of Blink State Based on Fatigued Driving 
Lei Chao 
School of computer science and engineering, Xi’an 
Technological University 
Xi’an, China 
E-mail:callofduty2015@163.com 
 
Wang Changyuan 
School of computer science and engineering, Xi’an 
Technological University 
Xi’an, China 
E-mail:cyw901@163.com 
 
Li Guang 
School of computer science and engineering, Xi’an 
Technological University 
Xi’an, China 
E-mail:865413666@qq.com 
 
Shi Lu 
School of computer science and engineering, Xi’an 
Technological University 
Xi’an, China 
E-mail:892178238@qq.com 
 
 
 
Abstract—In recent years, with the improvement of the 
national economy, the penetration rate of automobiles has been 
increasing, and traffic accidents have also increased. Fatigue 
driving is the main factor in many traffic accidents. Fatigue 
driving can cause the driver's inattention, slow response, and 
make wrong decisions on danger signals, which affect the 
driver's personal safety. In modern development, driving 
safety is developing towards intelligence and safety. Therefore, 
the detection of driver fatigue has become a generally accepted 
demand. This paper proposes a method to calculate the 
threshold of blinking, which can detect the blinking state of the 
driver in real time through video. During the driving process, 
when the driver is in the closed eye state for a long time, an 
early warning is issued to avoid the accident. This paper uses 
Python language to achieve the first, through the digital image 
technology call Dlib open source library to detect 68 feature 
points of the face, and then measure the aspect ratio between 
the length and width of the human eye, and finally through the 
Kmeans clustering algorithm to collect the ratio The analysis 
yields the blink threshold. The experimental results show that 
the recognition rate is 92.5% when the video frame rate is 30, 
and the recognition accuracy is 92.5%. The experimental 
results show that the method designed in this paper can 
quickly detect the fatigue characteristics of the human eye, has 
a higher recognition rate and accuracy for fatigue driving, and 
helps reduce the occurrence of traffic accidents. 
Keywords-Blinking Algorithm; Fatigue Detection; Digital 
Image Processing; Clustering Algorithm; Key Points Of Human 
Eyes 
I. INTRODUCTION  
With the improvement of people's material living 
standards, cars have become the main means of 
transportation for people, but the growing number of 
vehicles has led to more traffic accidents. According to 
statistics, fatigue driving is the main cause of traffic 
accidents[1,2].Under normal circumstances, the 
medical community believes that there are two reasons 
for fatigue driving, one is because the driver's attention 
is too concentrated, and the other is that the body does 
not rest well. Because of being in this state for a long 
time, the body will be fatigued, lose concentration, the 
driver will snoring, lose concentration, decrease the 
ability to judge dangerous situations, and cause traffic 
accidents. At present, there are relatively few 
applications of fatigue driving equipment in China's 
in-vehicle systems. Fatigue detection mainly through 
facial features, eye and mouth features, human 
electrical signal characteristics and convolutional 
neural network characteristics[3,4,5].The detection of 
facial features is generally based on the frequency of 
blinking eyes, the degree of mouth opening, and the 
frequency of head movements due to fatigue. The 
fatigue of human body electrical signals is generally 
the measurement of surface EMG signals, because 
human fatigue can be expressed by muscle 
physiological information. Surface EMG signals can 
reflect real-time physiological processes of muscle 
information and physiological signals on the skin 
surface. Convolutional neural networks generally 
extract facial features through image processing 
methods, and then extract the main features through 
convolutional layers, pooling layers, and fully 
connected layers to analyze and determine whether 
fatigue. Chen[6] uses the ASM algorithm to accurately 
locate the eyes and mouth area, calculates the eye's 
aspect ratio, mouth height value, and black and white 
pixel ratio near the mouth, and obtains the blink 
frequency and mouth opening degree. The degree of 
mouth opening is used as an input to the fuzzy 
International Journal of Advanced Network, Monitoring and Controls         Volume 04, No.04, 2019 
25 
inference engine to obtain three types of fatigue levels 
to accurately quantify the degree of fatigue 
The method proposed in this paper is to judge the 
driver's fatigue driving according to the characteristics 
of the human eye. Because the digital image processing 
open source visual library OpenCV comes with a 
human face detection library, but the disadvantage is 
that the lighting requirements are very high, the 
lighting slightly changed, it will be difficult to locate or 
inaccurate positioning[7]. Therefore, this paper chooses 
Dlib open source library to detect human eye features. 
Firstly, the 68 face feature points provided by the Dlib 
open source library are used to accurately calibrate the 
position of the face and the human eye, and then the 
aspect ratio between the length and the width of the 
human eye is measured. Finally, the Kmeans clustering 
algorithm is used to analyze the collected ratio. The 
threshold of blinking. Figure 1 below, a is the 68 face 
feature points marked by Dlib, and b is the feature 
point on the face of the paper. 
 
