ATTENDANCE SYSTEM BASED ON FACE RECOGNITION

USING LBPH
A Project report submitted in partial fulfillment
For the Award of Degree of

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
[2019-2020]

Submitted by
B. Anusha (16A51A0506) G. Shiridi Venkata Sai (16A51A0555)
B. Radhika (16A51A0526) A. Vineeth (16A51A0502)

Under the esteemed Guidance of

Dr.B. Kameswara Rao, M. Tech, Ph. D
Assoc. Professor, Department of CSE

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

ADITYA INSTITUTE OF TECHNOLOGY AND MANAGEMENT

[Autonomous]

Approved by AICTE, Permanently Affiliated to JNTU, Kakinada,

Accredited by NBA & NACC K. Kotturu, Tekkali-532201, Srikakulam dist. (A.P)
 ADITYA INSTITUTE OF TECHNOLOGY AND MANAGEMENT
(Approved by AICTE, Permanently Affiliated to JNTU, Kakinada)
(Accredited by NBA & NAAC)
K. Kotturu, Tekkali-532201, Srikakulam dist. (A.P)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE

This is to certify that the project work entitled as “Attendance system based on Face
Recognition using LBPH” is carried out by B. Anusha (16A51A0506), G. Shiridi Venkata
Sai (16A51A0555), B. Radhika (16A51A0526), A. Vineeth (16A51A0502) submitted in
partial fulfillment for the requirements for the award of Bachelor Of Technology in
COMPUTER SCIENCE AND ENGINEERING during the year 2019-2020 to the
Jawaharlal Nehru Technological University, Kakinada is a record of bonafide work
carried out by them under my guidance and supervision.

Signature of Project Guide Signature of Head of the Department

Dr. B. Kameswara Rao, M. Tech, Ph. D, Dr. G. S. N. Murthy, M. Tech, Ph. D,
Associate Professor Head of the Department
Department of CSE. Department of CSE.
 ACKNOWLEDGEMENTS

We have great pleasure to acknowledge our sincere gratitude to our project guide Dr.B.
Kameswara Rao, Assoc.Professor of Department Computer Science and Engineering,
AITAM, Tekkali for his help and Guidance during the project. His valuable suggestions and
encouragement helped us a lot in carrying out this project work as well as in bringing this
project to this form.

We take this opportunity to express our sincere gratitude to our Director Prof. V. V.

Nageswara Rao for providing the excellent infrastructure.

We take the privilege to thank our principal Dr. A. Srinivasa Rao for his encouragement
and support.

We are also very much thankful to Dr. G.S.N. Murthy, Head of Computer Science &
Engineering for his help and valuable support in completing the project.

We are also thankful to all staff members in the Department of Computer Science and
Engineering, for their feedback in the reviews and kind help throughout our project.

Last but not the least, we thank all our classmates for their encouragement and their help in
making this project a success. There are many others who have contributed towards the
project in some manner or the other whose names could not be mentioned.

Project Team
B. Anusha (16A51A0506)
G. Shiridi Venkata Sai (16A51A0555)
B. Radhika (16A51A0526)
A. Vineeth (16A51A0502)
 DECLARATION

We hereby declare that the project titled "Attendance system based on Face Recognition
using LBPH” is a bonafide work done by us at AITAM, Tekkali Affiliated to JNTU,
Kakinada towards the partial fulfillment for the award of Degree of Bachelor of Technology
in Computer Science and Engineering during the period 2019-2020.

Project Associates
B. Anusha (16A51A0506)
G. Shiridi Venkata Sai (16A51A0555)
B. Radhika (16A51A0526)
A. Vineeth (16A51A0502)
 Program Outcomes(PO)

