10 I January 2022

https://doi.org/10.22214/ijraset.2022.39702
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue I Jan 2022- Available at www.ijraset.com

Face Recognition Attendance System

Shrey Bhagat1, Vithal Kashkari2, Shubhangi Srivastava3, Ashutosh Sharma4
1, 2, 3
Manav Rachna International Institute Of Research And Studies,Faridabad
4
Assistant Professor, CSE, FET, Manav Rachna International Institute Of Research And Studies,Faridabad

Abstract: Face recognition systems are used in practically every industry in this digital age. One of the most widely utilized
biometrics is face recognition. It can be used for security, authentication, and identity, among other things. Despite its low
accuracy relative to iris and fingerprint identification, it is extensively utilized because it is a contactless and non-invasive
technique. Face recognition systems can also be used to track attendance in schools, colleges, and companies. Because the
existing manual attendance system is time consuming and difficult to maintain, this system intends to create a class attendance
system that employs the concept of face recognition. There’s also the possibility of proxy attendance. As a result, the demand for
this system grows. Database development, face detection, face recognition, and attendance updating are the four steps of this
system. The photos of the kids in class are used to generate the database. Faces are discovered and recognized from the
classroom's live streaming footage. At the end of the session, the attendance will be mailed to the appropriate faculty.
Keywords: Smart Attendance System, NFC, RFID, OpenCV, NumPy

I. INTRODUCTION
This is a project for educational institutions on a facial recognition-based attendance system. The traditional way of marking
commute to work can be a tedious task in many skills and colleges. It is also an additional responsibility for schools to mark an
attendance by naming Individuals which may take up to 5 minutes for a full session. This can be time consuming. There are certain
chances of a representative. Therefore, many institutions began using many other recording methods such as the use of Frequency
Identification (RFID) [3], Iris recognition [4], fingerprint recognition, and more. However, these online based systems can be time
consuming and disruptive in nature. Face recognition has set a very important biometric feature, which is easily accessible and
unobtrusive. Face-based systems that ignore a lot of facial expressions. The face recognition program consists of two stages:
verification and facial recognition. Face verification is a 1: 1 matching process, comparing face-to-face image processing and there
is a 1: N comparing face query image. The purpose of this approach is to create a travel plan based on face recognition strategies.
Here a personal face is considered a mark of presence. Today, facial recognition is gaining popularity and has been widely used. In
the middle of this page, we suggested a face recognition system in the live video class and attendees will be marked when the found
face is found within the website. In comparison to existing procedures, this new technology will take less time.

II. LITERATURE REVIEW

A. Attendance System Using NFC Technology with Embedded Camera on Mobile Device
"NFC (Near Field Communication) Technology with a camera incorporated in a mobile device," according to a study publication
(Bhise, Khichi, Korde, Lokare, 2015). NFC technology and a mobile application are used to improve the attendance system. At the
time of enrolment in the faculty, each student is issued an NFC tag with a unique ID, according to the research article. The travelling
instructor will then take attendance at each lesson by touching or distributing these tags. The integrated camera will then take a
picture of the student's face before sending all of the data to the college server for verification. The benefits of this technology
include the ease of use of NFC and the fast connection speed. It greatly facilitates the process of being in the present moment.
However, if the NFC tag was not tagged by the user, the system would not be able to identify infringement automatically. Aside
from that, the usage of a mobile app was necessary since the NFC student was interrupting the teacher. Would it be a support system
to record everyone present if a pastor failed to bring his mobile phone to work? Furthermore, because of a confidential topic, most
professors would not want their iPhones to be used in this manner. As a result, instead of the NFC marker, unique student
information such as biometrics or face recognition, guanine to the student should be employed. This ensures that a specific student
will be the first to take attendance.

