Effective Attendance Markingusing Face Recognition & RFID Tags

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 807
EFFECTIVE ATTENDANCE MARKINGUSING FACE RECOGNITION & RFID
TAGS
R.Kavitha1, Shankar vijayalakshmi 2, S.UmaMaheswari 3 Mrs.jerrinsimla.A 4
Assistant Professor, Dept. of computer science Engineering, Panimalar Institute of technology, chennai-600 123
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Attendance System is pretty Old Technology to call
the names of the Students Manually. It takes more time to call
each student one by one. Also they might miss outcallingsome
students name. It will not be effective. Due to this student can
get less attendance percentage in their reportcard. soouraim
is to make Attendance automatic. Instead of calling out the
names, rather using RFID system to monitor the student
attendance. To overcome this problem we propose a Effective
attendance marking using RFID. RFID tag is verified then
Camera is initialed. Face Recognition and Matching can be
verified and is processed using Mat lab. Attendance system is
made automatic. After verifying if it matches then it mark as
present such that it will be verifying for all the students .After
the Time limit it will put absent for student those not come to
college and messages will be sent to their parents. As a result,
the proposed system achieves the more effective for marking
attendance.
Key Words: RFID tags, face recognition
1.INTRODUCTION
Face recognition is a well developed technology; it had been
applied to person authentication. Challenges in face
recognition include illumination, pose, facial expression,
aging, hair and glasses. Radio-frequency identification
(RFID) tags contain electronically stored information has
widely used for access control system. However, traditional
RFID-based access control system identifies people only by
RFID card. Anyone presents a registered RFID card will pass
the authentication even he/she is not the card holder. To
avoid this problem, face recognition was involved in the
RFID-based access control system. The proposed access
control system is implemented and performed in a
multinational enterprise. The purpose of this system is used
to inspect who has the permission to enter the factory for
work. All the operations will be recorded with time. HR
manager could check the records from the database.
Experimental results show that the proposed access control
system has strong ability to reject the person presents
others'
RFID card. First, employees are required to present his/her
RFID card. Only the person presents a registered RFID card
will undergo the face recognition. In face recognition, a face
detection technology is applied to extract faces. The
normalization process is used to adjustthesizeandintensity
of the extracted faces. The SURFalgorithmisthenperformed
to align the extracted and registered faces. Finally, the CW-
SSIM is adopted to calculate the similarity of the extracted
and registered faces.
2. Face detection
Robust Real-Time Face Detection is a powerful face
detection technology with high accuracy. The algorithm
consists of three major methods includes integral image,
AdaBoost, and cascade detection. In this paper, the Robust
Real-Time Face Detection is used to detect faces. B. Face
Extraction- Since the backgroundandhairsignificantlyaffect
recognition, background and hairstyle of detected faces are
removed. Only the "inner face" is used to identify the card
holder in the proposed method.
2 .1 Registration
In this module we are going to create an User application by
which the User is allowed to access the data from the Server
of the Cloud Service Provider. Here first the User want to