1. ENGINEERING KNOWLEDGE: Apply the knowledge of mathematics, science,

engineering fundamentals, and an engineering specialization to the solution of
complex engineering problems.
2. PROBLEM ANALYSIS: Identify, formulate, review research literature, and analyze
complex engineering problems reaching substantiated conclusions using first
principles of mathematics, natural sciences, and engineering sciences.
3. DESIGN/DEVELOPMENT OF SOLUTIONS: Design solutions for complex
engineering problems and design system components or processes that meet the
specified needs with appropriate consideration for the public health and safety, and
the cultural, societal, and environmental considerations.
4. CONDUCT INVESTIGATIONS OF COMPLEX PROBLEMS: Use research-
based knowledge and research methods including design of experiments, analysis and
interpretation of data, and synthesis of the information to provide valid conclusions.
5. MODERN TOOL USAGE: Create, select, and apply appropriate techniques,
resources, and modern engineering and IT tools including prediction and modeling to
complex engineering activities with an understanding of the limitations.
6. THE ENGINEER AND SOCIETY: Apply reasoning informed by the contextual
knowledge to assess societal, health, safety, legal and cultural issues and the
consequent responsibilities relevant to the professional engineering practice.
7. ENVIRONMENT AND SUSTAINABILITY: Understand the impact of the
professional engineering solutions in societal and environmental contexts, and
demonstrate the knowledge of, and need for sustainable development.
8. ETHICS: Apply ethical principles and commit to professional ethics and
responsibilities and norms of the engineering practice.
9. INDIVIDUAL AND TEAM WORK: Function effectively as an individual, and as a
member or leader in diverse teams, and in multidisciplinary settings.
10. COMMUNICATION: Communicate effectively on complex engineering activities
with the engineering community and with society at large, such as, being able to
comprehend and write effective reports and design documentation, make effective
presentations, and give and receive clear instructions.
11. PROJECT MANAGEMENT AND FINANCE: Demonstrate knowledge and
understanding of the engineering and management principles and apply these to one’s
own work, as a member and leader in a team, to manage projects and in
multidisciplinary environments.
12. LIFE-LONG LEARNING: Recognize the need for, and have the preparation and
ability to engage in independent and life-long learning in the broadest context of
technological change.
 Program Specific Outcomes

 PSO1:- Apply mathematical foundations, algorithmic principles, techniques and

theoretical computer science in the modeling and design of computer-based systems
in a way that demonstrates comprehension of the tradeoffs involved in design choices.
 PSO2:-Demonstrate understanding of the principles and working of the hardware and
software programming aspects of computer systems.
 PSO3:-Use knowledge in various domains to identify research gaps and hence to
provide solution to new ideas and innovations

PO-PSO Mapping

Project Title: “Face recognition-based attendance system”

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3

3 3 3 3 3 3 3 1 3 3 3 3 3 3 3

Area of the Project Machine Learning

Description of the project Attendance of students in a large classroom is

hard to be handled by the traditional system,
as it is time-consuming and has a high
probability of error during the process of
inputting data into the computer. Our project
proposed automated attendance marking
system using face recognition technique. The
system deployed Haar cascade classifier to
find the positive and negative of the face and
LBPH (Local binary pattern histogram)
algorithm for face recognition by using
python programming and OpenCV library.
Here we use the tkinter
GUI interface for user interface purpose.
Batch Details: Batch-11 Academic Year: 2019-2020
Roll No.:
B. Anusha (16A51A0506)
G. Shiridi Venkata Sai (16A51A0555)
B. Radhika (16A51A0526)
A. Vineeth (16A51A0502)
 ABSTRACT

STATEMENT OF PROBLEM:
Attendance of students in a large classroom is hard to be handled by the traditional system, as
it is time-consuming and has a high probability of error during the process of inputting data
into the computer. Our project proposed automated attendance marking system using face
recognition technique.
RESULT:
The system deployed Haar cascade classifier to find the positive and negative of the face and
LBPH (Local binary pattern histogram) algorithm for face recognition by using python
programming and OpenCV library. Here we use the tkinter GUI interface for user interface
purpose. Firstly, our app asks to fill the details of the student and take image of the particular
student. It takes 60 images as sample and store them in folder Training Image. After
completion it notify that images saved. After taking image sample we have to click Train
Image button. Now it takes few seconds to train machine for the images that are taken by
clicking Take Image button and creates a Trainner.yml file and store in TrainingImageLabel
folder. Now all initial setups are done. By clicking Track Image button camera of running
machine is opened again. If face is recognized by system then Id and Name of person is
shown on Image. Press Q (or q) for quit this window. The attendance of the student was
updated to the Excel sheet after student's face has been recognized.
 INDEX
TABLE OF CONTENT Page No’s

