Smart Attendance System using Face

Recognition

Suraj Kumar Sharma Sachin Kumar Satyam Kumar

Final Year Student Final Year Student Final Year Student
Computer Science and Engineering Computer Science and Engineering Computer Science and Engineering
Greater Noida Institute of Technology Greater Noida Institute of Technology Greater Noida Institute of Technology
Greater Noida, India Greater Noida, India Greater Noida, India
surajsharmakld@[Link] sachinkumar7920@[Link] satyam.kumar2504@[Link]

Mr. Imran Ansari

Sachin Prajapati Assistant Professor
Final Year Student Computer Science and Engineering
Computer Science and Engineering Greater Noida Institute of Technology
Greater Noida Institute of Technology Greater Noida, India
Greater Noida, India [Link]@[Link]
prajapatisachin470@[Link]

Abstract— The primary aim of this endeavor is to elevate reliability, students often face long queues upon entering the
the attendance management system employed in classroom.
educational institutions through the introduction of an
advanced smart attendance system leveraging facial
recognition technology. The current system is beset by
issues related to accuracy and efficiency. By
incorporating facial recognition capabilities, the new
system will establish databases of facial profiles, compare
them during attendance sessions, and seamlessly update
an Excel sheet with attendance records. To ensure a
meticulous tracking process, the compiled daily
attendance data will be transmitted via email to the
respective faculty members. The utilization of facial
recognition technology in attendance management
represents a method of identifying students based on
facial biometrics, drawing upon sophisticated monitoring
and computer technologies.

Keywords — Face Detection, Face Recognition, LBPH

Algorithm, Biometrics, RFID

I. INTRODUCTION

Pupil attendance in most educational institutions is

traditionally recorded manually using attendance sheets
issued by department heads as mandated by regulations. In
these sheets, students sign up for upcoming sessions, which
are then manually transcribed onto a computer. However, this
method proves to be slow, time-consuming, and inconsistent,
as some students often sign in for absent peers. Moreover,
tracking individual attendance in large classroom settings
becomes challenging.
In our study, we propose the implementation of a facial
detection and recognition system to automatically identify
students present in the classroom during lectures and mark
their attendance by recognizing their faces. While other
forms of biometric authentication may offer greater
1
Due to its non-intrusive nature and widespread familiarity,
facial recognition is chosen as the preferred method since
people naturally recognize others primarily based on their
facial features.

One of the major drawbacks of the previous attendance

system is the sensitivity of the collected data. This is
primarily because attendance might be recorded by
individuals other than the original person, meaning that
attendance for a specific individual could be marked by a
third party without the institution's validation, thus
compromising the sensitivity of the data.

Another issue arises with the accessibility of this

information by relevant stakeholders. For instance, many
parents are deeply concerned about tracking their child's
actual whereabouts to ensure their attendance in classes.
However, in the previous system, there was no provision
for parents to access such information. Hence,
enhancements are required in the existing system to
improve effectiveness, and data sensitivity, and provide
access to information for the relevant parties [1].

The current attendance systems often lack effectiveness and

fail in information sharing. In our proposed design, these
limitations will be addressed and further improved upon in
the following ways:

Students will be more prompt in attending classes.

Enhanced data sensitivity and privacy measures will be
implemented. Accessibility to attendance information will
be facilitated for relevant stakeholders [2], such as parents
and academic staff. This is due to the attendance of pupil
can only be taken tête- à-tête where any absentees will be
noticed byte system. This can't only train the pupil to be
immediate as well as avoids any immoral ethics similar as
subscribing the attendance for their musketeers. The
institution can save a lot of coffers as

2
enforcement is now done by means of technology rather than created
mortal supervision which will waste a lot of mortal resources
for an insignificant process.

1.1 Limitation of other Attendance System

Varieties of attendance Restrictions

system

RFID based Attendance False utilization

System

It takes a lot of time for

Fingerprint-based system pupils to wait and submit
their attendance.