create an account and then only they are allowed to access
the Network. Once the User create an account, they are to
login into their account and request the Job from the Cloud
Service Provider. Based on the User’s request, the Cloud
Service Provider will process the User requested Job and
respond to them. All the User details will be stored in the
Database of the Cloud Service Provider. In this Project, we
will design the User Interface Frame to Communicate with
the Cloud Server through Network Coding using the
programming Languages like Java/ .Net. By sending the
request to Cloud Server Provider, the User can access the
requested data if they authenticated by the Cloud Service
Provider. Register to the RFID Card and face recognization.
2.2 Class Attendance
In this module we will create attendance system , In colleges
attendance system is pretty old technology to call thenames
manually. Nowadays the technology improved day by dayin
other applications. We never consider about the simple
application such as student attendance system. In thispaper
we are going to implement such a thing like student
attendance system at the same time we are integrating
student behavior monitoring system during the class
session.
Fig: 2.1: Data Flow Diagram
2.3 Face Recognization
In this module a new student tracking technology using
ultrasonic sensor and RFID technology. The system is being
developed for economic with respect to School and College
point of view. RFID tag based Attendance System of every
user is implemented with cheap cost. Two types of
implementation are integrated here. First one isstudent will
be showing RFID tag in front of the Door, which initiates the
camera and Photo is Captured.
2.4 Misbehaviour
In this module used to analyze the misbehavior student.
During the class hours, Ultrasonic sensor which is placed in
the above of the entrance detects any student movement. If
someone leaves in between the class hours or someone
comes late to the class, Ultrasonic is triggered and
automatically camera is initiated which captures the image
and sends it to the server. The Department Head or other
department professors can view the list of students who
bunked or came late using their android application. The
application hits the server and the serverreplieswiththelist
of students who bunked.
2.5 Parents Notification
In this module, parents will download to the android
application .Incase student leave the class hours or comes
late to the class, the HOD can send an SMS to the particular
student’s parents about their behavior.
2.6 Android Application for Parents
Develop an android application. We cannot store lot of data
in a mobile due to limited memory. So, there is no space to
store new files. Also we cannot delete the old files. However,
loss is there. Mobile Client is an Android application which
created and installed in the User’s Android Mobile Phone. So
that we can perform the activities.TheApplicationFirstPage
Consist of the User registrationProcess.We’ll createtheUser
Login Page by Button and Text Field Class in the Android.
While creating the Android Application, we have to design
Shows
RFID tag
Automatically
camera will be
initiate
Face is
captured
Attendance
Marking

the page by dragging the tools like Button, Text field, and
Radio Button. Once we designed the page we have to write
the codes for each. Once we create the full mobile
application, it will generated as Android Platform Kit (APK)
file. This APK file will be installed in the User’s Mobile Phone
an Application.
3. EFFECTIVE ATTENDANCE MARKING ALGORITHMS
3.1THE VIOLA/JONES FACE DETECTOR
It’s a widely used method for real-time object detection.
Training is slow, but detection is very fast. Training Data –
5000 faces , All frontal – 300 million non faces ,9400 non-
face images. The cascade objectdetectorusestheViola-Jones
algorithm to detect people's faces, noses, eyes, mouth, or
upper body. The Viola-Jones algorithm uses Haar-like
features, that is, a scalar product between the image and
some Haar-like templates. More precisely, let I and P denote
an image and a pattern, both of the same size N × N, The
feature associated with pattern P of image I is defined by
3.2 FEATURE EXTRACTION
GLCM, HOG, Gabor Filter Bank
Feature extraction a type of dimensionality reduction that
efficiently represents interesting parts of an image as a
compact feature vector. This approach is useful when image
sizes are large and a reduced feature representation is
required to quickly complete tasks such as image matching
and retrieval. Feature detection, feature extraction, and
matching are often combined to solve common computer
vision problems such as object detection and recognition,
content-based image retrieval, face detection
and recognition, and texture classification.
GLCM (Gray Level Co-occurrence Matrix) Features
The GLCM is a well-established statistical device for
extracting second order texture information from images. A
GLCM is a matrix where the number of rows and columns is
equal to the number of distinct gray levels or pixel values in
the image of that surface. GLCM is a matrixthatdescribesthe
frequency of one gray level appearing in a specified spatial
linear relationship with another gray level withinthearea of
investigation. Given an image, each with an intensity, the
GLCM is a tabulation of how often different combinations of
gray levels co-occur in an image or image section. Texture
feature calculations use the contents of the GLCM to give a
measure of the variation in intensity at the pixel of interest.
Typically, the co-occurrence matrix is computed based on
two parameters, which are the relativedistancebetween the
pixel pair d measured in pixel number and their relative
orientation.
3.3 HOG (Histogram of Oriented Gradient)
Histogram of Oriented Gradients (HOG) features are a
trending topic in object detection. HOG features are a robust
way of describing local object appearances and shapes by
their distribution of intensity gradients or edge directions,
and have been used successfully as a low level feature in a
number of object recognition tasks. Human faces are
generally considered interesting and important to detect in
many applications such as surveillance,recognitionsystems,
biomedical, and video. HOG descriptors have been shown to
significantly outperform existing feature sets for human
detection.
3.4 Gabor Filter Bank
The Gabor filters (GF) are optimally localized in both space
and spatial frequency and getting a set of filtered images
which correspond to a specific scale and orientation
component of the original texture.Inthiswork 5scalesand6
orientations are used in terms of Homogenous Texture
Descriptor. The Gabor functiondefinedforGaborfilterbanks
is written as

