See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/377223850

Facial Recognition based Attendance System: A Survey

Article · December 2023

CITATIONS READS

0 185

5 authors, including:

Pramila M. Chawan Maitray Wani

Veermata Jijabai Technological Institute Veermata Jijabai Technological Institute
184 PUBLICATIONS 746 CITATIONS 1 PUBLICATION 0 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Pramila M. Chawan on 08 January 2024.

The user has requested enhancement of the downloaded file.

 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 11 | Nov 2023 www.irjet.net p-ISSN: 2395-0072

Facial Recognition based Attendance System: A Survey

Mihir Ghanekar1, Archita Sehgal2, Shrishail Gouragond3, Maitray Wani4, Prof. Pramila M.
Chawan5

1,2,3,4B.Tech Student, Dept of Computer Engineering and IT, VJTI College, Mumbai, Maharashtra, India
5Associate Professor, Dept of Computer Engineering and IT, VJTI College, Mumbai, Maharashtra, India
-------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Efficient attendance monitoring is hindered by in the attendance management process. When individuals
time-consuming manual methods vulnerable to inaccuracies interact with a face recognition-enabled system, their facial
and fraud. The Attendance System with Face Recognition data is captured and compared to a database of stored
offers a pioneering solution, diverging from traditional facial templates, allowing for quick and precise
approaches. Utilizing advanced facial recognition identification. This technology not only eliminates the need
technology, it ensures precise identification and verification, for manual data entry but also mitigates the risks
minimizing errors. With a user-friendly interface, it enhances associated with proxy attendance, a common issue in
accessibility for administrators and end-users. Real-time traditional methods.
tracking empowers swift issue resolution, improving
operational efficiency and data integrity. Representing a Additionally, real-time monitoring and instant data
paradigm shift in attendance management, this system updates empower administrators to make prompt
provides a secure, accurate, and efficient alternative to decisions and interventions when needed, further
conventional methods in educational institutions, corporate enhancing operational efficiency. The integration of face
offices, and organizations. recognition technology in attendance systems not only
offers a streamlined and secure approach to tracking
Key Words: Facial Recognition Technology, Real-time attendance but also represents a forward-thinking solution
Tracking, OpenCV, InsightFace, Cosine Similarity, Machine that aligns with the demands of modern organizations and
Learning educational institutions.

1.INTRODUCTION 1.2 Purpose

The Attendance System with Face Recognition represents a An Attendance System with Face Recognition built using
technological leap forward in the realm of attendance OpenCV, Machine Learning, and Python, embodies the
tracking and management. Harnessing the power of convergence of advanced technologies to provide a
cutting-edge facial recognition technology, this system cuttingedge solution for attendance tracking. OpenCV, a
offers a seamless and highly efficient solution for powerful computer vision library, forms the backbone of
accurately monitoring attendance in various settings, this system, enabling it to capture, analyse, and recognize
including educational institutions, corporate offices, and faces in realtime. Through the utilization of Machine
organizations. Traditional attendance methods, often Learning algorithms, the system learns to identify and
plagued by errors and inefficiencies, are eclipsed by this differentiate individuals based on their facial features.
innovative system's ability to identify and verify individuals Python serves as the programming language that
through their unique facial features. With real-time orchestrates these technologies, facilitating seamless
monitoring, robust security measures, and the flexibility to integration and customization.
integrate with existing databases, the Attendance System
with Face Recognition not only simplifies the attendance 2. LITERATURE REVIEW
tracking process but also ensures precision, security, and
compliance with data protection regulations. It is a 2.1 Facial Recognition
transformative tool that has the potential to streamline
operations and elevate the quality of attendance Facial recognition attendance systems have emerged as a
management in today's fastpaced and data-driven world. game changer in the field of employee monitoring and
attendance management. Leveraging the power of machine
1.1 Need for Facial Recognition in Attendance System learning and Python, these systems offer a seamless and
efficient approach to tracking employee presence.
The use of facial recognition technology into attendance
systems has transformed the way businesses and The implementation of facial recognition attendance
institutions measure attendance. By leveraging the unique systems typically involves three key stages: face detection,
and unalterable facial features of individuals, this feature extraction, and recognition. Face detection
technology ensures a high degree of accuracy and security algorithms identify and locate faces within images or video

© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 719
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 11 | Nov 2023 www.irjet.net p-ISSN: 2395-0072

streams. Feature extraction techniques then extract unique Cosine Similarity enhances the system's ability to identify
facial features, such as the shape of the nose, eyes, and lips. individuals accurately, particularly in scenarios where
Finally, recognition algorithms compare the extracted
facial appearance may vary due to different lighting or
features against a database of known faces to identify the
angles.
individual.
2.2.6 Distance Method
2.2 Machine Learning Search Algorithms
Distance Method refers to the use of specific distance
Machine learning powers facial recognition attendance
metrics, such as Euclidean, Manhattan, or Chebyshev
systems, enabling accurate and efficient identification
distances, to measure the likeness between a captured
through facial feature recognition. Trained on vast datasets,
facial template and those stored in the system's database.
these systems adapt to changes in appearance, ensuring
These metrics calculate the difference between
consistent performance.
corresponding facial features, offering a quantifiable
2.2.1 Manhattan Distance measure of similarity. By employing the Distance Method,
the system efficiently matches and verifies individuals,
In Facial Recognition Attendance Systems, Manhattan contributing to precise attendance tracking.
Distance, a crucial metric, measures the likeness between
captured and stored facial templates. It quantifies 2.2.7 Similarity Method
differences by summing absolute feature disparities, aiding
This method relies on machine learning to compare
swift and accurate identification. This enhances security
the facial templates of individuals in real-time with those
and ensures reliable attendance tracking.
stored in the database. It measures the similarity between
2.2.2 Euclidean Distance the captured facial features and the stored templates,
allowing for quick and accurate identification. The
Euclidean Distance is a critical tool employed by machine algorithm enhances the system's efficiency, enabling it to
learning algorithms to determine the similarity between a recognize individuals promptly, while minimizing false
captured facial template and those stored in the database. positives and negatives. As a result, the Similarity Method
It calculates the straight-line distance between two sets of is an essential part of ensuring that attendance records are
facial features in a multidimensional space, providing a both secure and precise.
measure of their likeness. Euclidean Distance enhances the
system's ability to identify individuals accurately and Search Key Difference Accuracy
quickly. By using this metric, the system can effectively Algorithm rate
match the facial data, ensuring precise attendance tracking
and bolstering security in the process. Manhattan Sum of absolute 85%
Distance differences between
2.2.3 Chebyshev Distance corresponding
coordinates.
Chebyshev Distance plays a crucial role as a distance Chebyshev Maximum absolute 80%
metric used by machine learning algorithms to assess the Distance difference between
similarity between a captured facial template and those corresponding
stored in the system's database. It calculates the maximum coordinates
absolute difference between corresponding features in the
Minkowski Generalization of both 82%
two sets, providing a robust measure of likeness. Manhattan and
Distance
Chebyshev Distance aids in quick and accurate individual Chebyshev distances.
identification, contributing to the system's precision and
efficiency. Distance Measures dissimilarity 78%
Method between feature vectors.
2.2.4 Minkowski Distance
Similarity Measures similarity 79%
Minkowski Distances are an adaptable collection of Method between feature vectors.
distance metrics that include Manhattan, Euclidean, and
Chebyshev distances, providing for greater versatility in Cosine Cosine Similarity 92%
assessing resemblance. This adaptability enables the Similarity calculates the angle's
cosine between two non-
system to fine-tune the matching process to suit specific zero vectors. Often used
identification needs, ensuring both precision and efficiency. for high-dimensional
data like facial features.
2.2.5 Cosine Similarity Closer to 1 means more
similarity.
Cosine Similarity computes the cosine of the angle
between these templates to determine their similarity. Table -1: Comparison of different Search algorithms.

© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 720
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 11 | Nov 2023 www.irjet.net p-ISSN: 2395-0072

Cosine Similarity stands out as the preferred choice in the classroom in addition to calling names. It may be tough
facial recognition due to its ability to measure likeness to circulate the attendance sheet around the lecture class,
between facial templates, considering variations in lighting especially if there are a high number of students. Thus, a
and angles. Unlike distance metrics such as Manhattan, face recognition attendance system is proposed to replace
Euclidean, and Chebyshev, Cosine Similarity focuses on the the tedious manual signing of students' presence, which
angle between vectors, making it robust to differences in causes students to get distracted to sign for their
facial appearance. The Similarity Method, utilizing Cosine attendance.
Similarity, excels in accurately identifying individuals,
minimizing false positives and negatives. Its adaptability to Furthermore, the automatic student attendance system
various facial features contributes to a higher accuracy rate based on facial recognition can overcome the problem of
compared to other distance methods like Minkowski. fraudulent approaches, and lecturers are not required to
count the number of students numerous times to confirm
In facial recognition scenarios where precise the students' presence.
measurements of similarity are crucial, Cosine Similarity
emerges as the optimal choice, ensuring a more reliable 3.3 PROPOSED METHODOLOGY
and efficient attendance tracking process with enhanced
security and data integrity. We propose a clustering method of recommendation
systems. Clustering methods are an important tool in
machine learning and data analysis, and can be particularly
useful for mutual fund rec The proposed methodology for
developing a comprehensive Attendance System with Face
Recognition, integrating Redis database, OpenCV, machine
learning, and search algorithms in Python, involves a step-
by-step approach:

a) Data Collection and Annotation: Collect and

annotate a diverse facial image dataset for system
users.

b) Data Preprocessing: Apply normalization, resizing,

and noise reduction techniques for consistent and
Fig -1: Cosine Similarity in Face recognition. quality images.

