11 International Journal for Modern Trends in Science and Technology Smart Attendance Monitoring System to Avoid Fraudulence by Synchronizing Results of RFID and Face Recognition System

11 International Journal for Modern Trends in Science and Technology
Smart Attendance Monitoring System to Avoid Fraudulence by
Synchronizing Results of RFID and Face Recognition System
Prof.M.Ramalingam1
| Prof.A.Jeevanandham1
| Keerthana P2
| Indumathi D2
| Nithyashree M2
|
ThilakRaj S2
| Naveenkumar N2
| Harish R2
1 Assistant Professor, Department of Information, Kongu Engineering College, Perundurai, Tamil Nadu, India
2 Final Year Students, Department of Information Technology, Kongu Engineering College, Perundurai, Tamilnadu, India
To Cite this Article
Prof.M.Ramalingam, Prof.A.Jeevanandham, Keerthana P, Indumathi D, Nithyashree M, ThilakRaj S, Naveenkumar N and
Harish R, “Smart Attendance Monitoring System to Avoid Fraudulence by Synchronizing Results of RFID and Face
Recognition System”, International Journal for Modern Trends in Science and Technology, Vol. 03, Issue 03, 2017, pp.
11-14.
Regularity of student’s attendance is prior in the administration of all the Educational Institutions during
the recent decades. Poor attendance leads to detention which affects the overall academic performance of the
students. Even in this hi-tech century, student’s attendances are marked on attendance sheet delivered by
the faculty members in the classroom, which leads to consumption of time and the process is also completely
manual. Although RFID based and face recognition based implementation have been proposed, but they are
separately implemented. The proposed system for student’s attendance system includes a RFID reader
combined with Face recognition system. RFID readers would be installed at different locations in campus
and also in classes alongside cameras for face recognition. When student enters the campus, reader sends
that location to the server and the student is tracked easily. Server checks the timetable of that student if he/
she is unable to attend lecture according to timetable then notification will be directed to the admin. This
system guarantees that attendance record of the students would be preserved appropriately and efficiently.
The system will accordingly generate detention list of the students. It is minor scale automated application,
which is easy to govern as well as time redeemable and trustworthy.
KEYWORDS: RFID, Face Recognition System
Copyright © 2017 International Journal for Modern Trends in Science and Technology
All rights reserved.
I. INTRODUCTION
Attendance of each and every student during
working hours has to be maintained by the
academic institutions. The faculty who are
handling the classes should maintain the relevant
record of the attendance. The current existing
traditional system is completely manual work and
also time consuming process. Hence there is a need
for a system that should automate this process and
also to identify the actual strength of the students
who came to college out of the strength who left
hostel.
In traditional method, lots of difficulties exist
which includes lost of attendance book, fake
attendance and so on. If the book is lost, faculty
has to create the new attendance book and
therefore absented students get an opportunity to
mark their fake presence in the new log book.
This procedure is hectic and also time
consuming. Therefore, there is a need for an
automated system that should replace all these
traditional human work which would help the
faculty members to maintain and mark the
attendance easily.
II. NEED FOR RFID
RFID is a combination of radar and radio
ABSTRACT
International Journal for Modern Trends in Science and Technology
Volume: 03, Issue No: 03, March 2017
ISSN: 2455-3778
http://www.ijmtst.com

