International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 08 Issue: 02 | Feb 2021 www.irjet.net p-ISSN: 2395-0072

“APPLICATION OF FACE RECOGNITION FOR ATTENDANCE SYSTEM”

Ms. Pranjal P Waghunde1 Mr. Akshay A Sabale3
Zeal College of Engineering and Research Pune Zeal College of Engineering and Research Pune
Student in Information Technology Student in Information Technology
Savitribai Phule Pune University Maharashtra Savitribai Phule Pune University Maharashtra

Ms. Manali P Tayde2 Mr. Yashpal B Sawant4

Zeal College of Engineering and Research Pune Zeal College of Engineering and Research Pune
Student in Information Technology Student in Information Technology
Savitribai Phule Pune University Maharashtra Savitribai Phule Pune University Maharashtra

Prof. Amarnath S. Chadchankar

Zeal College of Engineering and Research Pune
Asst. Prof Information Technology Department

---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - This paper represents the prototype of an members. But it is a time consuming event. Also, it is very
automated Online Biometric-enabled Class Attendance difficult to verify students one by one in a large classroom
Register System (OBCARS). The system is designed and environment, whether they are present or not. The proposed
developed to address the obstacles of misplaced and/or torn system demonstrates how face recognition is used for taking
attendance register paper sheets in various classrooms in attendance of a student automatically using Java, how to
Higher Educational Institutions. The system is built to provide store the faces in the database and how to retrieve the
an efficient and effective class attendance tracking method absent list.
that avoids attendance marking impersonation among
students, and simplify students’ attendance record It determines if the image of the face of any given person
computation. Biometric appreciation comprises alike, within matches any of the face images stored in a database. This
an open-mindedness of calculation, of pragmatic biometric problem is challenging to resolve automatically due to the
behaviors on the contrary of formerly poised data for a focus. changes that various factors, such as facial expression, aging
Estimated identical is obligatory due to the dissimilarities in and even lighting, can cause on the image. Amongst different
biological characteristics, deeds both within and among biometric techniques facial recognition may be unreliable
persons. On the basis of student's presence in the class, the but it has several advantages over the others. This system is
attendance will be generated by the system. The face of the proven to be useful in various areas such as security and
student is recognized and it saves the response in database access control, forensic medicine, police controls and in
automatically by the system. attendance management system. The various techniques for
marking attendance are:
Key Words : Face Recognition, Attendance system and
1) Signature based System
Bio-metric, etc.
2) Fingerprint based System

1.INTRODUCTION: 3) Iris Recognition

Face recognition is one of the few biometric methods that 4) RFID based System
includes the merits of both accuracy and low intrusiveness.
Due to this reason since the 70’s, face recognition has gained 5) Face Recognition
attention of researchers in fields from security and image
processing to computer vision. Face recognition is Amongst the above techniques, Face Recognition is
considered useful in multimedia information processing natural, easy to use and does not require aid from the test
areas. Traditionally, attendances are taken manually in the subject.. It is a series of several related problems which are
class room using attendance registers given to the faculty solved step by step:

© 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2299
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 08 Issue: 02 | Feb 2021 www.irjet.net p-ISSN: 2395-0072