c) Feature Extraction and Template Creation: Use

3. PROPOSED SYSTEM
OpenCV and machine learning to extract unique
3.1 PROBLEM STATEMENT facial features and create templates.

d) Machine Learning Model Development: Train a

Develop an efficient and secure Attendance System with
model for accurate facial feature recognition,
Face Recognition to overcome the shortcomings of
optimizing for various conditions.
traditional attendance tracking in educational institutions
and organizations. The challenge involves leveraging e) Redis Database Integration: Integrate Redis for
cutting-edge technologies like facial recognition, machine secure storage and retrieval of facial templates and
learning, and database management to ensure real-time attendance records.
monitoring, prevent proxy attendance, and enhance data
integrity. The goal is to create a user-friendly solution that f) Search Algorithms and Matching: Implement
not only improves attendance accuracy but also prioritizes optimized search algorithms like Euclidean,
privacy, seamless database integration, and insightful data Manhattan, Chebyshev distances, or cosine
analysis, addressing the evolving needs of the modern similarity.
digital era.
g) Real-Time Monitoring and Alerting: Enable real-
3.2 PROBLEM ELABORATION time attendance monitoring and implement
alerting for immediate administrator action.
The traditional student attendance marking system
frequently faces difficulties. By eliminating traditional h) Customization and Integration: Design a highly
student attendance marking techniques such as calling customizable system for tailored attendance
student names or verifying relevant identity cards, the policies and seamless integration.
facial recognition student attendance system highlights its
simplicity. They not only disrupt the instructional process, i) User Interface and Reporting: Develop a user
but they also distract pupils during test sessions. During friendly Python interface and robust reporting
the lecture sessions, an attendance sheet is handed around features for valuable insights.

© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 721
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 11 | Nov 2023 www.irjet.net p-ISSN: 2395-0072

j) Security and Data Protection: Address security and The second phase deals with creation of the two different
privacy concerns through encryption, compliance, Streamlit Web Apps followed by compiling of the report
and regular audits. and dashboard.

k) Real-World Testing and Validation: Conduct 5. CONCLUSION

comprehensive testing in real-world educational
and corporate environments. The proposed Attendance System with Face
Recognition, incorporating Redis database, OpenCV,
l) Maintenance and Optimization: Develop a strategy machine learning, and search algorithms in Python,
for continuous maintenance, updates, and presents a transformative solution with numerous
optimization for long-term reliability. advantages across diverse domains. Notable benefits
include enhanced accuracy through facial recognition,
3.4 SYSTEM ARCHITECTURE automation for increased efficiency, heightened security
against unauthorized access, and robust data integrity
provided by the Redis database. The system's
customization, user-friendly interface, and reporting
features make it adaptable to the unique needs of
educational institutions, corporate offices, and various
businesses. Its scalability and potential for cost savings
underscore its practicality for both small and large entities.
The system's versatile use cases span educational
institutions, corporate offices, healthcare facilities,
government institutions, retail outlets, transportation,
hospitality, and beyond.

REFERENCES
[1] P. Hegde, "face recognition based attendance
management system", International Journal of
Engineering Research

[2] Face Recognition Based Attendance System. (2020,

June). Dhanush Gowda H.L , K Vishal , Keertiraj B. R ,
Neha

[3] Hasan, R. and Sallow, A. (2021). face detection and

recognition using opencv. Journal of Soft Computing
and Data Mining, 2(2).
https://doi.org/10.30880/jscdm.2021.02.02.008

[4] Nath, R., Kakoty, K., Bora, D. J., & Welipitiya, U. (2021,
January 31). Face Detection and Recognition Using
Machine Learning. ResearchGate;
https://www.researchgate.net/publication/3489172
90_Face_Detection_and_Recognition_Using_Machine_L
earning

[5] Anjeana, N., & Anusudha, K. (2023, September 19).

Real time face recognition system based on YOLO and
InsightFace. Multimedia Tools and Applications;
Springer Science+Business Media.
Fig -2: Proposed workflow https://doi.org/10.1007/s11042-023-16831-7

[6] Kulkarni. (2023, July). FACE RECOGNITION-BASED

The above workflow has two planned phases. The first
ATTENDANCE MANAGEMENT SYSTEM. European
phase is going to be about the Facial Recognition System
comprising of the Feature extraction and Algorithm Chemical Bulletin. Retrieved November 4, 2023, from
selection activities. This will be followed by creation of the https://www.eurchembull.com/uploads/paper/1e352
New User’s registration form and setting up the Redis 83b24f34bb113e83356c134eb6a.pdf
Database.

© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 722
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
View publication stats

Volume: 10 Issue: 11 | Nov 2023 www.irjet.net p-ISSN: 2395-0072

[7] (n.d.). Face Recognition and Identification using Deep

Learning Approach. Iopscience.
https://iopscience.iop.org/article/10.1088/17426596
/1755/1/012006/pdf

© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 723