See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/309722042

Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

Article · August 2016

CITATIONS READS

2 9,496

1 author:

Geetha Baskaran
University of Nottingham, Malaysia Campus
17 PUBLICATIONS   31 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Moodle good learning environment? Survey to Support Lecturers in Identifying VARK Learning Styles and Students Learning Experiences View project

Nurse Scheduling using ant colony technique View project

All content following this page was uploaded by Geetha Baskaran on 06 November 2016.

The user has requested enhancement of the downloaded file.

International Journal of Advances in Electronics and Computer Science, ISSN: 2393-2835 Volume-3, Issue-8, Aug.-2016

ATTENDANCE SYSTEM USING A MOBILE DEVICE: FACE

RECOGNITION, GPS OR BOTH?
1
GEETHA BASKARAN, 2AHMAD FARHAN AZNAN
1,2
The University of Nottingham (Malaysia Campus), Computer Science Department
E-mail: 1Geetha.Baskaran@nottingham.edu.my, 2farhan5157@gmail.com

Abstract— In every higher education setting in Malaysia, there are concerns about student attendance, as the current process
of manual attendance taking is not only time consuming but is also inaccurate. Inconsistent attendance in class may
significantlyaffectstudents’overall academic performance. Thus, having a consistent attendance system is important. This
paper proposesa mobile attendance system equipped with face recognition and a GPS locator. The face recognition adopts the
Local Binary Pattern Histogram (LBPH) algorithm and retrieves thestudent’s location using GPS services. This project has a
high potential to replace the current attendance system, as it is designed for speed and accuracy and is moreconvenient than the
current approach.

Keywords— Mobile attendance, Face recognition, GPS, Local Binary Pattern.

I. INTRODUCTION approach to overcome the problems of the current

methods and to make it more convenient for
As a student, it is necessary to attend regularly all lecturersto record their students’ attendance.
lectures, tutorials and lab sessions listed in the Previous attempts at automated time and attendance
timetable. Doing so enables student to learn systems have used electronic tags, barcoded badges,
effectively across the semester with the designed magnetic strip cards, biometrics (vein reader, hand
syllabus. Some might argue that independent learning geometry, fingerprint or facial) and touch screens [4]
is the best way for students to learn and that students in place of paper cards. Such attendance systems try to
have the right to manage their own time, even if this overcome the aforementioned problems by ensuring
means missing class. However, considering the studentsaredirectly interacting with the device and that
amount of money students are paying for their the device is in the particular class in which the student
education, and the fact that lax attendance systems are should be. Conversely, the aim of this project is to
known toaffect particular students’ studies and the create an attendance system that allows students to
university’s reputation [1],attendance recordsare record their attendance using their own mobile device,
important to understand student progress and with the help of face recognition technology and a
development. In some institutions, without a certain GPS locator.Our proposed attendance system does not
percentage of attendance, studentsare not allowed to require any kind of peripheral device other than
sit for an examination, while in some other students’ own smartphones,thereby reducing
institutions,attendance is part of the continuous computational time and avoiding the cost of placing
assessment. physical devices in classes.
The classic attendance system of calling students’
names and recording their presence on paper is easily II. PREVIOUS WORK
manipulated by students [2],who know how to abuse
the system and have their friends record their Several techniques and methods have been accepted to
attendance falsely. The system is also time consuming effectively monitor students’ attendance. Shoewuet al.
and may adversely affect students’ learning [5] proposed a cost-effective computer-based
experience [3]. Imagine how long it would take to embedded attendance management system that
register attendance in a class of 100–300 students allowed the electric monitoring of attendance using
using this method. Further, it would require anelectronic card. These cards, which contain all
preparation on the part of the attendance taker, which necessary information on the individual, are inserted
is tedious, and the lecturer would need to monitor into a machine that records the time and other
students manuallyto detect cases of dishonesty. To information to a server. In another example, Cheng et
solve this problem, some universitieshave introduced al. [6] designed and implemented a system that applies
the Moodle attendance system,where an attendance user identification and a passwordfor authentication.
link is provided for a short period for students to However, the issue with these electronic card or
update their attendance. This method requires students password-based systems is that they allow for the
to login to a device using their own account. However, sharing or dishonest use of the cards or passwords.
while this method improves efficacy, some This problem can be addressed by using a biometric
problemsremain. For example, students can mark their recognition system,such asfingerprint or iris
attendance from outside the class or university with recognition.A system was proposed and implemented
the right timing. Therefore, it is essential to find a new by the authors in [7] and [8] for using fingerprint scans

Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

26
International Journal of Advances in Electronics and Computer Science, ISSN: 2393-2835 Volume-3, Issue-8, Aug.-2016

to record attendance and generate reports after a fixed B. Testing

duration. To have their attendance verified, We piloted our program first in University of
individuals simply had toinsert theirfingers into a Nottingham Malaysia Campus (UNMC) and
fingerprint reader. Polytechnic Sultan Abdul Halim Mu'adzam Shah
In another attempt to address the problem of misuse of located in Jitra, Kedah. We have tested not just in the
electronic attendance-taking systems, Kadry et al [9] smallest room in UNMC as well as the largest room in
proposed a wireless attendance management system UNMC. We conducted the testing usingfourdevices
using an individual’s iris, which is unique, for :Samsung S advance, Oneplus one, Galaxy Mega 2
authentication. In this system,a scanner is used to scan and Samsung S5. The results are identical. The devices
the iris and automatically log in the person. are all similar inits process time which is less than 1
Unlikefingerprints, the iris is more preserved from the second.
external environment. However, both fingerprint- and
iris-recognition-based approachesrequire extra IV. PROPOSED SOLUTION APPROACH
devices and scanners,usually connected to a server.
In radio frequency identification (RFID)-based A. How the Program Works
methods, attendance is recorded in the same way as for The program needs to be installedon an android device
the fingerprint reader, with the only difference being with an active internet connection, GPS and a camera.
the tools used;that is, the RFID card [10]. The RFID Users need to follow some simple steps to enable the
card stores user’s information on the card as data. This program to update their attendance record,including
data is encrypted into the card, which is then used as a permitting the program to obtain their current location
key to record when the user arrives [11]. and providing the necessary input to allow the
In our work, we address the problem of the misuse of program to recognise the student’s face. This program
electronic attendance-taking systems byusing the can only recognise one face at a time.
internet connectivity of smartphones to monitorthe The primary objective of the program is to be able to
presence or attendance of an individual. take attendance using students’ mobile devices
Smartphone-based monitoring systemsprevent the without inaccuracy. For the project to succeed,it must
expense of additional scanning devicesby leveraging employ a location tracker and face recognition to
on the fact that almost all studentsown asmartphone. deliver a reliable attendance system. The face
In our system, an area is fixed for every student. When recognition requires the student to have direct
he or she enters or exitsthat area, a time stamp is saved interaction with the device, while the GPS locator
and the system calculates the duration of any particular specifies the device’s location. Students also benefit
student residingwithin the area. from this system,as they can check their attendance
status for their current classes. Since student can use
III. AGILE METHODOLOGY their own mobile device, which they can bring
anywhere,the system offers excellent mobility.
A. Extreme Programming (XP) To summarise, this program requires the following
Extreme programming (XP) is one of the agile core functions:
methods that emphasize iterative developmentand has  Face recognition
been very effectivein producing high-quality software  A classroom locator
in real-worldprojects with strict time constraints.Table  The ability to register attendance and allow
1 maps the XP practices, distinguishing the XP students to access their attendance record.
practices which address the software quality andthose 1) FacialRecognition Technology
which address the development process quality. We A camera is needed to use facial recognition. Before
used this mapping to address the software quality, deploying the application to users, it must be
emphasize technical and code-oriented aspects, initialised with the required dataset images (facial
whereas the XP practices,which address the images of the students),which will be processed at the
development process, emphasize human and social start of the program. To ensure the optimal speed of
aspects. Needless to say that bothaspects are important the program, the dataset images must be minimised.
and there is a synergetic relationship among them [12]. The best way of doing this is by separating the dataset
images by course. Thus, every student in each course
Table 1: XP practices mapping with respect to would use the same application, except it will have
quality subjects been initialised with different images. Once the
program has been loaded with the student images, it
will be able to recognise students’ faces by using an
appropriate algorithmto compare the current frame
image with the one that has been initialised.
Initialising the images in the program before
generating the installer provides much greater
reliability because students cannot easily alter the
initialised images.

Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

27
International Journal of Advances in Electronics and Computer Science, ISSN: 2393-2835 Volume-3, Issue-8, Aug.-2016

2) Classroom or Location Locator D. Local Binary Pattern Histogram

GPS coordinatesare requiredfor the program to Only a few facerecognition algorithms are provided in
instantly determine the student’s current location, the OpenCV library,including Local Binary Pattern
based on the coordinates received. Using GPS, we can Histograms (LBPH), Eigenfaces and Fisherfaces. This
obtain both x- and y-coordinates up to 6 decimal project uses LBPH, which takes a different approach
points with the help of ground and space satellites. The comparedto the other methods. In LBPH,
location becomes even more accurate with the help of characterisation of featuresis done locally,whereas
cellular network providers. To interpret the other approaches process the image as a whole.
coordinates, the program must be integrated with TheLBP algorithm comes from a visual descriptor for
Google Maps APIs so that users can view the visual pattern classification mainly used in computer vision.
location of the coordinates receive. A credential is In this project, training imageswere set to 128 X 128
required to use the Google Maps APIs service,which pixels. It is important to maintain the image size to
can be obtainedby placing a request through Google avoid affecting the face recognition rate. This is
console. because the LBPH algorithm is highly prone to scaled
images. That is, once the algorithm extracts a feature,
3) Register Attendance the program can only identify the person when
The system automatically updatesattendance in the provided with an image at the same scale (in pixels).
database for any faces that the program could The first requirement of the LBPH algorithm or the
recognise. Students’ mobile devices are remotely pre-processing procedure is to convert the image to
connected to the local database. The information grayscale mode. Grayscale imagesare not images in
updatedis student name, x-coordinate, y-coordinate, black and white or binary images; instead, grayscale
classroom and timestamp. In addition to registering mode is a series of numbers, each of which represents
attendance, the application allows students to access a different intensity level. Having images in grayscale
their attendance record. The x- and y-coordinates mode represents a significant advantage when using
stored during attendance registration can also be the LBPH algorithm,as the image can be treated as a
retrieved to show the location on Google Maps.The vector to extract valuable information. Next, for each
workflow for this program is outlined in Section B pixel in the grayscale image, we select a
(Fig.1). neighbouringpixel of size 8 surrounding the centre
pixel. The LBP value is calculated based on the centre
C. Overall Workflow of Program value by thresholding it to a 3 X 3 array. The intensity
level threshold is set to 8. A more formal description
of the LBP operator can be given as equation
(1),where the notation (P, R) denotes a neighbourhood
of P sampling points on a circle of radius R:

LBP , ( , ) = S(

− ) 2 (1)

Formally, given a pixel at (Xc,Yc), the resulting LBP

can be expressed in decimal form as in equation
(1),where intensity ip and ic are respectively gray-level
values of the central pixel and P surrounding pixels in
the circle neighbourhood with a radius R, and function
s(x) is defined as:

The operator LBP (P, R) creates 2p different output

values, matching to 2p different binary patterns
formed by P pixels in the neighborhood.The basic
LBP operator is invariant to monotonic gray-scale
transformations maintaining pixel strength order in the
local neighborhoods. The histogram of LBP labels
calculated over a region can be exploited as a texture
descriptor.Fig.2 is an example of calculating the LBP
Fig.1. Attendance system overall workflow value with a neighbouring size 8 pixel.

Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

28
International Journal of Advances in Electronics and Computer Science, ISSN: 2393-2835 Volume-3, Issue-8, Aug.-2016

Fig. 4 illustrates on the right the output value from the

original image on the left. The process of thresholding,
accumulating binary strings and storing the calculated
LBP value is repeated for each pixel in the input
image. After obtaining all LBP values for each pixel,
the next step is the histogram. The histogram
represents the number of times each LBP pattern
occurs that acts as a feature vector. TheLBPH
Input Output algorithm represents the local structure of an image by
Fig.2.Calculation of LBP value—size 8 pixel
calculating the histogram efficiently and summarising
In the above figure, the value 4 is the centre pixel. the histogram across different blocks.
Note that each of the values represents acolour What makes the LBPH algorithm different from others
intensity. Theexpected output is an 8 binary digit for is that each image in the dataset is locally
each pixel LBP calculation. After performing the LBP characterised. When a new image is provided, the
calculation, the value is stored in a 2D array with the same feature analysis is performed and the result is
exact same dimension as the input image. With 8 compared to the dataset images. The purpose is to
adjacent pixels converted to binary digits, we have a analyse the local structure in an image by comparing
total of 2^8 = 256 possible combinations of local each pixel with each adjacent pixel. For example,a
binary patterns. The stored result in an 8-bit array can pixel is taken as centre and then thresholded against its
be processed to obtain a decimal value. This process is neighbours. A neighbour with greater or equal
visualised in Fig.3. intensity is denotedby1,with lesser intensity denoted
as 0. This process resultsin a binary number foreach
pixel (e.g., 1101011). Theoretically, with 8
surrounding pixels, there are2^8 possible
combinationsofLBPs.
To summarise, the steps to createLBP histogramsare
as follows:
1. Convert image to grayscale
2. Calculate the LBP for each pixel
3. Create a histogram based on each of the LBP
values
4. When new faces areprovided, generate the
LBP histogram exactly as was done forthe
trained image.
5. Recognition comes when a new histogram
matches the histogram pattern of a trained
image.