1) To capture a picture and discern all the faces in it. 2. A web enabled secured system for attendance monitoring
and real time location tracking using Biometric and Radio
2) Concentrate on one face at a time and Frequency Identification (RFID) technology.
understand that even if a face is turned in a strange
direction or in bad lighting, it is still the same Srinidhi MB ; Romil Roy
person.
Published in: 2015 International Conference on Computer
3) Determine various unique features of the face Communication and Informatics (ICCCI)
that can help in distinguishing it from the face of
any other person. These characteristics can be the The main idea of this paper is to built a safe and secure web
size eyes, nose, length of face, skin colour, etc . based attendance monitoring system using Biometrics and
Radio Frequency Identification (RFID) Technology based on
4) Compare these distinctive features of that face to multi-tier architecture, for both computers and
all the faces of people we already know to find out smartphones.
the person’s name. Human brain is made to do all of
Limitation: Students can exchange their RFID cards.
this automatically and instantaneously. Computers
are not capable of such kind of high-level 3.Real-Time Online Attendance System Based on Fingerprint
generalization, so we need to teach or program each and GPS in the Smartphone.
step of face recognition separately to the system.
Face recognition system is further divided into two Lia Kamelia; Eki Ahmad Dzaki Hamidi; Wahvudin
categories i.e. verification and identification. Face Darmalaksana; Afit Nugraha
verification is a 1:1 match which compares a face
image against a template face images, whose Published in: 2018 4th International Conference on Wireless
identity is being claimed. Contradictory, face and Telematics (ICWT)
identification is a 1:N problem that compares a
The purpose of the research is to develop an online presence
query face image.
system which is a combination of fingerprint modules and
GPS. The ZFM-20 fingerprint module is used as the system's
2.LITERATURE SURVEY main input as well as a security tool as an entrance to get
access to the entire system. To determine the user's location
1.Aadhaar Based Biometric Attendance System Using
and sends it to the smartphone, GPS Module is used. Arduino
Wireless Fingerprint Terminals.
module present in the system will send a text message to the
Narra Dhanalakshmi; Saketi Goutham Kumar; Y Padma Sai. parties concerned about the user's location data
automatically.
Published in: 2017 IEEE 7th International Advance
Computing Conference (IACC) Limitation: It is a fingerprint based system and has its own
disadvantages.
In this paper, two different approaches are proposed to
authenticate the captured fingerprint in the process of 4.Design and Implementation of a Student Attendance
verification. The first approach uses data base which is System Using Iris Biometric Recognition.
created by the organization itself and the second approach
uses the Aadhaar Central Identification Repository (CIDR). Kennedy O. Okokpujie; Etinosa Noma-Osaghae; Olatunji J.
Wireless fingerprint terminals are used to capture and store Okesola; Samuel N. John; Okonigene Robert.
the attendance records of the students in the device data
Published in: 2017 International Conference on
base and updating them to the server data base. SMS Alerts
Computational Science and Computational Intelligence
are sent to students and their parents in case of their
(CSCI)
irregularity, absence or shortage of attendance.
In this paper, the iris of human eye is used as a biometric.
Limitation: Aadhar Data may not be available and also
After enrolling all attendees by storing their particulars
fingerprint bases system has its own drawbacks.
along with their unique iris template, the designed system
automatically took class attendance by capturing the eye

© 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2300
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 08 Issue: 02 | Feb 2021 www.irjet.net p-ISSN: 2395-0072

image of each attendee, recognizing the user's iris, and 5.PROPOSED SYSTEM:
searching for a match in the database created.

Limitation: This system is not cost effective.

5.Development of an Online Biometric-enabled Class

Attendance Register System.

Victor Oluwatobiloba Adeniji; Mfundo Shakes Scott; Nomnga

Phumzile.
Fig.1: Proposed system architecture.
Published in: IST-Africa 2016 Conference Proceedings Paul
Cunningham and Miriam Cunningham (Eds) IIMC Proposed system is biometric attendance system using face
International Information Management Corporation, 2016 recognition. Face detection has been extensively researched
ISBN: 978-1-905824-55-7. in past few decades. It is a specific case of object detection
which determines the size of candidate faces in an image. It
In this paper, the system was designed to record attendances is a process of designing a system by giving input consisting
of students for both lectures and exams with aid of of images that contains faces and then training a classifier to
Fingerprint. Through the system, the attendance records of identify a face in an image. The main focus of this system is
the students are managed online as Admin and Lecturers can to decrease false positive rate thereby increasing accuracy.
view and modify the student’s attendance data via Web
browser. 6.ALGORITHM:

Limitation: It is a Fingerprint based system which has its The main idea of Principal Component Analysis (PCA) is to
own disadvantages. reduce the dimensionality of a data set including of many
variables that are related with each other, either heavily or
3.PROBLEM STATEMENT: lightly, while retaining the variation consisted in the dataset,
up to the maximum extent. The same process is done by
To develop a windows based prototype model for biometric
transforming the variables to a new set of variables, which
attendance system using face recognition using python
are called as the principal components (or simply, the PCs)
programming language.
and are orthogonal, ordered in such a way that the retention
OBJECTIVES: of variation present in the original variables decreases as we
move down in the order. Hence, the 1st principal component
1. To detect faces. retains maximum variation that was present in the original
components. The eigenvectors of a covariance matrix are the
2. To mark attendance. principal components, and hence they are orthogonal.

