Face Recognition Using Machine Learning

Priyanka Chilap1, Nikita Chaskar2, Vaishnavi Amup3 , Ass. Prof. Supriya Pawar4
Department of Computer Engineering Jaihind College of Engineering, Kuran, Pune
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract – Now a day’s most of the education system OpenCV is a video and image processing library and it is
introduces the concept of smart classroom which involves the used for image and video analysis, like facial detection,
smart attendance system. In this project we are going to license plate reading, photo editing, advanced robotic
describe the student attendance system with face recognition vision, and many more. The method in which with the help
that uses the machine learning algorithms like haar cascade of python and OpenCV in deep learning is the most
algorithm and local binary pattern histogram LBPH efficient way to detect the face of the person. This method
algorithm. This project contains two main parts of attendance is useful in many fields such as the military, for security,
system that is face detection and face recognition. In this schools, colleges and universities, airlines, banking, online
proposed system we use the OpenCV library along with python web applications, gaming etc. this system uses powerful
that provides various functions or algorithms related face python algorithm through which the detection and
recognition. The main objective of this project is to make the recognition of face is very easy and efficient.
attendance management system reliable, efficient, simple, time When the system detects the face, it will produce an sub-
saving and easy. image and this sub-image is scaled such that the face appears
in the center and presented at a uniform size. OpenCV
Key Words:- machine learning, haar cascade, LBPH, face already provide an algorithm to locate faces.
detection, face recognition, OpenCV, python, attendance.
1.1 Problem Statement

Implementing Attendance System using Machine

1.INTRODUCTION Learning. Traditional student attendance marking technique
is often facing a lot of trouble. The face recognition student
The success of an educational institute begins by engaging attendance system emphasizes its simplicity by eliminating
students and having regular attendance of students. Having a classical student attendance marking technique such as
higher attendance score results in higher marks, higher retention calling student names or checking respective identification
rates, and a better educational experience. It is difficult for cards. There are not only disturbing the teaching process but
teachers and students to build a strong relationship if students also causes distraction for students during exam sessions. In
are frequently absent. This hampers teachers and students to this project we are going to describe the student attendance
develop their skills and make progression. In many schools, the system with face recognition that uses the machine learning
algorithms. This project contains two main parts of
school budgets are based on the average daily attendance of the
attendance system that is face detection and face recognition.
school. If the attendance rates are low, then school budgets
In this proposed system we use the OpenCV library along
suffer. with python that provides various functions or algorithms
Computer Vision is one of the most fascinating and related face recognition. The main objective of this project is
challenging tasks in the field of Artificial Intelligence. Computer to make the attendance management system reliable,
Vision serves as a link between computer software and the efficient, simple, time saving and easy.
visuals we see around us. It enables computer software to
comprehend and learn about the visuals in its environment.
Facial Recognition represents the event of a system which may 1.2 Motivation
determine the person with the assistance of a face using
Computer Vision (Open CV). • Reducing time wastage during conventional class
The term "OpenCV" is an abbreviation for "open source attendance.
computer vision." The architecture is made up of • Utilizing latest trends in machine vision to implement a
software, databases, and plugins that are pre-programmed feasible solution for class attendance system.
with support for integrating computer vision applications. It • Automating the whole process so that we have digital
is one of the most used toolkits with a large developer group. environment.
It is well-known for the size at which it builds real- • Preventing fake roll calls as one to one attendance
world usage cases for industrial use. OpenCV follows C/C++, marking is possible only.
Python, Java programming languages and can be used to • Encouraging the use of technology in daily lives.
build computer vision software for desktop and smartphone
platforms such as Windows, Linux, macOS, Android, and iOS.