B. Face Recognition Based Attendance Marking System

Face recognition is used in the second research publication, "Face Recognition System Based on Face Recognition"
(SenthamilSelvi, Chitrakala, Antony Jenitha, 2014), to overcome prior system challenges.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 280
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue I Jan 2022- Available at www.ijraset.com

This method involves taking images of the employee using a camera in order to capture their faces and visions. When the result is
located on the face website, the taken image is compared individually with the face mask to display the employee's face, where
presence is noted. The key benefit of this method is that the presence is recorded on a highly secure server that no one else can
access. Furthermore, the face detection algorithm in this suggested system is built employing a skin-splitting approach to improve
the accuracy of the detection process. Despite ongoing efforts to improve the accuracy of the face detection algorithm, the system
remains unaffected at this time. This application needs a stand-alone computer with a constant power source that is not portable.
This sort of system is prepared to mark staff attendance since they only need to submit attendance once a day, unlike students who
must indicate that they are present in each class on a certain day. If marking is present, it will be tough. The system is out of control.
To address this issue, the whole old system management system is converted to a portable module, which is then used to operate a
Python system.

C. RFID based Student Attendance System

According to the fourth research journal “RFID based Student Attendance System” (Hussain, Dugar, Deka, Hannan, 2014), the
proposed solution is almost identical to the first research journal in which RFID technology was used to enhance the adult
attendance program. during this process, the tag and the student are also used as a way to track the presence of students. The
difference between the original journals and that is where the information for the participants will be available through the web site.
Provides very easy to retrieve information. Also, this method is not perfect in the sense that, first of all, it is not portable, because
the RFID reader can only work if it is connected to a PC. Second, the RFID tag is not guanine information that can specifically
identify the reader, thus, leading to inaccuracies in the data collected by attendees.

III. PROPOSED SYSTEM

The function of the proposed system is to capture the face of every student and keep it on the website for them to attend. The face of
the expert must be taken in such a way that everyone can see what the student's face is like, even the seating area and the way the
students stand. There is no need for the teacher to be physically present in the classroom because the system records the video and
then with continuous face processing steps is monitored and therefore the attendance website is updated. All Individuals in the
category must register themselves by entering the information they require so that their photos can be taken and stored within the
database. During each session, a face is found in the live streaming video of the class. The recovered faces are compared with the
existing images in the database. Once a match is found, attendees are marked on the appropriate reader. At the top of each session, a
list of absentees will be sent to the appropriate faculty in charge of the session.
A. Existing Recognition Systems
1) Fingerprint Based Recognition System: For a fingerprint-based departure system, the portable fingerprint device should be pre-
configured with Individual fingerprints ahead of time. Later in the teaching hours or before, the coed should record fingerprints
on the suspended device to ensure their daily presence. The point is that during the study it should be distracting to the eyes of
individuals.
2) RFID (Radio Frequency Identification) Based Recognition System: In an existing RFID-based system, Co-ed should always
carry good identification and place an ID with a cardboard reader to record their daily presence. The system is able to connect
to RS232 and record attendees on a saved website. There is a possibility of fraudulent access that may occur. Some students
may use another student's ID to verify their presence in the absence of the real student or themselves try to misuse it sometimes.
3) Iris Based Recognition System: In an Iris-based student travel program, the scholar should rotate in front of the camera, so that
the camera will scan the Iris code. The scanned iris is compared with the individual data stored on the website and their
presence should be updated. This reduces the paper and pen function of the college members of the institution. This also
reduces the chances of being represented within the classroom, and helps maintain secure code records. it is a wireless
biometric method that solves the issue of false existence and therefore the problem of setting up a compatible network.
4) Face Based Recognition System: Biometric detection technology will be used to record attendees with a high-definition camera
that detects individual faces so the machine compares known faces with student faces stored within the website. When the face
of the code is matched to a saved image, attendees are marked with the current website for further calculation. If the captured
image does not match the existing student face on the website, this image is saved as a new image on the website. During this
process, there is a chance that the camera will not take the correct picture or will miss the number of individuals in the picture.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 281
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue I Jan 2022- Available at www.ijraset.com

