IRJET- Student Attendance System by Face Detection

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2206
Student Attendance System by Face Detection
Abhinav Mishra1, Aditya Kumar2, Prof.Ashutosh Pandey3
1,2,3Computer Science and Engineering, ABES Institute of Technology, Ghaziabad, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract-The uniqueness or individuality of anindividualis
his face. In this project, a person's face is used for automatic
presence. Student attendance is very important for every
college, university, and school. The methodology of
conventional attendance can be called registration of student
names or number of roles and recording of attendance.
Spending time for this purpose is an important concern.
Suppose the duration of the topic is approximately 60minutes
or 1 hour and that after the session it takes 10 to 15 minutes.
For every teacher, it's long-lasting. In order to avoid these
losses, an automated process based on image processing is
used in this project. In this project, face recognition and facial
recognition are used. Face detection is used to determine the
position of the face, and face recognition is used to draw
attention to the repression. The database of all students in the
class is stored and when the individualstudent'sfaceispresent
on one of the persons stored in the database.
Key Words: Image processing, Face Recognition, Face
Detection, Principal Component Analysis (PCA), Eigen
Face.
1. INTRODUCTION
Maintaining participation in all learning institutions is
important to monitor student performance.Inmostlearning
institutions, students receive a list of attendances issued by
department heads as part of theregulations.Studentsrecord
these forms and then enter or manually enter the computer
for future analysis. Thismethodisannoying,timeconsuming
and inaccurate because some students often sign their
absent colleagues. This approach also makes it difficult to
find individual students ina largeclassroomenvironment.In
this project, we propose a design and use of a face detection
and recognition systemthatautomaticallyallowsstudentsto
keep abreast of lectures in the classroom and mark their
presence by identifying their faces.
While other biometric methods (such as iris scans or
fingerprints) may be more accurate, students often have to
wait a long time when they enter the classroom. Face
recognition is chosen because of its non-invasiveness and
familiarity, as people identifyothersbasedprimarilyontheir
facial function. The (face) biometric system will include a
registration process in which the unique features of the face
are stored in a database, followed by an identification and
verification process. The face in the detected image
(obtained from the camera) is compared to the previously
saved face captured in the project.
2. LITERATURE SURVEY
Digital image processing is essentially digital image
processing. Digital imaging technology is driven by three
main applications:
1 Improve the image information of human
perception
2 Image processing for automatic machines
3 Efficient storage and transfer.
2.1 Human Perception
This application employs a method to improve image
information for human interpretation and analysis. Typical
applications include: Noise filtering content enhancement is
mainly contrast enhancement or anti-blur and remote
sensing.
2.2 Machine Vision Applications
Here, attention is focused on processing of extracting image
information suitable for computer processing. Typical
applications are included.
 Industrial machine vision for product
assembly and inspection.
 Automated target detection and tracking.
 Finger print recognition.
 Weather processing and mechanical
processing for aerial and satellite
images that crops evaluate.
Facial detection and recognition falls within the machine
vision application of digital image processing.

3. WORK FLOW
Fig -1: Flow Diagram
3.1 Methodology
Given an unknown face of the same size as the training setof
M images, the PCA eigenface method, as shown, intends to
represent the face image as a linear combination of a set of
eigenfaces / featurevectors.TheseEigenfaces(eigenvectors)
are in fact the principle components of the training set of
face images generated after reducing the dimensionality of
the training set. Once Eigenfaces are selected, each training
set image is represented in terms of these eigenfaces. When
an unknown face comes for recognition, it is also
represented in terms of the selected eigenfaces.
Fig -2: A training set consisting of M images
3.2 Data set creation
For the database we have to capture the photos of our
webcam or the external camera. To do this, based on the
camera we use, we need to install the library from the
website www.opencv.org on the OpenCV website. Then we
need at least 500 to 1000 captures togeta higherpercentage
of our due and to achieve the goal we are making in this
project. We can store information on the form of separate
folders, which separates each person from others.
Fig -3: Dataset
3.3 Data set Training
Training is given so that picture captured by webcam or the
external camera is trained. Here we tell that a specific
picture is associated to a particular label.Thatlabel isunique
about that picture. Whenever that picture come across that
unique label is projected or that picture is identified.
Fig -4: Training Dataset
Here in Fig 4 we can see that that data set is being trained
and unique id given to data set is 1.
3.4 Face Detection
Face Recognizer compares the face for recording on an
image recorded with people recorded during the recording.
If it matches, it gets the name associated with the person to
enter. Face detection we can do it using the cascading class
of the object and we use the b-box method. The face
detection system that uses the cascade installation was

