Smart Attendance System with Facial Recognition

Our project will digitize the process of attendance collection by using image processing technique and will automatically update real time data. Since the project is software based, we will be only using one hardware component, that is, Device?s Camera, to capture the real time face of the student a

Project Title

Smart Attendance System with Facial Recognition

Project Area of Specialization

Artificial Intelligence

Project Summary

Our project will digitize the process of attendance collection by using image processing technique and will automatically update real time data. Since the project is software based, we will be only using one hardware component, that is, Device’s Camera, to capture the real time face of the student as an input to the computer. This image is processed and compared with preloaded image, as soon as image gets identified our algorithm indicated the master processor to transmit the identified person data to the csv Attendance sheet. The csv Attendance sheet can be modified easily. 

Project Objectives

• Main objective is to digitize the whole attendance concept.
• Improve time management.
• To help people with hearing and speaking impairments. 
• To encourage the use of technology and digitizing our environment. 
   

Project Implementation Method

A pipeline is built, where we solve each step of face recognition separately and pass the result of the current step to the next step. In simple words, we will chain together several machine learning algorithms. This project uses Face-recognition library to recognize our faces and differentiate it among a lot of people. The HOG method (algorithm), which stands for Histogram of Oriented Gradient, is used at the backend for the recognition process.  Dlib library is used for the facial landmarks recognition.  The library recognizes the landmarks of the face and matches it with the preloaded images present in the folder and make it more centered for the face to be recognized more clearly.  The centered image is sent to a neural network, already trained, which gives us the encoding features. The neural network generated 128 different measurements of the images that we feed into it, and help us to define and differentiate different persons. Then the project uses a Machine Learning method, called SVM classifier, to identify if the measurements are of a given person or not. 
 

Benefits of the Project

• Reducing time wastage during conventional class attendance.
• Utilizing latest trends in machine vision to implement a feasible solution for class attendance system.
• Automating the whole process so that we have digital environment.
• Preventing fake roll calls as one to one attendance marking makes it possible only.
• Encouraging the use of technology in daily lives.
• Help people with hearing and speaking impairments.

Technical Details of Final Deliverable

Software Requirements    

• PyCharm 2021.2
• Programming Language used: Python 
• CMake 3.22.1 (Helps running any library based on the language C++)
• Visual Studio Build Tools 2019 (For PyCharm libraries to run properly)

Hardware Requirements    

• The camera is the only hardware component required to capture live video feed of students.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

IT

Other Industries

IT

Core Technology

Artificial Intelligence(AI)

Other Technologies

Others

Sustainable Development Goals

Quality Education

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com