Iris-based system Disturbs the user's privacy

Wireless-based system Terrible performance in the

event of poor topography

1.2 Varieties of Attendance System

i. RFID

Before each lecture in the institute, students' attendance is

recorded using an RFID-based attendance system. To
indicate their presence on the RFID reader, the pupils must
utilize an RFID tag. The attendance system efficiently and
accurately stores the data. Faculty members can use it for
additional operations.

ii. Fingerprint-based system

Fingerprint biometrics can be used as an identity verification

technique to make sure someone is who they claim to be, or
they can be used to authenticate a person based on data
within a system matching. In addition to password and token
security methods, fingerprint biometrics can provide an
additional degree of protection.

iii. Iris-based system

Using mathematical pattern-recognition techniques on video

footage of one or both of an individual's irises—whose
complex patterns are distinct, stable, and visible from a
distance—iris recognition is an automated biometric
identification approach.

iv. Wireless-based system

This work efficiently automates the traditional attendance

system. Spend time gathering attendance in the classroom. Under
this approach, a student can connect his or her mobile phone
using an Android application to a Wi-Fi hotspot that is
3
by the individual teacher throughout each period.

1.3 Approaches Used in Attendance System

Introducing a smart attendance system in educational

institutions necessitates the adoption of diverse strategies
aimed at refining accuracy and efficiency. Among these
approaches, facial recognition technology stands out as a
prominent choice. This involves establishing a repository of
enrolled students' facial images and employing real-time
detection and recognition during attendance sessions.

Another viable method involves the utilization of RFID

(Radio Frequency Identification) technology. Here,
students are furnished with RFID cards or tags, which
facilitate automatic attendance logging upon entry through
designated points.

Voice recognition, biometric thumb impression scanners,

QR code scanning, Wi-Fi tracking, and automated
classroom sensors present additional avenues for
consideration [11]. Each of these methods offers distinct
advantages in terms of cost, infrastructure requirements,
and the desired level of accuracy.

In many cases, a combination of these approaches proves to

be the most effective solution for implementing a
comprehensive and efficient smart attendance system. By
leveraging a mix of technologies, educational institutions
can tailor the system to suit their specific needs and
maximize attendance tracking capabilities.

i. Holistic Approach

Employing the entire facial image as the input for the face
recognition process, as illustrated in Figure 1, is commonly
referred to as the Holistic Approach. However, it's
important to note that utilizing this holistic approach does
not address the illumination invariance problem. This is
because the method considers the entire face present in the
image as the input, without specifically accounting for
variations in illumination conditions.

Fig 1. Holistic Approach

ii. Feature-Based Approach

The Feature-Based Approach, as its name implies, involves

considering individual facial features for the calculation
and evaluation operations inherent in the face recognition
process. Unlike the holistic approach, which utilizes the
entire face image, the feature-based approach addresses
issues such as illumination and pose variance by focusing
on specific facial

4
features. III. PROPOSED METHODOLOGY
When developing attendance systems that utilize face
recognition technology, the feature-based approach is Facial recognition serves as a pivotal tool for personal
commonly employed. This method emphasizes the extraction identification, leveraging a multitude of unique features
and analysis of attributes to achieve precise identification of inherent in an individual's face. Each person possesses
individuals. Key elements such as eyes, nose, mouth, and distinctive characteristics, including the eyes, nose, mouth,
unique facial landmarks are identified and captured for and ears, which contribute to enhancing accuracy and
analysis in this approach. By focusing on these distinctive minimizing errors during the authentication process. In face
features, the feature-based approach enhances accuracy and recognition, these facial features are quantitatively
robustness in face recognition systems, particularly in computed, and the disparities between different faces are
varying lighting conditions and facial orientations. meticulously measured. These measurements serve as the
foundation for identification methodologies. The system
II. LITERATURE REVIEW archives user requests alongside corresponding responses,
facilitating seamless query processing.
The Smart Attendance Monitoring System: A Face
Recognition Grounded Attendance System for Classroom The integration of facial recognition into automation dates
Environment proposed an attendance solution that addresses back to the 1960s, marking a significant milestone in
the limitations of traditional systems by utilizing facial technological advancement. Key facial attributes such as
recognition technology [2]. This system effectively captures nose, eyes, mouth, and ears are meticulously analyzed, with
attendance while considering factors like facial expressions, calculations made to determine distances and ratios among
lighting conditions, and potential disguises. By automating these features. Subsequently, these measurements are
the attendance process, it reduces manual efforts compared with existing data sets for identification purposes.
significantly. In the 1970s, Goldstein, Harmon, and Lesk pioneered the
Similarly, the Attendance System Using Face Recognition development of a comprehensive set of 21 facial
and Class Monitoring System focuses on uploading characteristics, encompassing attributes such as lip thickness
attendance data based on facial recognition. This automated and hair color. However, given that all measurements were
approach reduces manual work and enhances efficiency. The conducted manually, the veracity of the actual measurements
Automatic Attendance System Using Face Recognition for remained challenging to ascertain.
speakers or staffs employs algorithms like Viola-Jones and
PCA for facial recognition. By capturing images at the 3.1 Face Detection Process
beginning and end of classes, it ensures accurate attendance
tracking [3]. Classroom Attendance System Using Facial In face detection, one of the primary tasks is to isolate the
Recognition System introduces a 3D facial model to identify facial region from the rest of the image. This process
students within a classroom environment. This logical typically involves two main steps:
approach aids in automating attendance recording and
evaluating student performance [4].

