Mini-Project Report On

Automatic Attendance System using AI Face

Recognition

Submitted in partial fulfillment of the requirements of

the T.E.

T.E COMPUTER ENGINEERING

By

Chavan Anuj 17
Bhosale Santosh 14
Kayande Pradip 44
Patil Prathamesh 71

Name of the Mentor

Prof. Manisha Sonawane

(Size 50 mm x 50 mm)
Department of Computer Engineering
Shivajirao S. Jondhale College of Engineering.
Dombivli (E)

University of Mumbai

1
 (AY 2022-23)

CERTIFICATE

This is to certify that the Synopsis on Mini Project entitled “Automatic

Attendance System using AI Face Recognition” is a bonafide work of

Chavan Anuj (17), Bhosale Santosh (14), Kayande Pradip (44), Patil

Prathamesh (71) submitted to the University of Mumbai in partial fulfilment

of the requirement for the award of the degree of “Bachelor of Engineering”

in “Computer Engineering”.

Prof. Manisha Sonawane

Mentor

Dr. Renuka Deshpande Dr. Uttara Gogate Dr. Pramod Rodge

Project Coordinator Head of Department Principal

2
 Mini Project Approval

This Synopsis on Mini Project entitled “Automatic Attendance System

using AI Face Recognition” by Chavan Anuj (17), Bhosale Santosh(14),

Kayande Pradip(44), Patil Prathamesh(71) is approved for TE (Computer

Engineering) Semester V during the academic year 2022-23

Examiners

1………………………………………
(Internal Examiner Name & Sign)

2…………………………………………
(External Examiner name & Sign)

Date:

Place:

3
 TABLE OF CONTENT

Abstract……………………………………………………………………………… ii

Acknowledgments…………………………………………………………………... iii

List of Abbreviations………………………………………………………………...iv

List of Figures………………………………………………………………………...v

List of Tables………………………………………………………………………... vi

1 Introduction…………………………………………………………………..1
1.1 Introduction……………………………………………………………
1.2 Motivation……………………………………………………………..
1.3 Problem Statement & Objectives………………………………………

2 Literature Survey………………………………………………………….. 3

2.1 Survey of Existing System/SRS………………………...…………..

2.2 Limitation Existing system……………….…………………………

3 Proposed System …………………………………………………………..6

3.1 Introduction…………………………………………………………..
3.2 Architecture………………………………………………………….
3.3 Algorithm and Process Design……………………………………….
3.4 Details of Hardware & Software……………………………………..
3.5 Expected Results ……………………………………………………..
3.6 Conclusion…………………………………………………………….

References………………………………………………………………………... 11

1
 Abstract

Automatic face recognition (AFR) technologies have made many improvements in the
changing world. Smart Attendance using Real-Time Face Recognition is a real-world solution
which comes with day to day activities of handling student attendance system. Face
recognition-based attendance system is a process of recognizing the students faces for taking
attendance by using face biometrics based on high-definition monitor video and other
information technology. In my face recognition project, a computer system can find and
recognize human faces fast and precisely in images or videos captured through a surveillance
camera. Numerous algorithms and techniques have been developed to improve face
recognition performance, but Deep Learning is the concept to be implemented here. It helps in
converting the frames of the video into images so that the face of the student can be easily
recognized for their attendance and the attendance database can be easily reflected
automatically.

2
 Acknowledgement

We have great pleasure in presenting the report on the Automatic Attendance System using
AI Face Recognition. We take the opportunity to express our sincere thanks towards our
guide Prof. Manisha Sonawane Department of Computer Engineering for providing the
technical guidelines and suggestions regarding the line of work. We would like to express our
gratitude towards her constant encouragement, support and guidelines throughout the
planning of the project.

We thank Dr Uttara Gogate Head of the Computer Department, for his encouragement
during the progress meeting and for providing guidelines to write this project.