© 2022, IRJEdT Volume: 04 Issue: 05 | May-2022 Page 195

2. LITERATURE SURVEY the shape of the cheekbones, the length of the jaw line, etc.
are registered into the database folder by using the facial
With the rapid development of video monitoring, the recognition xml file from the „OpenCV‟ python library. Once
massive informa- tion of the monitoring image has far the features are registered, the model is trained using the
exceeded the effective processing range of human resources. gathered.
A face recognition is prevalently carried out by using
„perfect‟ data of full-frontal facial images without any sort of
damage like due to accident on the image. Nowadays the Face Recognition:-Although the terms face detection and
number of thefts and identity fraud has become a serious face recognition are often used together, facial recognition is
issue. In order to avoid these thefts and identity fraud, a face only one application for face detection albeit one of the most
recognition system must be established. An application for significant ones.
tracking and detecting faces in videos and in cameras which OpenCV:- OpenCV is a video and image processing library
can be used for multipurpose activities. The intention of the and it is used for image and video analysis, like facial
paper is deep study of face detection using open CV. detection, license plate reading, photo editing, advanced
robotic vision, and many more.
Dlib:-The dlib library contains our implementation of „deep
3. ARCHITECTURE metric learning‟ which is used to construct our face
embeddings used for the actual recognition process.
Attendance Update:- Once the facial recognition is done
successfully, the attendance for the corre- sponding student is
updated into the database automatically, without any hu-
man intervention. If a match is found from the existing
database, the student is marked as present, in all other cases
the student is marked absent.

4. FUTURE SCOPE
In the future this system can be implemented as a part of the
smart classroom objective. However, the efficiency could be
improved by integrating high speed computers with a good
RAM and Usage of a good quality video camera capable of
capturing live feed.

5. CONCLUSIONS

Face recognition technology is one of the most popular

application of artificial intelligence which is used in several
places for security purpose. In this project we describe the
student attendance system will be helpful for many as it is
simple, effi- cient, time saving and cost effective. The use of
machine learning algorithms makes it an easier and reliable
system which can be made by anyone according to their re-
quirement.
Fig -1: Architecture Diagram

Face Detection:-Face detection also called facial detection is ACKNOWLEDGEMENT

an artificial intelligence (AI) based computer technology We would like to sincerely thank our project guide Miss.
used to find and identify human faces in digital images. Face Supriya mam for guiding throughout this project work also
detection technology can be applied to various fields would like to thank our other faculty members from the
including security, biometrics, law enforcement, computer engineering department at Jaihind College of
entertainment and personal safety to provide surveillance Engineering, Kuran for allowing us to perform our project
and tracking of people in real time. Face work.

Feature Extraction:- The facial features such as distance

between the eyes, width of the nose, depth of the eye sockets,

© 2022, IRJEdT Volume: 04 Issue: 05 | May-2022 Page 196

REFERENCES

[1] ZUOLIN DONG , JIAHONG WEI , XIAOYU CHEN , AND

PENGFEI ZHENG, “Face Detection in Security Monitoring
Based on Artificial Intelligence Video Retrieval
Technology”, IEEE, April 15,2020.
[2] Tejashree Dhawle, Urvashi Ukey, Rakshandha
Choudante , “ Face Detection and Recognition using
OpenCV and Python ”IRJET,Oct 2020. R. Nicole, “Title of
paper with only first word capitalized,” J. Name Stand.
Abbrev., in press.
[3] K.Akintoye A, O Onuodu F. E , An Improved Model for
Imperfect Facial Recognition using Python-Open CV
”,IJERT,Nov 2019.
[4] Shrutika V. Deshmukh, Prof Dr. U. A. Kshirsagar , “Face
Detection and Face Recognition Using Raspberry Pi
”,IJARCCE,April 2017.
[5] Kruti Goyal ,Kartikey Agarwal ,Rishi Kumar , Face
Detection and Tracking Using OpenCV ”, ICECA,2017.
[6] Student Attendance System with Face Recognition using
Machine Learning Priyanka Chilap1, Nikita Chaskar2,
Vaishnavi Amup3
[7] Haar Cascade Algorithm And Local Binary Pattern
Histogram LBPH Algorithm In Face Recognition
Priyanka Chilap1, Nikita Chaskar2, Vaishnavi Amup3,
Supriya Pawar4

© 2022, IRJEdT Volume: 04 Issue: 05 | May-2022 Page 197