 
(a) 68 feature points of a face annotation 
 
(b) Recognition of face images 
Figure 1. Facial feature points 
 
II. RELATED WORK 
A.  Blink detection and threshold analysis methods 
This chapter mainly introduces the blink algorithm 
formula and blink threshold analysis method. The blink 
threshold analysis method uses the Kmeans clustering 
algorithm in machine learning. There are many 
methods for blink detection, such as support vector 
machine classification, eye movement sequence 
analysis, convolutional neural network feature 
extraction, eye feature point analysis, etc. This article 
uses the eye feature analysis method. Threshold 
analysis methods in machine learning usually use 
regression algorithms, decision tree methods, Bayesian 
methods, and clustering algorithms. This article uses 
the Kmeans clustering algorithm in machine learning. 
B.  Blinking formula 
There are currently many methods in the field of 
blink detection. Andrej Fogelto et al[8] analyzed the 
relationship between the speed of blinking and the 
duration of time through the cyclic neural network 
(RNN), so as to better distinguish the state of blink and 
blink, through the comparison of one-way and two-way 
circulating neural networks. One-way neural networks 
work better in blink detection. However, neural 
networks have their own limitations. For example, 
network merging will lose a lot of information. In the 
field of face recognition, the relationship between part 
and whole is neglected, and each person's face features 
are different, so it takes a lot of time to train. parameter. 
RenAnhu et al[9] trained the blink classifier through 
the AdaBoost algorithm, but the AdaBoost algorithm is 
very sensitive to the discrete data of the blink. The 
detection of the eye part during image processing is 
easily affected by the speed of light and object 
movement, just as the blinking behavior is fast. the 
process of. ZengYouwen et al[10] used the correlation 
between computer signals and the number of blinks to 
determine the fatigue state, but the experiment required 
special equipment and equipment, and the operation 
was difficult and difficult to implement. Since the 
blinking algorithm proposed by Soukupová[11] has 
measured the blink threshold of the aspect ratio of the 
eye, using the support vector machine[12] method to 
analyze the collected threshold of the blink to finally 
obtain an EAR of 0.2, the algorithm of this paper is the 
In addition, by measuring the aspect ratio of the eye, 
the Key clustering algorithm in machine learning is 
used to obtain the blink threshold. As shown in Figure 
2.1a, the absolute value of the longitudinal distance ab 
of the eye will become smaller when the eye is blinking. 
At this time, the ratio of cd to ab will suddenly become 
larger, so we analyze the threshold when the ratio 
International Journal of Advanced Network, Monitoring and Controls         Volume 04, No.04, 2019 
26 
becomes larger when blinking. Figure 2a shows the 
distance between ab and cd, and b is the position of the 
human eye feature point marked by Dlib. This paper 
proposes the blink threshold formula as follows: 

5362
412
sho
pppp
pp
ldBlinkthre


  


(a) 
 

(b) 
Figure 2. (a) The lateral distance is cd longitudinally ab; (b) dlib human 
eye calibration features 
 
C.  Kmeans clustering algorithm 
The Kmeans algorithm is a relatively common 
algorithm in clustering algorithms. Its advantage is that 
it is easy to implement and understand, and the 
calculation speed is fast. The core idea is to calculate 
the distance between the sample point and the centroid 
of the cluster, and divide the calculated result into the 
same cluster as the sample point with the centroid of 
the cluster. 
The similarity between samples in K-means is 
determined by the distance between them. The closer 
the distance is, the higher the similarity is. The 
common distance calculation methods are Euclidean 
distance, Euclidean distance and Manhattan distance. 
European distance. In the cluster analysis, the formulas 
for two m-dimensional samples xi=(xi1,xi2,xi3...,xim) 
and xj=(xj1,xj2,xj3...,xjm) are as follows: 
 
 


m
k
jkiked xxt
1
2)(dis  
The steps of the k-means algorithm are as follows: 
1) First randomly select the centroids of K clusters. 
2) Calculate the Euclidean distance from each 
sample point to each centroid, and classify it into the 
cluster with the smallest center of mass, and then 
calculate the centroid of each new cluster. 
3) After all the sample points are divided, 
recalculate the position of the centroid of each cluster, 
and then iteratively calculate the distance from each 
sample point to the centroid of each cluster, and then 
re-divide the sample points. 
4) Repeat steps 2 and 3 until after the iteration, the 
partitioning of all sample points remains unchanged, 
and K-means gets the optimal solution. 
The main problem of the calculation result is to 
ensure the convergence of the algorithm. Here, the 
square error is calculated by the following formula, 
which is used to illustrate that the clustering effect can 
minimize the sum of squares in each cluster. 
  