We thank Dr Renuka Deshpande TE project coordinator, Department of Computer

Engineering, for being encouraging throughout the course and for guidance.

Lastly, we would like to thank our college principal Dr P.R.Rodge for providing lab facilities
and permitting us to go on with our project. We would also like to thank our colleagues who
helped us directly or indirectly during our project.

Chavan Anuj 17/A

Patil Prathamesh 71/B
Kayande Pradip 44 /A
Bhosale Santosh 14/A

3
 List of abbreviations

AI Artificial Intelligence
ML Machine Learning
GUI Graphical User Interface
LBP Local Binary Pattern
CSV Comma Separated Value
ROI Region of Interests

4
 List of Figures
Figure No. Figure Name Page no.
3.2.1 Architecture of Proposed 7
System

3.5.1 Expected Result of Proposed 10

System

5
 List of Tables
Figure No. Figure Name Page no.
2.1.1 Literature Survey 4-5

6
7
 Chapter 1
Introduction

1.1 Introduction
The technology aims in imparting tremendous knowledge-oriented technical innovations these
days. Deep Learning is one of the interesting domains that enables the machine to train itself
by providing some datasets as input and providing an appropriate output during testing by
applying different learning algorithms. Nowadays Attendance is considered as an important
factor for both the student as well as the teacher of an educational organization. With the
advancement of deep learning technology, the machine automatically detects the attendance
performance of the students and maintains a record of the collected data. In general, the
attendance system of the student can be maintained in two different forms namely,

● Manual Attendance System (MAS)

● Automated Attendance System (AAS).

A manual Student Attendance Management system is a process where a teacher concerned

with a particular subject needs to call the student’s name and mark the attendance manually.
Manual attendance may be considered a time-consuming process or sometimes it happens for
the teacher to miss someone or students may answer multiple times in the absence of their
friends. So, the problem arises when we think about the traditional process of marking
attendance in the classroom. To solve all these issues, we go with the Automatic Attendance
System (AAS).
An automated Attendance System (AAS) is a process to automatically estimate the presence
or the absence of the student in the classroom by using face recognition technology. It is also
possible to recognize whether the student is sleeping or awake during the lecture and it can
also be implemented in the exam sessions to ensure the presence of the student. The presence
of the students can be determined by capturing their faces on to a high-definition monitor
video streaming service, so it becomes highly reliable for the machine to understand the
presence of all the students in the classroom. The two common Human Face Recognition
techniques are,

● Feature-based approach

● Brightness-based approach

1
The Feature-based approach also known as the local face recognition system, is used in
pointing the key features of the face like eyes, ears, nose, mouth, edges, etc., whereas the
brightness-based approach also termed as the global face recognition system, used in
recognizing all the parts of the image.

1.2 Motivation
The driving force behind implementing the Automatic Attendance system is to contribute to
educational society by providing an attendance system so that the teachers can efficiently
track student attendance.

1.3 Problem Statement & Objective

There have been several problems with pre-existing attendance system. This project aims to
describe some of those disadvantages like project cost, and complex product design like face
enrolment process and attendance marking. An app that has a simple and user-friendly UI that
can make face enrolment and marking attendance easier. It will capture a single image of the
entire classroom, recognizing faces from an individual image, hence reducing the storage
space.

2
 Chapter 2
Literature Survey

2.1 Survey of Existing System

The Automated Attendance System is the progress that has taken place in the field of
automation replacing the attendance marking activity traditionally. Automated Attendance
Systems are generally bio-metric , RFIDcardand MATLABbased. These systems are
widely used in different organizations. Traditional method of attendance marking is
very time consuming and becomes difficult when the strength is high. Automation of
Attendance System has a boundary over conventional method as it saves time and also can
be used for security purposes. This also helps to prevent fake attendance[1].

