Secure and Efficient Facial Identification Based Attendance System For Institution

ABSTRACT
Attendance is a major part of any institution in the whole world. Since older
times, Attendance are taken with the help of roll call manually and marked in the
register and vice versa. It is a tedious task to do given the modern age we are in
right now. Since, every task is automated so why not taking attendance!. Moreover,
manual task involves human error which is unavoidable. In a mission to automate
and modernize the attendance marking system, We created a digital attendance
which marks present or absent with the help of Scanning in camera and
maintaining a database in backend. This system recognize face with the help of
LBPH algorithm and Haar cascading algorithms which in turn generates a facial
map. The algorithm used above gives better results compared all other similar
algorithms available Defining whole requirement and management is defined as a
necessary step in the developing the successful software projects and systems
v
TABLE OF CONTENTS
ABSTRACT v
LIST OF FIGURES viii
LIST OF ABBREVIATIONS ix
CHAPTER TITLE PAGE

NO. NO.
1. INTRODUCTION 1
1.1 INTRODUCTION 1
1.2 TECHNOLOGIES USED 3
1.3 ALGORITHM USED 9
2. LITERATURE SURVEY 16
2.1 LITERATURE REVIEW 16

3. AIM AND SCOPE OF THE PRESENT INVESTIGATION 22
3.1 PROBLEM STATEMENT 22

3.2 AIM OF THE PROJECT 22
3.3 OBJECTIVES 23
3.4 EXISTING SYSTEM 24
3.5 PROPOSED SYSTEM 24
4. EXPERIMENTAL OR MATERIALS AND METHODS 26
4.1 ARCHITECTURAL DIAGRAM 26

4.2 MODULE DESCRIPTION 28
5. RESULTS AND DISCUSSION, PERFORMANCE 35
ANALYSIS
6 SUMMARY AND CONCLUSIONS 40
vi
REFERENCES 41
APPENDIX
A. SOURCE CODE 43
B. PLAGIARISM REPORT 47
vii
LIST OF FIGURES
FIGURE NO. NAME OF THE FIGURE PAGE

NO.
1.1 Deep Learning Layers 3
1.2 Deep Learning Process 4
1.3 Example of LBPH 10
1.4 Circular LBH 12
1.5 Integral Image 1
4
1.6 Integral Image is used here to calculate the Haar 1
value 5
1.7 Exceptional case while calculating haar value 1
5
4.1 Face detection Architecture 2
6
4.2 Calculation in LBPH Algorithm 2
7
4.3 Add Record 2
9
4.4 Delete record 2
9
4.5 Train The data 3
0
4.6 Photo Sample 3
1
4.7 Face Recognizer 3
2
4.8 Attendence Report 3
3
4.9 Admin report 3
3
viii
LIST OF ABBREVIATIONS
CNN Convolutional Neural Network

ILSVRC ImageNet Large Scale Visual Recognition Challenge
RNN Recurrent Neural Networks
HTS Hand tracking and segmentation
ix
CHAPTER 1 INTRODUCTION
1.1 INTRODUCTION
The human face plays an important role in our social interaction, conveying
people‟s identity. Using the human face as a key to security, biometric face
recognition technology has received significant attention in the past several years
due to its potential for a wide variety of applications in both law enforcement and
non-law enforcement.
As compared with other biometrics systems using fingerprint/palmprint and iris,
face recognition has distinct advantages because of its non-contact process.
Face images can be captured from a distance without touching the person being
identified, and the identification does not require interacting with the person.
In addition, face recognition serves the crime deterrent purpose because face
images that have been recorded and archived can later help identify a person.
After quitting it, attendance of person will be stored in report table in the databases
with name, id, date and time and status.
This attendance system can be readily used by non-programming personal
avoiding human handled chance of error. In this project apart from marking
attendance by face recognition, one can register new user, update details of user
and delete details. Train dataset, extract embedding's, change password, and view
the attendance report.
In this project, to recognize their face and marking their attendance, the
individual had to register their details in employee management system. Then
extract embedding for every new individual and then train the machine according to
the sample photos taken. After that the individual is free to mark their attendance.
The person can also check their attendance status, update details, delete details,
check sample photos and also change the password credentials. The database is
updated automatically, no need to update manually.
Pros
1. Automated Time Tracking System
Entry and exit time monitoring done manually or with other biometric systems can be
1
0
fully automated with facial recognition attendance systems. There is no need for human
intervention or physical validation as the system‟s advanced algorithms can locate and
identify faces autonomously. It is effortless to track time for employees with facial
recognition
2. Cost Effective
A facial recognition attendance system can save business resources by

automatic employee time tracking.. Irrespective of the business size, such an
attendance system can:
 Increase employee productivity by 10%
 Cut administrative costs by 5-10%
 Save 15% supervision time, helping supervisors with attendance

control
The cost savings are even higher as data received from the face
recognition-based employee attendance system is in real-time and valid.
3. Touchless Sign In System: A Post Pandemic Requirement
Pandemic like Covid 19 can be better managed by minimizing physical contact in public
places and work environments. Post pandemic there has been a significant increase in
demand and adoption of contactless technologies. The industry has recognized the
benefits of facial recognition and the adoption of attendance systems like Truein.
Workplaces and multi-tenant environments can greatly reduce the frequency of contact
between individuals, thus minimizing the risk of virus transmission.
Cons
1. Threatens individual and societal privacy
The threat to individual privacy is a significant downside of facial recognition