2
1i
)(
)(, 


K
ic
i uxucJ  
 uc,j represents the sum of squares of the distance 
from each sample point to its cluster, )(u ic  represents 
the centroid of the cluster to which the i-th sample 
belongs, and the smaller  uc,j , all the sample points 
and their clusters The smaller the distance, the better 
the quality of the division. The termination condition of 
the K-means algorithm is that  uc,j  converges to a 
minimum. In order to achieve clustering, the maximum 
value of the objective function is obtained. Take a 
one-dimensional array as an example. 
 J = ∑ ∑ (x(i) − uc(i))
2
xj∈ui
k
i=1  
Transform the above formula to get: 
𝜕𝐽
𝜕𝑢𝑖
=
𝜕
𝜕𝑢𝑖
∑ ∑ (𝑥𝑗 − 𝑢𝑖)
2
𝑥𝑗∈𝑢𝑖
𝑘
𝑖=1
 
International Journal of Advanced Network, Monitoring and Controls         Volume 04, No.04, 2019 
27 
       = ∑ ∑ (𝑥𝑗 − 𝑢𝑖)
2
𝑥𝑗∈𝑢𝑖
𝑘
𝑖=1
 
       = (−2) ∗ ∑ (𝑥𝑗 − 𝑢𝑖)
𝑥𝑗∈𝑢𝑖
 
When 


ij u
ij ux
x
0)(*2- ）（ ui =
1
|ci|
∑ xjxj∈ui  
The result of the optimization is to calculate the mean 
of the cluster. 
During the experiment, the algorithm may be too 
slow to achieve effective results because the data set is 
too large. Therefore, you can specify the maximum 
number of convergence times for the K-means 
algorithm or specify the cluster center transformation 
threshold. When the algorithm reaches the maximum 
number of times or When the cluster center rate of 
change is less than a certain threshold, the algorithm 
stops updating. 
K-means algorithm advantages: easy to understand, 
easy to implement, high operating efficiency, the 
disadvantage is that the greedy strategy is used to 
cluster the sample points, resulting in easy local 
convergence of the algorithm, slower data processing 
in big data, and outliers and The noise is very sensitive, 
and a small number of outliers and noise points can 
have a significant impact on the averaging of the 
algorithm. 
III. THE EXPERIMENT 
This article mainly introduces two aspects, one is to 
introduce the source of the experimental data set, and 
the other is to analyze the experimental data.Figure 3 
shows the author's own data collection and analysis. 
From left to right, the first picture is the analysis of the 
blink value of the author's 5 blinks, and the middle 
figure is when the blink threshold is 5.1 when Kmeans 
= 2 The blink data graph, the right graph is the actual 
record of the author's experiment. Figure 4 shows the 
data of a random experimental sample in the public 
data set. From left to right, the first figure analyzes the 
blinking value of the aspect ratio of the 3 blinks in the 
experimental sample. The blink data graph at 5.1, the 
right graph is the actual record of the experimental 
sample.This article uses the blink data set provided by 
Zhejiang University[13]. All the data in the data set is 
collected under the natural light of the room. There is 
no special illumination. The collected equipment is a 
common camera that comes with the computer. There 
are 80 video clips and 20 people participate. , four 
segments per person, these four segments represent a. 
front view without glasses; b. front view with thin edge 
glasses; c. front view with black frame glasses; d. View. 
Participants spontaneously blink at the front of the 
camera at normal speed. The size of each video is 
320*240, the frame rate of the video is 30fps, and the 
duration of recording is generally about 5 seconds. The 
experimenter usually blinks about 1 to 6 Times, a total 
of 255 blinks. The following are the results of data 
collection and analysis. 
 
 
The text person has 5 blink-eye aspect ratio data 
Kmeans=2, the blink data chart 
 
The text person image 
Figure 3. The following is the experimental data of the paper 
 
International Journal of Advanced Network, Monitoring and Controls         Volume 04, No.04, 2019 
28 
Public data set 3 times blinking eye aspect ratio 
data Kmeans=2, blinking data chart 
 
Public data set sample 
Figure 4. Public data set sample 
 
The following table a is a comparison of the public 
data sets provided by Zhejiang University and the 
experimental results of the text person. Table b is a 
comparison of other methods with the method of this 
paper. RenAnhu[9] trained the classifiers of blinking 
and closed eyes through the Adaboosts algorithm. The 
person in the video is then tested for blinking. Zhang 
Wei[14] performed a correlation analysis of the blink 
of the eye by analyzing the left forehead EEG signals 
Attention and Meditation and Blink data. 
 