However, challenges such as fraudulent access arise with

RFID-based attendance systems. To address this, an auto-
enrolment model combining facial recognition and RFID is
proposed, ensuring accurate attendance records and
enhancing security. Additionally, studies have explored facial
recognition technology's role in student engagement,
suggesting methods like feature extraction and facial
expression analysis [5]. Improvements in image quality and
system resources can enhance the effectiveness of these
approaches. Overall, facial recognition-based attendance Fig 2: Face Detection
systems offer promising solutions for automating attendance
monitoring in educational environments, with ongoing i. The first step involves referencing measurements
research focusing on improving accuracy, efficiency, and obtained from pre-existing data. These measurements
security measures. serve as a reference point for subsequent analysis.
An attendance management system with wireless iris
recognition and its design and implementation [6] An iris ii. The second step entails identifying a specific individual
biometric method that can be used to this system is called iris by extracting facial features and calculating the distances
recognition. Iris Recognition is a wireless system that is between them. This involves isolating the subject's facial
designed and implemented. Daugman's algorithm is the features and quantifying the spatial relationships between
foundation of the Iris recognition system. The picture them. Subsequently, these distances are compared with
capture, image extraction, feature storage, and feature those stored in the database.
matching between the captured image and the image stored in
the database are all used in this iris recognition system. If the measured distances fall within an acceptable range,
Sadly, iris recognition topography is not very good. indicating a match with the stored data, the individual is
identified accordingly. However, if the distances exceed a
predefined threshold, suggesting discrepancies with the
5
stored data, the individual is considered distinct from
those in

6
the database. collection.

 Face Detection and Extraction: Face detection plays

Dataset Face Face Detection Framed a pivotal role as the captured images is fed into the
Image Face system. Various image processing algorithms are
activated to identify and extract facial regions
Background subtraction within the image, discerning the visible face.

 Face Alignment: Human faces possess 68 unique

Processed Pre-processing Extracted landmarks, which serve as reference points for
Face Face accurate positioning. This step involves identifying
these facial landmarks to precisely align and
Form Dataset position the face within the image. Python scripts
are utilized to measure facial features and ensure
optimal alignment without distorting the image.
Training
Dataset
Query Dataset Dataset Pre- Pre-
Perform Training Creation Processing Processing-
With Face 128d
Query Image CSV Detection Embedding
Trained Classifier

Training-
ML-SVM
Recognition

Result
Load Pre-Process
Classification
Model, LE frame from
Fig 3. Block Diagram of Smart Attendance System & CSV Camera

3.2 Face Recognition Process

Fig 4. Workflow of Attendance System
The face recognition process is a crucial technique employed
for identity verification, particularly in scenarios like
classroom attendance tracking. This process typically 3.3 Face Recognition Algorithm
involves four distinct stages:
i. Local Binary Patterns Histograms
i. Data Acquisition:
 A potent face recognition algorithm called LBPH
 Image Acquisition: Utilizing a high-definition is capable of recognizing faces from both the front
camera within the classroom, images of students are and side views. An intensity value between 0 and
captured. These images serve as input for the face 255 represents the color information of each pixel
recognition system. in an image represented as a matrix.
 LBPH functions by segmenting the facial image
 Dataset Creation: Before initiating the verification into many blocks. Every block will own its
individual histogram, and the matrix's pixels are
process, a student profile is generated. This dataset
contrasted with the central pixel. In the end, we will
showcases the system's functionality and accuracy.
have a binary number that will be converted to
Initially, profiles for five students are created, decimal representation.
including their names, student numbers,  In order for you to understand the Fig 5, let's break
departments, and multiple photos. To enhance down the procedure into several parts. Presume we
accuracy, a minimum of 15 images per student have an image that is grayscale.
should ideally be captured. Upon saving a student's
profile and image into the system to build a a. We split the image into three-by-three
database, deep learning techniques are employed to pixels to extract a section of it.
calculate a 128-dimensional face embedding, which b. A 3x3 matrix with an intensity value
is then stored within the student's facial profile for ranging from 0 to 255 for each pixel
subsequent retrieval during face recognition. This would be an alternate way to depict
process is applied to all images captured during data it.
c. The center value will be used to determine
7
a threshold value.