2. To check defaulter list. 7.EXPECTED RESULTS:

1. Face Recognition
4.MOTIVATION:
2. Marking Attendance
Recently, image processing which extracts useful 3. Defaulter Detection
information from a digital image plays a unique role in the
advent of technological advancements. It focuses on two 8.ADVANTAGES:
tasks i.e. improvement in pictorial information of human
interpretation, loading of image data for storage, 1. Ease in maintaining attendance.
transmission and representation for autonomous machine 2. Reduced paper work.
perception. Also people have started the usage of image 3. Automatically operated and accurate.
capturing devices never as before with the advent of smart 4. Reliable and user friendly.
phones and closed circuit television. 5. Increased productivity.

© 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2301
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 08 Issue: 02 | Feb 2021 www.irjet.net p-ISSN: 2395-0072

9.APPLICATIONS: on Automatic Face & Gesture Recognition. IEEE, 2018:577-

584.
1. To verify identities in Government organizations.
2. Enterprises. [5] ZHOU Feiyan, JIN Linpeng, DONG Jun. A review of
3. Attendance in Schools and colleges. convolutional neural networks[J]. Chinese Journal of
4. To detect fake entries at international borders.
5. Industries. Computers, 2017, 40(6): 1229-1251.

[6] Chang Liang, Deng Xiaoming, Zhou Mingquan, et al.

Convolutional Neural Networks in Image Understanding[J].

10.CONCLUSION & FUTURE WORK: Acta Automatica Sinica, 2016, 42(9):1300-1312.

In this system we are going to implement an attendance [7] Yang J, Ren P, Zhang D, et al. Neural Aggregation Network
system for a lecture, section or laboratory by which lecturer for Video Face Recognition [C]// IEEE Conference on
or teaching assistant can record students’ attendance. It will
Computer Vision and Pattern Recognition. IEEE, 2017: 5216-
save time and effort, especially if it is a lecture with huge
number of students. Automated Attendance System has 5225.
been envisioned for reducing the drawbacks in the
traditional (manual) system. [8] Shi Xuechao, Zhou Yatong, Chi Yue. Face gender
recognition based on multi-layer feature fusion adjustable
This attendance system demonstrates the use of image
processing techniques in classroom. This system can not supervised function convolutional neural network[J]. Journal
only merely help in the attendance system, but also improve of Computer Applications, 2019(4).
the goodwill of an institution.
[9] Viola, M. J. Jones and Paul, "Robust real-time face

11.REFERENCES : detection.," in International journal of computer vision 57.2

(2004), 2004.
[1] Pss S, Bhaskar M. RFID and pose invariant face
verification based automated classroom attendance system [10] A. Jha, ""Class Room Attendance System Using Facial
[C]// International Conference on Microelectronics, Recognition System."," in International journal of
Computing and Communications. IEEE, 2016:1-6. Mathematical science technology and management 2(3).
2007, 2007.
[2] Chang C Y, Liao J J. Combination of RFID and face
recognition for access control system [C]// IEEE
International Conference on Consumer Electronics - Taiwan.
IEEE, 2015: 470-471.

[3] Shu L I, University Y. Convolutional Neural Network-

Based Video Face Detection and Recognition [J]. Computer
Knowledge & Technology, 2018.

[4] Derman E, Salah A A. Continuous Real-Time Vehicle

Driver Authentication Using Convolutional Neural Network
Based Face Recognition [C]// IEEE International Conference

© 2021, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 2302