Prof.M.Ramalingam, Prof.A.Jeevanandham, Keerthana P, Indumathi D, Nithyashree M, ThilakRaj S, Naveenkumar N and Harish R :
Smart Attendance Monitoring System to Avoid Fraudulence by Synchronizing Results of RFID and Face Recognition System
broadcast technology. Among various solutions of
available to monitor the log entries that exist in the
market, RFID is the most emerging one that
infrared, Ultra sonic and WIFI. Infrared requires
line of sight property where ultra sonic is costly to
deploy when compared to RFID. As all RFIDs are
essentially originated for wireless sensor
technology, their localization granularity and
precision are similar so that performance
comparison on them is unnecessarily addressed.
III. NEED FOR FACE RECOGNITION TECHNOLOGY
Now-a-days, unique person identification is one
of the most important building blocks for
attendance system. If we use purely RFID based
system for automation, then there will be a
possibility of fake records i.e., proxies may increase
just by using his/her tag.
Biometric based techniques show better
results in identifying an individual instead of
authenticating people and providing them access
to physical and virtual domains based on
passwords, PINs, smart cards, tokens, keys, and so
forth. These methods inspect a person’s
behavioural and physical characteristics to identify
his or her unique identity. But the main drawback
of this mechanism is passwords and pins which are
difficult to remember and can be predicted easily or
stolen.
So, the motive is to identify the person who plays
a vital role. Amongst all the recognition methods
currently in the market, face recognition is well
known as the face modality is used to identify
people in daily life.
Although other approaches like finger print
identification which gives better performance but
the time it takes to recognize a person is high
compared to other techniques. Hence, face
recognition provides best performance for
identifying individual because it does not need to
liaise or take any specific action.
IV. WORKING PRINCIPLE OF RFID
In general, RFID system has a structure as
depicted in figure 1. RFID reader scans tags and
then forwards the information to the backend
database. In the backend, a well defined interface
with appropriate database can be used for storing
information.
When backend receives new information it adds
it to the database and if necessary it performs some
computation on certain fields. Finally the data is
returned from database. In most cases, the
application is collocated with reader itself for eg., in
market barcodes are used instead of RFID tags.
They are more common but the system would
behave as if tags were used. When the reader scans
the barcode, the application uses the identifier to
lookup the details of the person in the database.
Figure 1: Simple RFID system
This section describes how RFID tags work in
general.
There are three types of tags used by RFID. These
are the energy sources of RFID. They are classified
as
 Passive Tags
 Semi Passive Tags
 Active Tags
Passive Tags do not have an internal power
source. Hence, they always rely on the power
induced by the reader. This means that reader
wants to keep up its field until the transaction gets
completed. Because of battery, these tags are
smallest and cheapest tags available in market.
However it also restricts its reading range between
2mm and few meters.
The second type of tags is semi passive tags.
Those tags have an internal power source that
keeps the micro chip powered at all times. There
are many advantages since the chip is powered, it
can respond to requests faster so that number of
requests to be resolved per second will be
increased. The antenna is not required for
collecting power so that it can be used for back
scattering which increases the reading range. Due
to the above two reasons, semi passive tags work
with larger range.
The third type is active tags. Like semi passive
tags they contain an internal power source but
they use the energy supplied for both i.e., to power
up the micro chip and also to generate signal on
the antenna. An active tag generating a signal

without any request is called beacon. It works with
the range of 10 meters and life span is 5 to 6 years.
Frequency Bands:
 Low frequency bands (30-500 KHz)
 High Frequency bands (10-15 MHz)
 Very High Frequency bands (860 – 960 MHz,
300 MHz – 3 GHz, 900 MHz – 915 MHz)
Low frequency tags:
These are cheaper than any of the higher
frequency tags. This is more than enough for most
applications. But, the time needed for a tag to stay
in a sender will increase to load large amount of
data. These tags are least affected by presence of
fluids or metals. Major disadvantage is short range
of reading and the most common frequencies used
will be 125-134.2 KHz, 140-148.5 KHz.
Higher frequency tags:
These tags have higher transmission rates and
works for larger ranges which operate at 13.56
MHz. It is costlier compared to low frequency tags.
Ultra frequency tags:
Ultra frequency tags have the highest range of all
existing tags. It works with range of 3-6 Meters for
passive tags and 30 + meters for active tags. In
addition, the transmission rate of an UHF tag is
very high and allows reading more number of tags
in short time even the tagged entities move faster.
UHF are very expensive and also sensitive to fluids
and metals.
V. FACE RECOGNITION SYSTEM
3D facial recognition technology helps in
identifying a person and also to point out the
different nodal points of a human being and it is
proven with high accuracy. Since it works for 3D
method so that it removes the disadvantage of
correct lighting concepts. Thus the photo of the
person can be taken even in improper lighting and
that too in any angle.
Figure 2: Block Diagram of Face Recognition
are the steps which explain the process of face
recognition.
Detecting the person:
To know the proper working of this process, take a
look at the image shown below.
Figure 3: Face Recognition Process
Alignment of image:
For a 2D image, the system can be accurate
only if the angular position of the face towards the
camera is at least 35 degrees. But for a 3D Image,
the system can be accurate even if the angular
position of the face towards the camera is at 90
degrees. The size and pose can affect the accuracy.
Transfer of measurement:
The system then measures the curves of the
face on a submillimeter scale and creates a
template.
Representation:
The system translates the template into a
unique code. This code gives each code with a set of
numerals to represent the features on a subject’s
face.
Database Matching:
If the image is 3D and the database contains
3D images, then matching will takes place without
any changes being made to the image. However,
there is still a challenge in facing databases that
are having 2D images. 3D images provide a live
moving variable face being compared with flat,
stable image. When a 3D image is taken, different
points are identified. For example; both the eye
balls, nose tip location and so on. Once those
measurements are in place, algorithm will be
applied to the image to convert it to a 2D image.
After comparison the software will then compare
the image with the 2D images in the database to
find a potential match.
Verification or Identification:
In verification, an image will be compared with
anyone of the images within the database. In this
instance, one can take an image and compare it to
a database of shots to identify who is the subject.