8
 d. By taking this threshold value into account,
we can set a new binary value for each 100
neighbor. If the neighbor’s value is equal to
or higher than the cut-off points If the 75

Accuracy (%)
binary value is not set to 0, it will be set to
1.
50
e. The new matrix will now be binary in
nature, save from the threshold value. 25
Moving forward, we shall address each
binary value in accordance with its line-by-
line location within the matrix. For 0
example, 10001101 is the binary number in Category 1 Category 2 Category 3 Category 4
the accompanying image. It's not necessary No. of training data
to follow every line. The result will be the
same regardless of whether the author Face Recognized Face Detected
chooses to proceed in a clockwise or
counterclockwise manner.
Fig 6: Accuracy Result of Facial Recognition
f. This binary value will now be converted to
a decimal (141 is the decimal equivalent of For pupil enrolment, students are prompted to input all
10001101). We then convert this decimal necessary details into the enrolment form. Upon clicking the
number to the central value, or pixel, of the register button, the webcam is automatically activated. A
image. window, as depicted in Fig. 3, appears and begins detecting
faces within the frame. Simultaneously, the system initiates
g. We will obtain a fresh image at the end of image capture until either 60 samples are collected or CTRL
this process that will better describe its Q is pressed. These captured images undergo preprocessing
qualities. and are subsequently stored in a designated training images
directory for further processing.

In the case of faculty enrolment, instructors are required to

register with their respective course details, including their
dispatch ID, through a separate enrolment form. This step is
crucial as it ensures that the list of absentees can be
accurately communicated to the appropriate faculty
members. This segregation of enrolment data facilitates
efficient communication and attendance management within
the system.
1 0 0 200 50 50 The interface of the attendance system is designed to provide
an optimal user experience, catering to various stakeholders
0 1 50 90 100 such as teachers, students, and administrators. Upon logging
in through the authentication process, users are greeted with
1 0 1 160 70 210 a user-friendly dashboard offering a comprehensive
overview of attendance-related information.

150 90 80
30 141

Fig 5: Image Representation in Matrix format using LBPH

IV. RESULT AND DISCUSSION

The system interface allows users, whether students or Fig 7. Student Details of the Smart Attendance System
faculty, to interact via a Graphical User Interface (GUI),
providing them with three main options: pupil enrolment, For teachers, the dashboard may include features such as:
faculty enrolment, and marking attendance. Attendance summary for each class or course taught options
to mark attendance, view attendance history or generate
attendance reports Notifications for any anomalies or trends
in attendance patterns for students, the dashboard may

9
display:

10
 Fig 10: GUI of the System
Fig 8: Chatbot of Smart Attendance System
 Key features of the GUI include:
Personal attendance records for different classes or courses
Alerts for upcoming classes or events. Access to request Secure login functionality to ensure authorized access. A
leave or report any attendance-related issues dynamic dashboard presenting attendance metrics and
Administrators may have access to additional features on the upcoming events at a glance. Intuitive class selection options
dashboard, such as: Overview of attendance statistics across for easy navigation. Effortless attendance marking
the institution Tools for managing user accounts, capabilities, whether manual or automatic. Integrated
permissions, and system settings Integration with other calendars for convenient tracking of class schedules and
administrative systems for seamless data exchange Overall, important dates.
the attendance system interface aims to streamline Overall, the GUI of the smart attendance system is designed
attendance management processes, provide to streamline attendance management processes,
valuable insights, and empower users with the tools they need empowering teachers to efficiently monitor attendance and
to effectively monitor and track attendance. focus on delivering quality education.

Fig 11. Login Page of the Smart Attendance System

V. CONCLUSION

The primary goal of this system is to establish an efficient

Fig 9. Student Information class attendance system utilizing facial recognition
technology. This proposed system enables attendance
The GUI of the smart attendance system is meticulously marking via face ID, detecting faces through a webcam and
crafted to facilitate intuitive and efficient attendance accurately recognizing them. Upon recognition, it
management. Upon logging in through a secure automatically marks the attendance of the identified students
authentication process, users are greeted with a dynamic and updates the attendance records. The implementation of
dashboard that offers a comprehensive overview of this system aims to save time and resources by reducing
attendance metrics and upcoming events. manual efforts.