It is based on face detection and recognition algorithms, automatically detects the student
when he enters the class room and marks the attendance by recognizing him. The system
architecture and algorithms used in each stage are described in this paper. Different real time
scenarios are considered to evaluate the performance of various face recognition systems.
This paper also proposes the techniques to be used in order to handle the threats like spoofing.
When compared to traditional attendance marking this system saves the time and also helps to
monitor the students[2].

The attendance maintaining system is difficult process if it is done manually. The smart and
automated attendance system for managing the attendance can be implemented using the
various ways of biometrics. Face recognition is one of them. By using this system, the issue
of fake attendance and proxies can be solved. In the previous face recognition based
attendance system, there were some disadvantages like intensity of light problem and head
pose problem. Therefore to overcome these issues, various techniques like illumination
invariant, Viola and Jones algorithm, Principle component analysis are used. The major steps
in this system are detecting the faces and recognizing them. After these, the comparison of

3
detected faces can be done by crosschecking with the database of student's faces. This smart
system will be an effective way to maintain the attendance and records of students.[3]

Being one of the most successful applications of the image processing, face recognition has a
vital role in technical field especially in the field of security purpose. Human face recognition
is an important field for verification purpose especially in the case of student’s attendance.
This paper is aimed at implementing a digitized system for attendance recording. Current
attendance marking methods are monotonous & time consuming. Manually recorded
attendance can be easily manipulated. Hence the paper is proposed to tackle all these
issues[4].

Attendance marking system has become a challenging task in the real-time system. It is tough
to mark the attendance of the candidate in the huge classroom/hall, and there are many
students attending the class. Many attendance management systems have been implemented
in the current research. However, the attendance management system by using facial
recognition still has issues which allow the research to improve the current research to make
the attendance management system working well. The paper has conducted a literature survey
on the previous work by different researchers on their research paper[5].

2.2 SUMMARY OF LITERATURE REVIEW

Paper Approach Technology used Disadvantage

[1] Attendance The camera is present Histogram The problem with

System Using Face inside the classroom Normalization the image
Recognition and where the students are technique.  representation we are
Class Monitoring seated.  given is its high
System, Arun The camera captures dimensionality, so an
Katara, Mr. Sudesh, the images of students image with 100x100
V.Kolhe from the video frame.  pixels lies in a
10,000 dimensional
image space
already. 

[2] Shireesha When a person enters It uses the Viola-Jones The problem with
Chintalapati, M.V. the classroom his algorithm for face this approach is that
Raghunadh, image is captured by detection.  it captures only one
“Automated the camera at the It uses the Histogram student’s image at a
Attendance entrance.  normalization time when he enters
Management The face region is technique for the classroom.
System Based On then extracted and preprocessing.
Face Recognition pre-processed for PCA is used for feature
Algorithms”, further processing. extraction.
4
 SVM is used for the
classification of the
face.

[3] P. Wagh, R. Firstly; to mark the It uses PCA along with The will be a fake
Thakare, J. attendance of students, Eigenface. attendance if the
Chaudhari, and S. the image of students’ student just come in
Patil, “Attendance faces will be required.  classroom and then
system This image can be go back before the
based on face snapped from the end of class period
recognition using camera device. 
eigen face and PCA This image will act as
algorithms”. input to the system. 

[4] J. Joseph and K. The proposed system It uses PCA in The system have
P. Zacharia, consists of a high- MATLAB.  tested with the single
“Automatic resolution digital images only based
Attendance camera to monitor the on
Management classroom or office the result.
System Using Face room. 
Recognition”  It is embedded on a
micro-controller-
based motor system.
 The data or images
obtained by the
camera are sent to a
computer programmed
system for further
analysis. 

[5] A. S. S. The proposed system It uses a combination The computation

NAVAZ and T. D. integrates an web app of PCA along with time and
S. P. MAZUMDER, and face recognition ANN for facial implementation cost
“Face Recognition algorithms. Any recognition is higher because of
using Principal device with a camera combination of PCA
Component can capture an image with ANN
Analysis and Neural or a video and upload
Networks,” vol. 1, it to the server using
no. April, pp. 91– the web app. The
94, 2001. received file
undergoes face
detection and face
recognition so the
detected faces are
extracted from the
image.