IV. RESULTS AND DISCUSSIONS

The main rule of the project is that the video captured by the video is converted into an image for viewing and viewing. In addition,
a known code image is also provided, otherwise the system will mark the site as non-existent.
1) Take a Video: The camera is positioned at a selected distance within the classroom to capture pre-video videos of perfect
students of the class.
2) Divide as Frames in Video: The captured video must be converted to self-contained every second so that it can be easily
accessed and seen by the students' faces in order to present the audience.
3) Face Recognition: Face detection is a process by which an image, provided as input (image) is searched to investigate any face,
after finding the face processing image cleans the face image so that the face can easily be seen.
4) Facial Recognition: After completing the face detection and analysis, it is compared with the existing face on the student
website to review the Individual presence.
5) After Processing: Post-processing process includes the process of updating expert names on an excel sheet. An excel sheet is
usually kept weekly or monthly to record student attendance.
A. Face Recognition and Detection
In every session, as soon as you run the program the camera starts automatically and starts detecting the face in the frame. If the face
detected is registered in the database, the system recognizes the face and shows his/her name on the screen. If the face is not
registered the program will quit automatically.

Fig. 1 Face Detection

Fig.2 Face Detection

Fig.3 Face Detection

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 282
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue I Jan 2022- Available at www.ijraset.com

B. Post Processing
After face recognition and detection, the program creates an entry in the .csv file and exports and name and time in which the face
was detected and marks the attendance. The system does not allow overwriting of a single entry.

Fig.4 Attendance Sheet

V. CONCLUSION
Therefore, the purpose of this project is to capture a video of people, convert it into frames, link it to a database to ensure their
presence or absence, to mark the presence of a real student to keep a record. The Automated Classroom Attendance System helps to
increase accuracy and speed and ultimately achieve the highest accuracy of real-time arrival to satisfy the need for automatic
classroom testing

VI. FUTURE ENHANCEMENTS

The Automated Attendance System is used in larger areas such as the seminar where it helps to feel the presence of more people.
Sometimes poor classroom lighting may affect image quality that indirectly reduces system performance, this may be overcome in
the later phase by improving video quality or using certain algorithms.

REFERENCES
[1] N. Sudhakar Reddy, MVSumanth, S. Suresh Babu, "The Counterpart Approach to Attendance and Feedback System uses Machine Learning Techniques",
Journal of Emerging Technologies and Innovative Research (JETIR), Volume 5, Issue 12, Dec 2018.
[2] Dan Wang, Rong Fu, Zuying Luo, "Classroom Attendance Auto-management Based on Deep Learning", Social Sciences Development, Humanities Education
and Research, volume 123, ICESAME 2017.
[3] Akshara Jadhav, Akshay Jadhav, Tushar Ladhe, Krishna Yeolekar, "Automatic Travel System Using Face Recognition", International Research Journal of
Engineering and Technology (IRJET), Volume 4, Issue 1, Jan 2017.
[4] B Prabhavathi, V Tanuja, V Madhu Viswanatham and M Rajashekhara Babu, "A clever system of presence to see the face in the same way", IOP Conf. Series:
Materials Science and Engineering 263, 2017.
[5] Prajakta Lad, Sonali More, Simran Parkhe, Priyanka Nikam, Dipalee Chaudhari, "Student Travel Program Using Iris Discovery'', IJARIIE-ISSN (O) -2395-
4396, Vol -3 Issue-2 2017.
[6] “Navigation System Using NFC Technology and Camera Embedded on Mobile Device” (Bhise, Khichi, Korde, Lokare, 2015)
[7] K.SenthamilSelvi, P. Chitrakala, A.Antony Jenitha, "Marking Capture Marking System Based on Face Recognition", JCSMC, Vol. 3, Story. 2, February 2014.
[8] “A Train System Based on Fingerprints Using a Small Controller and LabView” (Kumar Yadav, Singh, Pujari, Mishra, 2015)

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 283