Teachers find it effortless to navigate through the interface, This system showcases a deep understanding of the
with the ability to seamlessly select classes, mark attendance underlying algorithms and adopts a rigorous approach to
manually or automatically, and conveniently track dates accurately recognizing individuals. It demonstrates the
using integrated calendars. The interface prioritizes user- capability to handle variations in facial poses and
friendliness, allowing teachers to efficiently manage environmental changes within the room effectively.
attendance tasks without unnecessary complexity.
Facial recognition technology, driven by machine learning
algorithms, addresses challenges such as variations in lighting

11
conditions by transforming the original image into a 10. Surekha, B., Nazare, K.J., Viswanadha Raju, S.
standardized representation that captures crucial facial and Dey, N., 2017. Attendance recording system
features independent of image quality. Original facial using partial face recognition algorithm.
landmarks are considered for further processing in the face Intelligent
recognition system.

The integration of facial recognition technology serves to

address the limitations of traditional attendance systems,
providing a more streamlined and efficient solution.
However, there is room for improvement to enhance the
system's performance, particularly in scenarios where
students may be at a distance or under challenging
conditions. Continuous refinement and optimization of the
system will contribute to its overall effectiveness and
reliability in the future.

VI. REFERENCES

1. Raj, A.A., Shoheb, M., Arvind, K. and Chethan,

K.S., 2020, June. Face recognition based smart
attendance system. In 2020 International conference
on intelligent engineering and management (ICIEM)
(pp. 354-357). IEEE.
2. Sawhney, S., Kacker, K., Jain, S., Singh, S.N. and
Garg, R., 2019, January. Real-time smart attendance
system using face recognition techniques. In 2019
9th international conference on cloud computing,
data science & engineering (Confluence) (pp. 522-
525). IEEE.
3. Bhatti, K., Mughal, L., Khuhawar, F. and Memon,
S., 2018. Smart attendance management system
using face recognition. EAI Endorsed Transactions
on Creative Technologies, 5(17).
4. Dang, T.V., 2023. Smart attendance system based
on improved facial recognition. Journal of Robotics
and Control (JRC), 4(1), pp.46-53.
5. Al-Muhaidhri, G. and Hussain, J., 2019. Smart
attendance system using face recognition.
International Journal of Engineering Research and,
8.
6. Bhattacharya, S., Nainala, G.S., Das, P. and
Routray, A., 2018, July. Smart attendance
monitoring system (SAMS): a face recognition
based attendance system for classroom environment.
In 2018 IEEE 18th international conference on
advanced learning technologies (ICALT) (pp. 358-
360). IEEE.
7. Kumar, N.A., Swarnalatha, P., Chowdary, P., Naidu,
J.K. and Kumar, K.S., 2019. Smart attendance
marking system using facial recognition. Research
Journal of Science and Technology, 11(2), pp.101-
108.
8. Jadhav, A., Jadhav, A., Ladhe, T. and Yeolekar, K.,
2017. Automated attendance system using face
recognition. International Research Journal of
Engineering and Technology (IRJET), 4(1),
pp.1467- 1471.
9. Yang, H. and Han, X., 2020. Face recognition
attendance system based on real-time video
processing. IEEE Access, 8, pp.159143-159150.
12
 techniques in signal processing for multimedia
security, pp.293-319.
11. Pawaskar, S.S. and Chavan, A.M., 2020, December.
Face recognition based class management and
attendance system. In 2020 IEEE Bombay Section
Signature Conference (IBSSC) (pp. 180-185). IEEE.
12. Ghosh, S., Mohammed, S.K., Mogal, N., Nayak,
P.K. and Champaty, B., 2018, January. Smart
attendance system. In 2018 international conference on
smart city and emerging technology (ICSCET) (pp. 1-
5). IEEE.
13. Fung-Lung, L., Nycander-Barúa, M. and Shiguihara-
Juárez, P., 2019, August. An image acquisition method
for face recognition and implementation of an
automatic attendance system for events. In 2019 IEEE
XXVI International Conference on Electronics,
Electrical Engineering and Computing (INTERCON)
(pp. 1-4). IEEE.
14. Vishe, A., Shirsath, A., Gujar, S. and Thakur, N.,
Student attendance system using face recognition.
Engpaper Journal.
15. Lin, Z.H. and Li, Y.Z., 2019, January. Design and
implementation of classroom attendance system based
on video face recognition. In 2019 international
conference on intelligent transportation, big data &
smart city (ICITBS) (pp. 385-388). IEEE.
16. Fakhir, T.M. and Hasan, R., 2020. Designing Smart
Attendance System Using Face Recognition and IoT
Networking Concept.
17. Lateef, A.S. and Kamil, M.Y., 2023. Facial
Recognition Technology-Based Attendance
Management System Application in Smart Classroom.
Iraqi Journal For Computer Science and Mathematics,
4(3), pp.136-158.
18. Vamsikrishna, J., Anudeep, K., Marcilin, L.J.A. and
Balamurugan, V., 2019, October. An Advanced
Attendance Marking system using facial Recognition.
In IOP Conference Series: Materials Science and
Engineering (Vol. 590, No. 1, p. 012049). IOP
Publishing.
19. Anshari, A., Hirtranusi, S.A., Sensuse, D.I. and
Suryono, R.R., 2021, July. Face recognition for
identification and verification in attendance system: A
systematic review. In 2021 IEEE International
Conference on Communication, Networks and Satellite
(COMNETSAT) (pp. 316-323). IEEE.
20. Malik, R., Kumar, P., Verma, A. and Rawat, S., 2016,
October. Prototype model for an intelligent attendance
system based on facial identification. In 2016
International Conference on Information Technology
(InCITe)-The Next Generation IT Summit on the
Theme-Internet of Things: Connect your Worlds (pp.
40-43). IEEE.
21. Roy, S., Chatterjee, S., Jana, S., Dasgupta, R., Ghosh,
S. and Mandal, S., 2023. Modern Attendance System-A
New Way For Taking Attendance by Face
Recognition. American Journal of Electronics &
Communication, 3(4), pp.18-19.