Figure 2.1.1

5
2.3 Limitations in Existing System
There have been several problems with the pre-existing attendance system. This project aims
to describe some of those disadvantages like project cost, and complex product design like
face enrollment process and attendance marking. An app that has a simple and user-friendly
UI that can make face enrollment and marking attendance easier. It will capture a single
image of the entire classroom, recognizing faces from an individual image, hence reducing the
storage space.

6
 Chapter 3
Proposed System

3.1 Introduction
The task of the proposed system is to capture the face of each student and to store it in
the database for their attendance. The face of the student needs to be captured in such a
manner that all the feature of the students’ face needs to be detected. There is no need
for the teacher to manually take attendance in the class because the system records a
video and through further processing steps the face is recognized and the attendance
database is updated. This system is developed using python OpenCV.

3.2 Architecture

7
 Figure 3.2.1
3.3 Algorithm and Process Design
3.3.1 Start
3.3.2 Open Camera
3.3.3 Capture the Image of Students
3.3.4 Apply Haar Cascade algorithm(Face Detection)
3.3.5 Extract the ROI in Rectangular Bounding Box
3.3.6 Convert to grayscale.
3.3.7
if Updating Database then
Store in Database

Enter Details of Student

8
 else
Apply LBP (For feature Extraction)
Apply Distance Classifier (For Classification)
end if

3.3.8
if Student Classified
Mark Attendance as Present of those Students and save in CSV
Else
Mark Absent for those whose faces not present in class.

3.4 Details of Hardware and Software

Hardware requirement

● Processor: Intel i5 and above

● Webcam or External Camera

● Computer monitor

● Keyboard

9
 ● Mouse

● RAM: 4GB to 6GB

● Mobile Phone

Software requirement:

● Operating system: Windows, Linux, Android or MAC OS.

● Language: Python & OpenCV

● Visual Studio or PyCharm

3.5 Expected Results

10
Recognition
 Marking Attendance

Figure 3.5.1

3.6 Conclusion
Capturing the images from a camera or cc camera and applying techniques of face detection
and recognition can decrease the manual work from humans and increase security safety,

11
taking the decision from this recognition result. Based on this face detection and recognition
can be used in implementing so many applications like automatic attendances system based
on face recognition, worker attendance, security, safety, and police application like finding a
thief in the image that help to catch the thief. In this system, we have implemented an
attendance system for a lecture, section or laboratory by which the lecturer or teaching
assistant records student’s attendance. It saves time and effort, especially if it is a lecture with
a huge number of students. This attendance system shows the use of facial recognition
techniques for the purpose of student attendance and for the further process this record of
student can be used in exam related issues.

Chapter 4
References

12
[1] Arun Katara1, Mr. Sudesh2, V.Kolhe3: Attendance System Using Face Recognition and
Class Monitoring System, IJRITCC Volume 5, 2017(pp 273-276).

[2] Shireesha Chintalapati, M.V. Raghunadh: “Automated Attendance Management System

Based On Face Recognition Algorithms” , IEEE International Conference on Computational
Intelligence and Computing Research, 2013.

[3] ] P. Wagh, R. Thakare, J. Chaudhari, and S. Patil: “Attendance system based on face
recognition using eigen face and PCA algorithms”, International Conference on Green
Computing and Internet of Things (ICGCloT), 2015

[4] J. Joseph and K. P. Zacharia: “Automatic Attendance Management System Using Face
Recognition” Int. J. Sci. Res., vol. 2, no. 11, pp. 327–330, 2013.

[5] A. S. S. NAVAZ and T. D. S. P. MAZUMDER: “Face Recognition using Principal

Component Analysis and Neural Networks,” vol. 1, no. April, pp. 91–94, 2001.

13