E. GPS
Mobile phones equipped with a GPS receiver
arereadilyavailable onthe market. The General Packet
Radio Service (GPRS) is currently one of the best and
Fig.3.LBP value stored in a 2D array
cheapest communication modes available.The
For the purpose of illustration, we start at the top right attendance system is deployed onthis kind of mobile
and move clockwise (the blue boxes indicate the phone, which is supported to perform all
sequence) to accumulate the binary string. Note that requiredoperations. When the application is started on
the sequence of collecting the binary string does not a user’smobile phone for the first time, they are
matter provided we use the same sequence for all other prompted to register.Thereafter, the user opensthe
Local Binary Pattern (LBP) calculations. software by entering theirusername and password.
Whenthe user enters their username and
password,thesearechecked for authenticity. If not
authenticated, the user is prompted with a message of
wrong username and password and may re-enter their
log in details.

V. DEVELOPMENT ENVIRONMENT

The Java-enforced object-oriented programming

language developed by Sun Microsystems was chosen
Fig.4.The output value from the original image for implementing this mobile program. It is designed

Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

29
International Journal of Advances in Electronics and Computer Science, ISSN: 2393-2835 Volume-3, Issue-8, Aug.-2016

to have as few implementation dependencies as

possible. We have used Java version 1.7.0, designed
for 64-bit operating systems. The reason for choosing
Java is the platform’s independence criteria. A Java
program can be developed and run on almost any
computer that comes with the Java Runtime
Environment. Java applications are usually converted
into a special byte code so that they can run on any
virtual Java machine, regardless of the computer
architecture. Moreover, the PHP language is a
hypertext processor widely used by web developers,
particularly in server-side scripting language. In this
project, we implement a short PHP that acts as a
translator between the database and the application
itself. The PHP script will be placed in the XAMPP
local web server. Fig.5. Main Menu

The developed software required a database to store Fig.5 shows the main menu of our system. We design
thedata and managecommunication between the the interface design in a simplicity way by mainly
application and database. XAMPP wasthe perfect focusing on user-friendly aspect. The sequence
solution. XML stands for Extensible Markup numbered presented in fig.5illustrate step of taking
Language, which functions as a set of rules for attendance.However, student can navigate to any other
encoding format. XML is also used in android function available such as locating current location,
development for purposes such as defining taking attendance with face recognition and accessing
applications’ user interfaces, describing components attendance log as they want. The enrolment and
of the system and for minor purposessuch as replacing registration phase is an administrative phase in which
hard-coded strings with a single string. the administrator (staff) needs to log in as shown in
fig.6. The studentsface photos as well as the other
Forthe development environment,we chose the newest bio-data are stored for the first time into the database
modern integrated development environment, Android for student registration. The student can login to the
Studio,developed by Jet Brains. Android Studio was main menu through the student login.
designed specifically for android development
purposes and has taken over end support for Eclipse
(another integrated development environment for
android)from Google. The official language of
Android Studio is Java,as alarge part of android
iswritten in Java and its API isintended to be called
from Java. Android Studiois a very useful tool because
each of itsmodules is independent andcan be run,
tested and debugged without affecting another
module. Moreover, Android Studio provides
improved features for interface design, includinga
drag and drop feature and a delivering mechanism for
interaction with resources and multi-tasking. Android
Studio alsohelpsdevelopersby adding an external
library and providing complete support forJunit and Fig.6. Thesystem login
android testing. Forthis project, Android Studio G. Test Data
version 1.5 was used throughoutthe software
development process.

IV. RESULTS AND DISCUSSION

The system proposed is a real-time system. The

experimental results showed that the acceptance
detection ratio of our suggested algorithm ranged from
75% to 95%. The result of the analysis process is
presented below:

F. Main Menu and Login

Fig.7. Faces in different lighting and distance

Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

30
International Journal of Advances in Electronics and Computer Science, ISSN: 2393-2835 Volume-3, Issue-8, Aug.-2016

Fig.7 shows some sample faces captured during the

registration phase. There are four different samples of
lighting, angle and distance taken.