13
22. Tantarpale, P., Puri, R., Pawar, R. and Sonawale, B.,
2022. Real-time Attendance using Machine
Learning and Face Detection Technique.
International Journal of Wireless Network Security,
8(1), pp.24-30.
23. Rajawat, S.S. and Saxena, K., 2022, October. Face
Recognition based Attendance System. In 2022 1st
IEEE International Conference on Industrial
Electronics: Developments & Applications
(ICIDeA) (pp. 95-99). IEEE.
24. Bhambure, K., Kadam, A., Dabhade, K., Deore, B.
and Gaikwad, P., 2023, August. An Integrated Face
Recognition based Attendance Monitoring System.
In 2023 7th International Conference On
Computing, Communication, Control And
Automation (ICCUBEA) (pp. 1-6). IEEE.
25. Bhosale, S., Patil, A., Ovhal, V., Sonawane, M. and
Gulhane, S., 2022. Facial Recognition Based Smart
Attendance System. International Research Journal
of Innovations in Engineering and Technology, 6(4),
p.100.
26. Agarwal, H., Verma, G. and Gupta, L., 2021.
Student attendance system based on the face
recognition. Asian Journal For Convergence In
Technology (AJCT) ISSN-2350-1146, 7(2), pp.70-
73.
27. Krishnan, P.S. and Manikuttan, A., 2022, June.
Attendance Management System Using Facial
Recognition. In 2022 International Conference on
Computing, Communication, Security and
Intelligent Systems (IC3SIS) (pp. 1-6). IEEE.
28. Rajput, I., Nazir, N., Kaur, N., Srivastava, S.,
Sarwar, A., Kaur, B., Dahiya, O. and Aggarwal, S.,
2022, April. Attendance Management System using
Facial Recognition. In 2022 3rd International
Conference on Intelligent Engineering and
Management (ICIEM) (pp. 797-801). IEEE.
29. Chavda, H.N., Bhavsar, S.P., Undavia, J.N., Solanki,
K. and Shukla, A., 2023, December. Attendance
System Using Face Detection and Face Recognition.
In International Conference on Information and
Communication Technology for Competitive
Strategies (pp. 351-361). Singapore: Springer
Nature Singapore.
30. Chaudhary, D., Rawat, A., Maurya, D., Patel, A. and
Shukla, D.S., 2020. Face Recognition Based
Attendance System. International Journal of
Engineering Applied Sciences and Technology, 5(1),
pp.485-487.
31. Gidd, A.A., Patil, A.R., Molaj, S.A., Bhosekar, S.D.
and Bavachkar, S.G., 2020. Modern Way of
Attendance System. Methods, 70, pp.92-100.
32. Gawande, U., Joshi, P., Ghatwai, S., Nemade, S.,
Balkothe, S. and Shrikhande, N., 2022. Efficient
Attendance Management System Based on Face
Recognition. In ICT Systems and Sustainability:
Proceedings of ICT4SD 2021, Volume 1 (pp. 113-
121). Springer Singapore.

14