ABSTRACT i

INDEX ii

LIST OF FIGURES iv

LIST OF TABLES v
CHAPTER

1. INTRODUCTION

1.1. Introduction 2

1.2. Importance of Facial Recognition 3

2. LITERATUTRE SURVEY

2.1. Applications of Facial Recognition 9

3. REQUIREMENTS AND TECHNICAL DESCRIPTION

3.1. System Requirements 12

3.2. Technical Description 14

4. DESIGN

4.1. Objective 20

4.2. UML Diagrams 20

4.3. Use Case Diagram 22

4.4. Class Diagram 23

4.5. Sequence Diagram 23

4.6. Activity Diagram 24

5. IMPLEMENTATION 27

6. CODING 36

7. SCREENSHOTS 46

8. TESTING

8.1. Introduction 52

8.2. Testing Methodologies 53

8.3. Test Cases 54

9. CONCLUSION AND FUTURE SCOPE 56

10. BIBLIOGRPHY 58
 LIST OF FIGURES

S. No Figure No Figure Name Page No

1 3.2.1 Face detection using OpenCV 15

2 3.2.3 steps for creating tkinter GUI 17

3 4.1 Use Case Diagram 22

4 4.2 Class Diagram 23

5 4.3 Sequence Diagram 24

6 4.4 Activity Diagram 25

7 5.1 Process involved in LBPH 28

8 5.2 LBP pixel value 29

9 5.3 monotonic grey scale transformations 30

10 5.4 Feature vector of the image 31

 LIST OF TABLES

S. No Table No Table Name Page No

1 3.a Hardware used 12

2 3.b Dependencies used 12

3 3.c Software’s used 13

4 7.4 Testing 54
Attendance system based on Face Recognition using LBPH 2020

CHAPTER-1
INTRODUCTION

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 1
Attendance system based on Face Recognition using LBPH 2020

1.Introduction
1.1 Introduction
In Face Recognition based attendance management systems, the flow process starts by
being able to detect and recognize frontal faces from an input dataset present in a database. In
today’s world, it has been proven that students engage better during lectures only when there
is effective classroom control. The need for high level student engagement is very important.
An analogy can be made with that of pilots as described by Mundschenk et al (2011 p101)”
Pilots need to keep in touch with an air traffic controller, but it would be annoying and
unhelpful if they called in every 5 minutes”. In the same way students need to be
continuously engaged during lectures and one of the ways is to recognize and address them
by their names. Therefore, a system like this will improve classroom control. In my own view
based on experience, during my time as a teacher, I realized calling a student by his/her name
gives me more control of the classroom and this draws the attention of the other students in
the classroom to engage during lectures.
Face detection and recognition is not new in our society we live in. The capacity of the
human mind to recognize particular individuals is remarkable. It is amazing how the human
mind can still persist in identification of certain individuals even through the passage of time,
despite slight changes in appearance.
Anthony (2014 p1) reports that, due to the remarkable ability of the human mind to generate
near positive identification of images and facial recognition of individuals, this has drawn
considerable attention for researchers to invest time in finding algorithms that will replicate
effective face recognition on electronic systems for use by humans.
Wang et al (2015 p318) states that” the process of searching a face is called face detection.
Face detection is to search for faces with different expressions, sizes and angles in images in
possession of complicated light and background and feeds back parameters of face”.
Face recognition processes images and identifies one or more faces in an image by analyzing
patterns and them. This process uses algorithms which extracts features and compare them to
a database to find a match. comparing Furthermore, in one of most recent research, Nobel
(2017, p. 1), suggest that DNA techniques could transform facial recognition technology, by
the use of video analysis software which can be improved thanks to a completely advance in
research in DNA analysis. By so doing, camera-based surveillance systems software to
analyze DNA sequences, by treating a video as a scene that evolves the same way DNA does,
to detect and recognize human face.
Problem Definition:

This project is being carried out due to the concerns that have been highlighted on the
methods which lectures use to take attendance during lectures. The technology aims in
imparting a tremendous knowledge oriented technical innovation these days. Machine
learning is one among the interesting domain that enables the machine to train itself by
providing an appropriate output during testing by applying different learning algorithms.
Nowadays Attendance is considered as an important for both the students as well as the
teacher of an educational organization. With the advancements of the machine learning
technology the machine automatically detects the attendance performance of the students and
maintains a record of those collected data. The motivations for organizing this special section

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 2
Attendance system based on Face Recognition using LBPH 2020

were to better address the challenges of face recognition in real – world scenarios, to promote
systematic research and evaluation of promising methods and systems, to provide a snapshot
of where we in this domain, and to stimulate discussion about future directions.
In general, the attendance system of the student can be maintained in two different forms
namely,

 Manual Attendance system (MAS)

 Automated Attendance System (AAS)
Manual Student Attendance Management system is a process is a process where a
teacher concerned with the particular subject need to call the students name and mark the
attendance manually. Manual attendance may be considered as a time–consuming process or
sometimes it happens for the teacher to miss someone or students may answer multiple times
on the absence of their friends. So, the problem arises when we think about the traditional
process of taking attendance in the classroom. To solve all these issues, we go with
Automatic Attendance System.
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 becoming 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.
The Feature-based approach also known as local face recognition system, used in pointing the
key features of the face like eyes, ears, nose, mouth, etc, Whereas the brightness-based
approach also termed as the global face recognition system used in recognizing all parts of
the image.
1.2 Importance of Face Recognition System:
Importance of Face Recognition System as a Security Solution Face is considered as the most
important part of human body. Research shows that even face can speak and it has different
words for different emotions. It plays a very crucial role for interacting with people in the
society. Its covey’s people’s identity, so it can be used as a key for security solutions in many
organizations. Nowadays, face recognition system is getting increasing trend across the world
for providing extremely safe and reliable security technology. It is gaining significant
importance and attention by thousands of corporate and government organizations only
because of its high level of security and reliability. Moreover, this system is providing vast
benefits when compared to other biometric security solutions like palm print and finger print.
The system captures biometric measurements of a person from a specific distance without
interacting with the person. With its crime deterrent purpose, this system can help many
organizations to identify a person who is having any kind of criminal record or any legal
issues .thus this technology is becoming very important for numerous residential buildings
and corporate organizations .This technique is based on the ability to recognize a human face
and then compare the different features of the face with previously recorded one.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 3
Attendance system based on Face Recognition using LBPH 2020

Along with it, it is developed by having user friendly features and operations that includes
different nodal points of the face. There are approximately 80-90 unique nodal points of a
face. From these nodal points, it measures some major points like distance between the eyes,
length of the jaw line, shape of the cheek bones, depth of the eyes etc. These points are
measured by creating a code called the face print which represents the identification of the
face in the computer database.
Face recognition is the most popular system that is widely used by millions of corporate
offices for maintaining their human resources. Without any errors and faults, the system
recognizes the employees and also records their entry as well as exit time in its computer
database.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 4
Attendance system based on Face Recognition using LBPH 2020

CHAPTER-2
LITERATURE SURVEY

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 5
Attendance system based on Face Recognition using LBPH 2020

2.LITERACTURE SURVEY
In this chapter, a brief overview of studies made on face recognition will be introduced
alongside some popular face detection and recognition algorithms. This will give a general
idea of the history of systems and approaches that have been used so far.
Overview of Face Recognition:
Most face recognition systems rely on face recognition algorithms to complete the following
functional task as suggested by Shang-Hung Lin. (2000, p.2). The figure below shows a
simplified diagram from the framework for face recognition from the study suggested by
Shang-Hung Lin.

Figure: Face Detection and Recognition Flow Diagram.