technology. People don‟t like having their faces recorded and stored in a database for unknown
future use.
1
1
Privacy is such a big issue that some cities, including San Francisco, California and Cambridge,
2. Imposes on Personal Freedom
Being recorded and scanned by facial recognition technology can

make people feel like they‟re always being watched and judged for their
behavior. Plus, police can use facial recognition to run everyone in their
database through a virtual criminal lineup, which is like treating you as a
criminal suspect without probable cause.
1.2 TECHNOLOGIES USED
Deep learning is a computer software that mimics the network of neurons in a

brain. It is a subset of machine learning and is called deep learning because it
makes use of deep neural networks. Deep learning algorithms are constructed with
connected layers.
 The first layer is called the Input Layer

 The last layer is called the Output Layer
1
2
 All layers in between are called Hidden Layers. The word deep means the
network join neurons in more than two layers.
Figure 1.1 Deep Learning Layers
Each Hidden layer is composed of neurons. The neurons are connected to

each other. The neuron will process and then propagate the input signal it receives
the layer above it. The strength of the signal given the neuron in the next layer
depends on the weight, bias and activation function.
The network consumes large amounts of input data and operates them
through multiple layers; the network can learn increasingly complex features of the
data at each layer.
1.2.1 Importance of Deep Learning:
Deep learning is a powerful tool to make prediction an actionable result.

Deep learning excels in pattern discovery (unsupervised learning) and knowledge-
based prediction. Big data is the fuel for deep learning. When both are combined, an
organization can reap unprecedented results in term of productivity, sales,
management, and innovation.
1
3
Deep learning can outperform traditional method. For instance, deep
learning algorithms are 41% more accurate than machine learning algorithm in
image classification, 27 % more accurate in facial recognition and 25% in voice
recognition.
1.2.2 Deep Learning Process:
Figure 1.2 Deep Learning Process
A deep neural network provides state-of-the-art accuracy in many tasks, from

object detection to speech recognition. They can learn automatically, without
predefined knowledge explicitly coded by the programmers.
1
4
1.3 Algorithm Used:
For determination of disease and for prediction purposes, there are five important
type of algorithms are used. These algorithms have all the type of prediction
accuracy and have all the precision control. These are:-:
 Local Binary Pattern Histogram (LBPH)
 Viola-Jones Face Detection Technique(Haar Cascades)
1.3.1 Local Binary Pattern Histogram(LBPH)
Local Binary Pattern (LBP) is a simple yet very efficient texture operator which
labels the pixels of an image by thresholding the neighborhood of each pixel and
considers the result as a binary number.
It was first described in 1994 (LBP) and has since been found to be a powerful
feature for texture classification. It has further been determined that when LBP is
combined with histograms of oriented gradients (HOG) descriptor, it improves the
detection performance considerably on some datasets.
Using the LBP combined with histograms we can represent the face images with a
simple data vector.
As LBP is a visual descriptor it can also be used for face recognition tasks,
as can be seen in the following step-by-step explanation.
The steps of the algorithm:
1. Parameters: the LBPH uses 4 parameters:
 Radius: the radius is used to build the circular local binary pattern and represents the
radius around the central pixel. It is usually set to 1.
 Neighbors: the number of sample points to build the circular local binary pattern.
Keep in mind: the more sample points you include, the higher the computational
cost. It is usually set to 8.
9

Secure and Efficient Facial Identification Based Attendance System For Institution

Uploaded by

Copyright:

Secure and Efficient Facial Identification Based Attendance System For Institution

Uploaded by

Document Information

Original Title

Copyright

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Secure and Efficient Facial Identification Based Attendance System For Institution

Uploaded by

Copyright:

ABSTRACT

CHAPTER TITLE PAGE

2.1 LITERATURE REVIEW 16

3.1 PROBLEM STATEMENT 22

4.1 ARCHITECTURAL DIAGRAM 26

5. RESULTS AND DISCUSSION, PERFORMANCE 35

6 SUMMARY AND CONCLUSIONS 40

FIGURE NO. NAME OF THE FIGURE PAGE

CNN Convolutional Neural Network

A facial recognition attendance system can save business resources by

 Increase employee productivity by 10%

 Cut administrative costs by 5-10%

 Save 15% supervision time, helping supervisors with attendance

3. Touchless Sign In System: A Post Pandemic Requirement

The threat to individual privacy is a significant downside of facial recognition

2. Imposes on Personal Freedom

Being recorded and scanned by facial recognition technology can

1.2 TECHNOLOGIES USED

Deep learning is a computer software that mimics the network of neurons in a

 The first layer is called the Input Layer

Figure 1.1 Deep Learning Layers

Each Hidden layer is composed of neurons. The neurons are connected to

1.2.1 Importance of Deep Learning:

Deep learning is a powerful tool to make prediction an actionable result.

1.2.2 Deep Learning Process:

Figure 1.2 Deep Learning Process

A deep neural network provides state-of-the-art accuracy in many tasks, from

1.3.1 Local Binary Pattern Histogram(LBPH)

The steps of the algorithm:

1. Parameters: the LBPH uses 4 parameters:

You might also like