Biometric Attendance System
The main focus of our project "Biometric Attendance System" is to provide a smart and efficient attendance taking system in organizations for students, employees or staff. In this project, we are using facial characteristics to mark attendance of a person. We are using concepts of Deep L
2025-06-28 16:30:38 - Adil Khan
Biometric Attendance System
Project Area of Specialization Artificial IntelligenceProject SummaryThe main focus of our project "Biometric Attendance System" is to provide a smart and efficient attendance taking system in organizations for students, employees or staff.
In this project, we are using facial characteristics to mark attendance of a person. We are using concepts of Deep Learning for this purpose.
The person will be recognized from the real-time video footage of the CCTV camera without even being bothered. Detection and Recognition is done using MTCNN and FaceNet algorithms.
After recognizing a person using deep learning algorithms, the data will be sent to the database using IoT. This data will be uploaded on the website and can be accessed by the organization manager or by the person itself.
This data will have the basic information about the person whose attendance is to be marked along with the time of entrance and the time of leaving the organization.
This system can also be used to keep track of the students, employees or the staff members by keeping the track of time of the person.
This system will reduce the chances of error in attendance by reducing the chance of proxy. This system does not need any human assistance thus reducing human error. That is why, this system is more reliable and efficient than the conventional attendance system.
Project ObjectivesIn this time of pandemic where COVID-19 can spread even if we are using fingerprint attendance system because everyone must scan their finger and that can cause the spread of virus. Our system can bring crowd to minimal level and prevent user intervention.
Our system will help in bettter functioning of organization by keeping the employees track of time. This will also help many organizations in computing the salary of employees. This attendance system is also more satisfactory than the conventional method.
Project Implementation MethodThis is hardware and software based system in which camera provides a real time footage to microprocessor which then applies deep learning algorithms on for face detection and recognition. Then save that data on the database that can then be accessed through website.
Hardware Implementation:
The hardware part includes a CCTV camera that captures the real-time footage and then send that footage to Jetson Nano (microprocessor). This microprocessor then uses MTCNN and FaceNet for face recognition and then send that data to database. For satisfaction of students/employees, a LCD will be used to show that either the attendance of the person is marked or not.
Software Implementation:
- Face Detection:
Obviously, the first thing to do would be to pass in an image to the program. In this model, we want to create an image pyramid, to detect faces of all different sizes. In other words, we want to create different copies of the same image in different sizes to search for different sized faces within the image.
- Face Recognition:
FaceNet takes an image of the person’s face as input and outputs a vector of 128 numbers which represent the most important features of a face. In machine learning, this vector is called embedding. Why embedding? Because all the important information from an image is embedded into this vector. Basically, FaceNet takes a person’s face and compresses it into a vector of 128 numbers. Ideally, embeddings of similar faces are also similar.
One possible way of recognising a person on an unseen image would be to calculate its embedding, calculate distances to images of known people and if the face embedding is close enough to embeddings of person A, we say that this image contains the face of person A.
There are many advantages or benefits of this project and some of them are mentioned below:
- Automated time tracking system:
Automation simplifies time tracking, and there is no need to have personnel to monitor the system 24 hours a day. To err is human, and with automated systems, human error is eliminated. A time and attendance system using facial recognition technology can accurately report attendance, absence, and overtime with an identification process that is fast as well as accurate. - Labor cost saving:
Facial recognition software can accurately track time and attendance without human error. It keeps track of the exact number of hours an employee is working, which can help save the company money. You will never have to worry about time fraud or “buddy punching” with a facial recognition time tracking system. - Time saving and reduced contagion:
In this time of pandemic (COVID -19) when contagious illnesses such as colds and viruses spread throughout the workforce, it can increase the incidence of employee absences and significantly reduce productivity. With facial recognition, employees can enter and leave the facility in considerably less time. There is no need to touch the surface of the system to clock in or out. This saves time, as well as minimizing the spread illnesses due to physical contact.
The technical details of final deliverables are:
- Detect Human Face using MTCNN:
This algorithm will detect that either there is a human face present or not in the frame. - Recognize Human Face:
FaceNet then uses the face image cropped by the MTCNN to search for similar faces in the encodings. - Mark attendance:
When the face is recognized, attendance will be marked on the database also keeping track of the time. - Create a daily report:
A report will be created on the daily bases which will provide information about the attendance. - Display data report on Web and LCD:
The attendance will be shown on the LCD on the real-time so that the person can know that his/her attendance is marked. This information can also be accesses through the website.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 41900 | |||
| Jetson Nano | Equipment | 1 | 25000 | 25000 |
| Jetson Nano case with fan | Equipment | 1 | 1500 | 1500 |
| CCTV camera | Equipment | 2 | 5000 | 10000 |
| LCD (21 inch) | Equipment | 1 | 2400 | 2400 |
| Micro SD Card (64 GB) | Equipment | 1 | 3000 | 3000 |