TABLE I.  COMPARED WITH PUBLIC DATASETS 
Experimental sample 𝐁𝐥𝐢𝐧𝐤 𝐭𝐡𝐫𝐞𝐬𝐡𝐨𝐥𝐝 Blink times 
Number of 
recognition 
Recognition rate 
Text person 5.1 100 90 90% 
Public data set 5.1 255 236 92.5% 
 
TABLE II.  COMPARED WITH OTHER LITERATURE 
literature Recognition rate 
9 91.5% 
14 83.7% 
This article 92.5% 
 
IV. CONCLUSION 
This paper overcomes the shortcomings of digital 
image processing and OpenCV vision open source 
library, and combines the existing open source Dlib 
machine learning library,The data between the vertical 
and horizontal ratio of blink is calculated by 
mathematical method, and the threshold value of the 
vertical and horizontal ratio of blink is analyzed by 
means of kmeans clustering algorithm in machine 
learning. According to the analysis of the public data 
set of Zhejiang University, when the threshold value of 
the vertical and horizontal ratio of blink is 5.1, the 
accurate recognition rate of blink is 92.5%. Through 
the experimental comparison, this algorithm can 
effectively detect the fatigue state of blink, which is 
more important This algorithm is fast, efficient and 
easy to transplant to various devices, and has great 
practical value in the field of fatigue driving. The 
shortcomings of the paper: for fatigue monitoring, not 
only eyes as a reference point, nose tip shaking, mouth 
opening and so on have an impact on face fatigue, so 
the fatigue detection algorithm in this paper needs to be 
improved. 
 
REFERENCES 
[1] M. Hülsmann,D. Donnermeyer,E. Schäfer. A critical appraisal of 
studies on cyclic fatigue resistance of engine‐driven endodontic 
instruments[J]. International Endodontic Journal,2019,52(10). 
[2] Pierre Thiffault,Jacques Bergeron. Monotony of road environment 
and driver fatigue: a simulator study[J]. Accident Analysis and 
Prevention,2003,35(3). 
International Journal of Advanced Network, Monitoring and Controls         Volume 04, No.04, 2019 
29 
[3] Liu Longfei, Wu Shizhen, Xu Wangming. Real-time detection 
method of fatigue driving based on face feature point analysis[J]. 
Television Technology, 2018, 42(12): 27-30+55. 
[4] Yan Wang,Rui Huang,Lei Guo. Eye gaze pattern analysis for fatigue 
detection based on GP-BCNN with ESM[J]. Pattern Recognition 
Letters,2019,123. 
[5] Driver’s Fatigue Detection Based on Yawning  Extraction[J]. Nawal 
Alioua,Aouatif Amine,Mohammed Rziza,Aboelmagd 
Noureldin.International Journal of Vehicular Technology. 2014 
[6] Chen Xin, Li Weixiang, Li Wei, Zhang Wenqing, Zhu Yuan. 
Multi-feature fusion fatigue detection method based on improved 
ASM [J]. Computer Engineering and Design, 2019, 40 (11): 
3269-3275. 
[7] Rafael C.Gonzalez,Richard E.Woods.Digital Image Processing,Third 
Edition[M],2017 
[8] Andrej Fogelton,Wanda Benesova. Eye blink completeness 
detection[J]. Computer Vision and Image Understanding,2018. 
[9] Ren Anhu, Liu Bei. Face Recognition Blink Detection Based on 
Adaboost[J]. Computer and Digital Engineering, 2016, 44(03): 
521-524. 
[10] Zeng Youwen, Feng Zhen, Zhu Yabing, Li Qi.Relationship between 
the number of blinks and fatigue based on EEG experiment[J].Journal 
of Changchun University of Science and Technology(Natural Science 
Edition),2017,40(01):123-126. 
[11] Tereza Soukupova ,́Jan Cˇ ech, Eye blink detection using facial 
landmarks[J]. 21st Computer Vision Winter 
Workshop(CVWW),2016 
[12] J. Manikandan,B. Venkataramani. Study and evaluation of a 
multi-class SVM classifier using diminishing learning technique[J]. 
Neurocomputing,2009,73(10). 
[13] F.Song, X.Tan, X.Liu and S.Chen, Eyes Closeness Detection from 
Still Images with Multi-scale Histograms of Principal Oriented 
Gradients, Pattern Recognition, 2014. 
[14] Zhang Wei, He Jian, Zhang Yan, Zhou Ming. A wearable fatigue 
driving detection system based on EEG and blink frequency[J]. 
Computer Engineering, 2017, 43(02): 293-298+303. 
 


Detection of Blink State Based on Fatigued Driving

Walczyk, Joanna

Sowa-Staszczak, Anna

Diagnostic imaging of gastrointestinal neuroendocrine neoplasms with a focus on ultrasound

Chen, Guoshao

Xu, Fei

English

Design of a Vibration Detection Terminal

Mellick, William

Sharp, Carla

Sumlin, Eric

Trust and general risk-taking in externalizing adolescent inpatients versus non-externalizing psychiatric controls

Not a member yet