Scribd
Upload
1 views

Enhanced_Literature_Survey_Face_Recognition

The document discusses the development of a face recognition-based attendance monitoring system aimed at addressing inefficiencies in traditional attendance methods. It highlights the limitations of existing systems, the technologies used, and the importance of privacy and security in handling biometric data. The proposed solution enhances productivity and accountability through real-time attendance tracking and offers future enhancements for improved functionality.

Uploaded by

notesforme09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
1 views

Enhanced_Literature_Survey_Face_Recognition

The document discusses the development of a face recognition-based attendance monitoring system aimed at addressing inefficiencies in traditional attendance methods. It highlights the limitations of existing systems, the technologies used, and the importance of privacy and security in handling biometric data. The proposed solution enhances productivity and accountability through real-time attendance tracking and offers future enhancements for improved functionality.

Uploaded by

notesforme09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Literature Survey

Attendance Monitoring System Using Face Recognition

Introduction:

With the rapid advancement in Artificial Intelligence and Deep Learning, face recognition has emerged as a

prominent solution for identity verification tasks. Attendance systems in corporate offices, hospitals, and

educational institutions have historically suffered from inefficiencies such as proxy attendance, manual errors,

and lack of real-time monitoring. By leveraging computer vision and deep learning, facial recognition-based

attendance systems offer a reliable and efficient alternative.

Existing Systems and Limitations:

Traditional systems like manual registers, RFID cards, or biometric fingerprints have been widely used.

However, each has notable drawbacks:

- Manual registers are prone to manipulation and time-consuming.

- RFID cards can be easily misused for proxy attendance.

- Fingerprint scanners are less hygienic, especially post-pandemic, and struggle with wet or damaged skin.

Use Cases and Motivation:

Real-world observations, particularly in banks and hospitals, reveal frequent delays, early exits, and

inefficient monitoring of work hours. These practices lead to productivity loss and poor accountability. Our

project is inspired by such workplace inefficiencies and aims to resolve them through automation and

technology.

Technologies Used:

This project utilizes Python as the core programming language, along with OpenCV and MediaPipe for face

detection and tracking. A deep learning-based approach using Convolutional Neural Networks (CNN) forms

the backbone of the face recognition pipeline. Integration with a secure backend database allows for real-time

attendance recording, timestamp logging, and duration tracking.

Literature Insights:

Previous studies have shown that face recognition systems can achieve up to 98% accuracy in controlled

environments. According to a 2021 IEEE paper, CNN-based models outperform traditional feature-based
models like Eigenfaces and Fisherfaces. Systems implemented in universities and corporations have proven

effective in reducing absenteeism and enhancing punctuality.

Privacy and Security:

Since face recognition involves sensitive biometric data, our system ensures encrypted data storage and

local device processing to minimize privacy risks. No personal data is shared over insecure networks, making

it GDPR-compliant in design.

Comparative Analysis:

| Method | Pros | Cons |

|--------------------|-----------------------------------|--------------------------------------|

| Manual Attendance | Easy to implement | Time-consuming, error-prone |

| RFID/ID Cards | Quick, Contactless | Susceptible to proxies |

| Fingerprint Scanner| Accurate, Widely Used | Unhygienic, Spoofable |

| Face Recognition | Contactless, Real-Time, Secure | Sensitive to lighting, needs a camera|

Proposed Solution:

Our system is a face recognition-based attendance tracker that not only marks attendance in real-time but

also logs entry and exit timestamps to calculate the total working hours. It also helps detect unusual patterns

such as frequent tardiness or early exits. The system ensures fairness and improves organizational

productivity by reducing human bias and manual intervention.

Future Scope:

The proposed system can be extended by incorporating features such as:

- Anti-spoofing measures (e.g., blink detection)

- Cloud-based dashboards for centralized monitoring

- Integration with payroll systems

- Emotion detection for mood-based productivity insights

Conclusion:

Face recognition-based attendance systems mark a significant step forward in automating workplace

monitoring. With enhanced security, real-time logging, and deep learning-powered accuracy, they are
well-suited to modern organizations aiming for transparency, discipline, and efficiency.

You might also like