From the figure, above, Face Detection or face detector will detect any given face in the
given image or input dataset. Face localization, will detect where the faces are located in the
given image/input dataset by use of bounding boxes. Face Alignment is when the system
will find a face and align landmarks such as nose, eyes, chin, and mouth for feature
extraction. Feature extraction, extracts key features such as the eyes, nose, and mouth to
undergo tracking. Feature matching and classification. Matches a face based on a trained data
set of pictures from a database of about minimum number of pictures. Face recognition, gives
a positive or negative output of a recognized face based on feature matching and
classification from a referenced facial image. Face detection is the process of locating a face
in a digital image by any special computer software build for this purpose. Feraud et al (2000
p.77) discuss face detection as to detect a face in an image means to find its position in the
image plane and its size or scale. As figure shows, the detection of a face in a digital image is
a prerequisite to any further process in face recognition or any face processing software. The

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 6
Attendance system based on Face Recognition using LBPH 2020

idea of the technology namely Student Attendance System has been implemented with a
machine learning approach. This system automatically detects the student’s performance and
maintains the student’s record like attendance. Therefore, the attendance of the student can be
made available by recognizing the face. On recognizing, the attendance details.
Automated Attendance System using Face Recognition proposes that the system is based on
face detection and detection and recognition algorithms, which is used to automatically
detects the students face he/she enters the class and the system is capable to marks the
attendance by recognizing him. The effectiveness of the pictures is also being discussed to
enable the faster recognition of the image.
The original LBP (Local binary patterns) operator was introduced by the paper of Timo
Ojala et al (2002).In paper by Md. Abdur Rahim et al. (2013), they proposed LBP to extract
both texture details and contour to represent facial images divides each facial image into
smaller regions and histogram of each region is extracted. The histograms of every region are
concatenated into a single feature vector. This feature vector is the representation of the facial
image and Chi square statistic is used to measure similarities between facial images. The
smallest window size of each region is 3 by 3. It is computed by thresholding each pixel in a
window where middle pixel is the threshold value. The neighborhood large than threshold
value is assigned to 1 whereas the neighborhood lower than threshold value is assigned to 0.
Then the resulting binary pixels will form a byte value representing center pixel.

5 4 3 1 1 1

4 3 1 Threshold 1 0

2 0 3 0 0 1

Fig:LBPOperator(Md. Abdur Rahim et.al,2013)

LBP has a few advantages which make it popular to be implemented. It has high tolerance
against the monotonic illumination changes and it is able to deal with variety of facial
expressions, image rotation and aging of persons. These overwhelming characteristics cause
LBP to be prevalent in real-time applications.
FACE RECOGNITION:
In the early 90s numerous algorithms were developed for face recognition and increase
in the need for face detection. Systems were designed to deal with video streaming. The past
few years has proven to have developed more research and systems to deal with such
challenges. Dodd, (2017 p.1) reported that in the recent Notting Hill carnival, some arrest
resulted due to trial of facial recognition systems. Hence the reason why there is still on-
going research on this system. In contrast, the 2011 London riots had just one arrest
contributed by facial recognition software out of the 4962 that took place. With the most
recent technology of facial Face recognition can be defined as the method of identifying an
individual based on biometrics by way of comparing a digital captured image with the stored
record of the person in question. Recognition and detection techniques, commercial products
have emerged on the markets. Despite the commercial success a few issues are still to be
explored.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 7
Attendance system based on Face Recognition using LBPH 2020