s,r
and r-th angular index σ ω s and σ θ r are the standard
deviations of the Gabor function in the radial direction and
the angular direction, respectively.
3.5 FACE RECOGNITION
EUCLIDEAN DISTANCE METHOD
In image analysis, the distance transform measures the
distance of each object point from the nearest boundaryand
is an important tool in computer vision, image processing
and pattern recognition. In the distance transform, binary
image specifies the distance from each pixel to the nearest
non-zero pixel. The euclidean distance is the straight-line
distance between two pixels and is evaluated using the
euclidean norm. The city block distancemetricmeasures the
path between the pixels based on a four connected
neighbourhood and pixels whose edges touch are one unit
apart and pixels diagonally touching are two units apart.
EXPERIMENTAL RESULTS
HOME PAGE
In home page they have four options like add students,
update attendance, attendance details, logout. For adding
any students can use the option add student. To update
attendance we can make changes using update option. Also
view the attendance detail using the attendance details
option.
.
Fig: 3.1: User homepage
The User home page can also be the user menu page. In
figure 4.1,the user should give their name and password.
After providing the valid user name and password it will
login to the database. If the user wishes to update their
profile, they can update the changes.
Fig: 3.2:user login page
4.2 UPDATE ATTENDANCE
Any changes in the student attendance can be modify by
signing it . need to enter the the student id and name then
their will be option like status in that status have to give
what changes have to make it.
Fig: 3.3:user update page
4.3 STUDENT RECORD
In student database it will be recordall thedetails of
the student like either they are present then their time at
when they enter the class and also their outtime.Thiswill be
record all the student.
where Gp ( ω, θ) is Gabor function at the s-th radial index 4.1 LOGIN

Fig: 3.4 :Student record details
5. CONCLUSIONS
This paper proposed a novel access control system that
integrates the RFID and face recognition technology. A real
time face detection method was adopted to detect human
faces. The similarity between the detected and registered
faces was measured by CW-SSIM. To speed up the
authentication process, user pass the authentication when
the similarity larger than a predefined threshold. The SURF
was performed to align the detected and registered image
when the user misses the authentication in the first pass.
REFERENCES
[1] G. Jong, P. Peng, et al., “Multi-recognition combined
security system for intelligent car electronics,”Int. Journal of
Innovative Computing, Information and Control, vol. 8, Apr.
2012.
[2] A. Affandi, M. Awedh, et al., “RFID and Face Recognition
Based Security and Access Control System,” International
Journal of Innovative Research in Science, Engineering and
Technology, vol. 2, Nov 2013.
[3] X.-L. Meng, Z.-W.Song, and X.-Y. Li, “RFID-based security
authentication system based on a novel face-recognition
structure,” WASE Int. Conf. on Information Engineering,
2010.
[4] X. Jiang, B. Mandal, and A. Kot, “EigenFeatures
Regularization and Extraction in Face Recognition,” IEEE
Trans. on Pattern Anal. and Machine Intell., vol. 30, March
2008.

Effective Attendance Markingusing Face Recognition & RFID Tags

More Related Content

What's hot (20)

Similar to Effective Attendance Markingusing Face Recognition & RFID Tags (20)

More from IRJET Journal (20)

Recently uploaded (20)

Effective Attendance Markingusing Face Recognition & RFID Tags