In our system, face identification is done on the
premise of still pictures i.e, frontal face catching.
Generally face recognition for static images can be
classified as following groups.
1. Holistic Approach
In this, the entire face is taken as information in
face identification framework to perform face
acknowledgement.
2. Feature Based Approach
Local features of face like eyeballs, nose, and lip
corners are used for identification.
3. Hybrid Approach
This derives the properties of above which uses
both the features and also shape of a face.
VI. PROPOSED SYSTEM
In our proposed system, the major
disadvantage of traditional system will be replaced.
The purely RFID system cannot be applied
completely to monitor the student attendance. As
discussed in section 1, the probability of
fraudulence to occur is very high. Other students
can easily make fake records just by using other’s
cards. So, to avoid fraudulence we have combined
both the technologies. So, the class room
attendance can be monitored and also we can
easily identify those students who came to the
college out of those who left the hostel.
In our approach, the RFID reader will be placed
in hostels and the students can register their
presence and in and out logs in the RFID device.
The classroom attendance will be taken from
the face recognition system implemented in the
class room. By synchronizing both the results of
class room and hostel attendance, we can easily
identify the actual strength that came to college out
of the students who left the hostel after breakfast
and lunch.
Face recognition system is trained with
different sample images of each student at various
angles so as to improve the accuracy of face
recognition. In a class some random group images
will be taken at randomly and the image will
recognize each student based on trained images
and the attendance will be marked as present.
Each day the results of both the system will be
compared and report will be generated to identify
the fraudulence.
VII. CONCLUSION
This paper proposed a student attendance
system by combining RFID and face recognition
technologies. In traditional mechanism it takes
more amount of time to mark the attendance and
the probability of fraudulence to be happen is high.
Thus by implementing the proposed framework
helps in identifying the actual attendance of the
class and also to identify the fraudulence activities
in the campus.
REFERENCES
[1] Arulogun O. T., Olatunbosun, A., Fakolujo O. A.,
and Olaniyi, O. M (2013), “RFID-Based Students
Attendance Management System”,International
Journal of Scientific & Engineering Research
Volume 4, Issue 2, February-2013, ISSN
2229-5518.
[2] Chitresh, S and Amit K (2010),”An efficient
Automatic Attendance Using Fingerprint
Verification Technique”, International Journal on
Computer Science and Engineering (IJCSE),Vol. 2
No. 2,pp 264-269.
[3] Mohamed A.B, Abdel-Hamid A and Mohammed
K.Y.,(2009), ”Implementation of an Improved secure
system detection for E passport by using EPC
RFIDtags”, World Academy of Science, Engineering
and Technology Journal, Volume 6,pp1-5.
[4] Liu C.M and Chen L.S (2009), "Applications of RFID
technology for improving production efficiency in an
Integrated-circuit packaging house," International
Journal of Production Research, vol 47, no. 8, pp.
2203-2216
[5] Sounderpandian J., Boppana R. V., S. Chalasani,
and A. M. Madni, "Models for Cost-Benefit Analysis
of RFID Implementations in Retail Stores, Systems
Journal, IEEE, vol. 1, pp. 105-114, 2007.
[6] Ricardo Tesoriero, José A. Gallud, María D. Lozano,
Víctor M. R. Penichet “Tracking Autonomous
Entities using RFID Technology”, IEEE
Transactions on Consumer Electronics, Vol. 55, No.
2, MAY 2009
[7] Nai-Jian Wang “A Real-time Multi-face Detection
System Implemented on FPGA”, 2012 IEEE
International Symposium on Intelligent Signal
Processing and Communication Systems (ISPACS
2012) November 4-7, 2012
[8] M. H. Yang, N. Ahuja, and D. Kriegmao, “Face
recognition using kernel eigenfaces,” IEEE
International Conference on Image Processing, vol.
1, pp. 10-13, Sept. 2000.
[9] Yugandhara M. Bhoge and Surabhi S.
Deshmukh,”A Survey Paper on Automated
Attendance Monitoring System using Face
Recognition”, International Journal For Research In
Emerging Science And Technology, vol.1 , Special
Issue-1, March-2015.
[10] Nirmalya Kar, Mrinal Kanti Debbarma, Ashim Saha,
and Dwijen Rudra Pal,” Study of Implementing
Automated Attendance System Using Face
Recognition Technique”, International Journal of
Computer and ommunication Engineering, Vol. 1,
No. 2, July 2012.

11 International Journal for Modern Trends in Science and Technology Smart Attendance Monitoring System to Avoid Fraudulence by Synchronizing Results of RFID and Face Recognition System

More Related Content

What's hot (20)

Similar to 11 International Journal for Modern Trends in Science and Technology Smart Attendance Monitoring System to Avoid Fraudulence by Synchronizing Results of RFID and Face Recognition System (20)

Recently uploaded (20)

11 International Journal for Modern Trends in Science and Technology Smart Attendance Monitoring System to Avoid Fraudulence by Synchronizing Results of RFID and Face Recognition System