Facial Id Attendance System

To maintain the attendance record with day to day activities is a challenging task. The conventional method of calling name of each student is time consuming and there is always a chance of proxy attendance. The following system is based on face recognition to maintain the attendance record of stude

2025-06-28 16:32:32 - Adil Khan

Project Title

Facial Id Attendance System

Project Area of Specialization Software EngineeringProject Summary

To maintain the attendance record with day to day activities is a challenging task. The conventional method of calling name of each student is time consuming and there is always a chance of proxy attendance. The following system is based on face recognition to maintain the attendance record of students using deep learning.

Students will register through our system.

Face recognition to identify faces of every student that are present in the classroom using deep learning models, MTCNN libraries to calculate unique face embeddings.

Classes will be registered in our system along with the timings of the class.

As the time of class arrives the attendance of the students will get marked by taking snaps of the students from the class.

The attendance will be updated in the database.

Attendence sheet will be generated and import to Excel format xslx.

As soon as the attendance sheet is generated email will be sent to the parents to inform them about their child being absent.

Option to generate report for each student and visualization showing the number of days student attended college as a percentage.

Project Objectives

To maintain the attendance record with day to day activities is a challenging task. The conventional method of calling name of each student is time consuming and there is always a chance of proxy attendance. The following system is based on face recognition to maintain the attendance record of students using deep learning.

Project Implementation Method

OpenCV dlib library

Python

MTCNN library to calculate facial embedding

HOG

SVD Classifier to identify faces

ReactJS front end

Backend with Flask

Hardware: Webcam

Benefits of the Project

To maintain the attendance record with day to day activities is a challenging task. The conventional method of calling name of each student is time consuming and there is always a chance of proxy attendance.Attendence system in Pakistan are mostly manual where teachers have to mark attendance manually. This is a tedious and time consuming process and a lot of times students can mark proxies. In our software we will use face recognition to maintain the attendance record of students.

Technical Details of Final Deliverable

The first step in implementing the system is to create a database of enrolled students. In actual implementation, this step must be a part of the admission process where we collect the necessary information of the students. This is accomplished using dashboard as mentioned in the proposed system. The set of images which is known image data set is stored in a folder named known. The facial recognition algorithmthen uses the image data set to create a dictionary of face encoding containing keys.Each image in unknown folder is taken and its face encodings are generated using face encodings (unknown_image) method from face recognition library where unknown_image is an image in unknown folder. The encoding is directly compared against all the encodings of known images stored in JSON file When an image is recognize.Whenever the algorithm finds a match, the name of the images identified are first stored in a dictionary with two keys where one represents identified and other represents unidentified. Based on the list we then update the corresponding field of the person in the firebase database with a ‘1’ on that particular date using Pyrebase library. Else by default, it is marked as ‘0’ which means that the person is absent. Firebaseprovides a very efficient way of storing the data.The attendance is posted for a given date and session in Firebase real-time database. Unidentified people images and date and session details are stored by generating temporary ids for each. The angular application fetches these details and displays it in a clean UI. See the visual output of angular web application in the result section.

Final Deliverable of the Project Software SystemCore Industry EducationOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Quality EducationRequired Resources
Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total in (Rs) 13500
web came Equipment110001000
Gpu card Equipment195009500
web hosting Miscellaneous 130003000

More Posts