H. Location detector

Fig.10. Attendance log

Fig.8. Left figure: Current Location, Right figure: Building Students can navigate to this windows activity by click
Markers the “check attendance” button in the main menu.
Later, they will need to click again the “check
The next interface is the location map. Once the attendance” button in the current interface to see the
student click “Your Location” button, it will directly student attendance record appear in the location. This
open google map interface. Refer to fig.8 (left), the button will also trigger the connection between
maps is programmed to zoom at user’s current application and database. Thus, allowing attendance
location. However, if the student wish to control the record to be display. Notice that the interface is
range of the map displayed, they able to that with the divided into 2 sections and both section are scrollable
zoom in and out button. To increase the student to fit all the information retrieved. The upper part is to
understanding of the map, the map has been flagged list down the entire student along with their details.
for each building such as in fig.8 (right). Meanwhile at the bottom, user can click on the student
name to display student’s location in the map and also
I. Face Recognition can print reports of attendance as fig. 11 shows an
example.

Fig.11. Database attendance log report

CONCLUSION

Fig.9. Face Recognition Interface This paper proposed a smart, location-based time and
attendance tracking system that runs as a mobile
Next interface is the face recognition mode designed application on a smartphoneand uses location and face
in a landscape mode. As noticed, there is a camera detection as its core components.The classroom area is
frame in the middle of interface for the purpose of face set for tracking using GPS, and student coordinates
recognition. Any face detected will then converted inside the area show thatthe student is present in the
into grayscale image and displayed at the top right class. The attendance system has been designed to
corner. So basically, the video frame provides the improve the efficiency of the student
program with lots of static image. This feature attendance-taking process and to reduce the rate of
provides more odds to be recognized by the program. errors in managing students’ attendance records.
Once the student has been recognized by the program,
a text will be prompted to notify the user their REFERENCES
attendance has been marked. Student also has the
authority to access face image gallery. However, they [1] U. Jain, M. Shirodkar, V. Sinha and B. Nemade., “
Automated Attendance Management System using Face
cannot add any new image. Recognition,” IJCA Proceedings on International
Conference and Workshop on Emerging Trends in
J. Attendance log Technology ICWET 2015(2):23-28, May 2015.
[2] A. Jha, “Class Room Attendance System Using Facial
Recognition System,” The International Journal of

Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

31
 International Journal of Advances in Electronics and Computer Science, ISSN: 2393-2835 Volume-3, Issue-8, Aug.-2016
Mathematics, Science, Technology and [8] Shoewu, O. and O.A. Idowu (2012), “Development of
Management,(ISSN : 2319-8125) Vol. 2 Issue 3. Attendance Management System usingBiometrics”, Pacific
[3] Lodha, R., Gupta, S., Jain, H. and Narula, H.,“Bluetooth Journal of Science and Technology, 13(1):300-307.
Smart Based Attendance Management System.”Procedia [9] Kadry, S., &Smaili, M. (2013). ”Wireless attendance
Computer Science, 45, pp.524-527, 2015. management system based on iris recognition”,Scientific
[4] 3M Electronic Safety Systems[Online] Research and essays, 5(12), 1428-1435.
Available on 4.5.16 [10] BISAM-BIS attendance Management System by
athttp://www.3msys.com/products/biometric-attendance-sy BISSoftware Development Services PVT Limited.
stems/ [Online].
[5] Shoewu, O. O. M. Olaniyi, and Lawson, “Embedded Availableon 4.5.16 at
Computer-Based Lecture AttendanceManagement http://www.softwarehouse.co/school-attendancebrochure.
System”, African Journal of Computing and ICT (Journal [11] RFIDSensNet Lab (2005), A white paper on
of IEEE Nigeria ComputerSection), 4(3):27 – 36, 2011. AutomaticAttendance System. Texas A & M University,
[6] Cheng, K., L. Xiang, T. Hirota, and K. Ushijimaa (2005), Texas, USA.
“Effective Teaching for Large Classes withRental PCs by [12] Dubinsky, Y. and hazzan, O, “Improvement of Software
Web System WTS”, Pro. Data Engineering Workshop Quality: Introducing eXtreme Programming into a
(DEWS2005), 1D – d3 (inJapanese). Project-based Course. The proceeding of the 14th
[7] M. K. P. Basheer and C. V. Raghu, “Fingerprint International Conference of the Israel Society for Quality,
attendancesystem for classroom needs,” in Proc. India Jerusalem, Israel 2002.
Conference(INDICON), 2012 AnnualIEEE, pp. 433-438,
7-9 Dec. 2012.



Attendance System Using a Mobile Device: Face Recognition, GPS or Both?

32

View publication stats