purchased with the most popular face recognition model,
Viola Jones. These are some of the objects present. Theseare
in the form of small blocks that contain them. They are
passed through an image and move through each block of
images and they are checked if they overlap. First we will
convert the gray-gray-gray-gray image. The faces of the
captured image are collected. The capturedfacesarecutinto
small resolution images of 114x94 resolution.It must be
around 15 KB.
Fig -5: Detected Face
Here in Fig 5 we can see that face is asociated with unique id
1.
3.5 Result
Fig -6: Result saved in database
In Fig 6 we can see that at number 3 ID 1 is saved with name
labelled “Abhinav” of section ‘A’ is present which is
denoted by ‘P’.
3.6 Conclusion
It can be concluded that a reliable, safe, fast and efficient
classroom management system has been developed that
replaces a manual and unreliable system. This facial
recognition and recognition system saves time, reduces
administration and replaces the office equipment currently
used with existing electronic devices.
No special hardware is required to install the system as only
one computer and one camera are used. The camera plays a
crucial role in the performance of the system. You should
therefore test the image quality and performance of the
camera in real time, especially if the system is powered by a
live camcorder.
The system can also be used in licensed and authenticaccess
control systems (availability of accessibility), personal
security video surveillance systems or law enforcement.
The main threat to the system is spoofing. For future
updates, anti-spoofing techniques, suchaseyedetection,can
be used to distinguish directlyfromstaticimages whenfacial
images taken from a class undergo facial recognition. Of the
overall system efficiency (80.1%), human intervention may
be required to make the system unique. In this way, you can
add a module that converts all unidentified faces and can be
manually corrected by the teacher.
Future tasks include adding well-structuredhelp records for
each class, as well as the ability to create monthly support
reports and automatically submit the same eligible
reviewers.
REFERENCES
[1] C. Kotropoulos and I. Pitas, “Rule-based face detection in
frontal views,” Proc. Int’l Conf. Acoustics, Speech and Signal
Processing, vol. 4, pp. 2537-2540, 1997.
[2] G. Yang and T. S. Huang, “Human face detection in
complex background,” Pattern Recognition Letter, vol. 27,
no.1, pp. 53-63, 1994.
[3] Muhammad Fuzail, Hafiz Muhammad Fahad Nouman.
Muhammad Omer Mushtaq, Binish Raza Awais Tayyab,
Muhammad Waqas Talib. “Face Detection System for
Attendance of Class Student”. International Journal of
Multidisciplinary SciencesandEngineering,Vol.No.5,4, April
2014.
[4] Dayanand S. Shilwant, Dr. A. R. Karwankar. “Student
Monitoring by Face Recognition System”. International
Jounaral of Electronic, Communication & Soft Computing
Science and Engineering (IJECSCSE) ISSN 2277-9477,
Volume 2, Issue 2.

[5] T. Matthew and A. Pentland, Eigenfaces for Recognition,
vol.3,Volume3,Number1vols. Vision and Modelling Group,
The Media Laboratory, MIT: Journal of Cognitive
Neuroscience, 1991.
[6] Anil K Jain, Lin Hong, Sharath Pankanti, and Ruud Bolle,
Biometric Identification. IEEE, 2004.
[7] Balwant Singh, Sunil Kumar, Paurush Bhulania “Lecture
Attendance System with Face Recognition and Image
Processing”. International Journal of Advance Research in
Science and Engineering IJARSE.Vol. No.2,IssueNo.3,March,
2013.
[8] Seema Rao and Prof.K.J.Satoa,“AnAttendanceMonitoring
System Using Biometrics Authentication”, International
Journal of Advanced Research in Computer Science and
Software Engineering, Volume 3, Issue 4, April 2013, ISSN:
2277 128X.
[9] P. Viola and M. J. Jones, “Robust real-time face detection,”
Int. J. Comput. Vis., vol. 57, no. 2, pp. 137–154, 2004.
[10] Jomon Joseph, K.P.Zacharia, “Automated Attendance
Management System using Face Recognition”, international
Journal of Science and Research, Volume 2 Issue
11,November 2013.

IRJET- Student Attendance System by Face Detection

More Related Content

What's hot (19)

Similar to IRJET- Student Attendance System by Face Detection (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- Student Attendance System by Face Detection