Jafri and Arabnia (2009) in their study discuss Face Recognition in two primary tasks.
Verification; a one-to-one matching of an unknown face alongside a claim of identity, to
ascertain the face of the individual claiming to be the one on the image. Identification which
is also a one-to-one matching, given an input image of a face for an individual (unknown), to
determine their identity by comparing the image against a database of images with known
individuals. However, Face Recognition can also be used in numerous applications such as
Security, Surveillance, General Identity Verification (electoral registration, national ID cards,
passports, driving licenses, student IDs), Criminal Justice systems, Image Database
Investigations, Smart Card, Multi-media Environments, Video Indexing and Witness face
reconstruction. Face Recognition in most common form is its frontal view which is not
unique or rigid as numerous factors cause its appearance to vary. Variations in facial
appearance has been categorized in two groups of intrinsic factors (physical nature of the face
which is independently of the observer) and extrinsic factors (illumination, pose, scale and
imaging parameters such as resolution, noise, focus, imaging) as discussed by Gong et al.
(200) and supported by Jafri and Arabnia (2009 p.42).
Lenc and Král (2014 pp.759-769) classify face recognition into various approaches;
Correlation Method, compares two images by computing the correlation between them,
with the images handled as one-dimensional vectors of intensity values. The images are
normalized to have zero mean and unit variance with the nearest neighbor classifier used in
the image directly. With these considerations stated, the light source intensity and
characteristics of the camera are suppressed. The limitations of this method are; Large
amount of memory storage needed, the corresponding points in the image space may not be
tightly clustered and it is computationally expensive.
Neural Networks; performs based on neural networks with the images sampled into a set of
vectors. The vectors created from the labeled images are used as a training set for Self-
Organized Map. In other study carried out by Dhanaseely et al. (2012), discuss the neural
Network Classifiers as an Artificial Neural Network (ANN) that comprises of artificial
neurons that uses a computational model to process information. They further conducted an
experiment based on their proposed system, to measure the performance recognition rate of
two of the neural networks, the Feed Forward Neural Network and Cascade Neural Network.
Hidden Markov Models; associated with the states of the HMM are the subdivided regions
of the face (eyes, nose, mouth etc.). the images in this method are sampled with a rectangular
window of the same width as the image and shifted downward with a specific block overlap.
This is done thanks to the representation of boundaries between regions which are
represented by probabilistic transition between the states of the HMM.
Local Binary Patterns; first used in texture as texture descriptor, the operator uses the value
of the central pixel to threshold a local image region. The pixels are labelled either as 0 or 1
depending on whether the value is lower or greater than the threshold. Linna et al. (2015) in
their study, proposed a system (Online Face Recognition System) that is based on LBP and
Facial Landmarks, which uses nearest neighbor classifier in LBP histogram matching. They
experimented the system on the videos of Honda/UCSD video database. They used both
Offline and Online testing for different distance thresholds and achieved recognition rates of
62.2%,64.0% and 98.6% respectively for the Offline test. The recognition rate was calculated
based on a confusion matrix that is shown in Figure 2.10 below, obtained as a screenshot
from this paper. The online test performed at a recognition rate of 95.9%. The high achieved
recognition rates as per their experiment is based on longer search strategy. The detected face

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 8
Attendance system based on Face Recognition using LBPH 2020

tracked, is used to find the nearest neighbor match and the number of frames from the start of
the face tracking are used in the database. This shows that the number of frames decreases as
the database gets larger and hence increase in search time. This is because more time is
needed to find the nearest match for a single frame. However, as more time is needed to find
the nearest match, although recognition rate may be high, it is still not robust enough to
compete with other methods.

2.1 Applications of face Recognition:

1. Fraud Detection for Passports and Visas
According to reports, experts using the automatic face-recognition software
in Australian Passport office are 20 percent more efficient as compared to average people
detecting fraud. An effective tool to detect fraud, face recognition is increasingly being used
to identify documents such as driving license and immigration visas.

2. ATM and Banks

China started using the first face recognition technology in the ATMs. The new
cash machine developed using this technology ensured increased security of the card user and
worked by mapping facial data, matching it against the database. As a part of the biometric
authentication, it used the data from facial features and iris recognition.

3. Identification of Criminals
An increasingly popular tool among the law enforcement agencies, face
recognition technology has significantly contributed in the domain of investigation and crime
detection. Several countries including the USA is building the facial recognition database, to
improve the quality of the investigation. According to a report released by the Center for
Privacy and Technology at Georgetown University law school, the law enforcement database
in the U.S includes 117 million individuals.

4. Prevent Fraud Voters

Face detection was used in 2000 presidential election in Mexico to prevent
duplicate voting. Several individuals had attempted to vote multiple times using different
names. The duplicate votes were prevented to a great extent, thanks to the face recognition
technology.

5. Track Attendance
Face recognition system is being used by some organization to track the
attendance of the employees. The system collects and records the facial fine points of the
employees in the database. Once the process is done, the employee only needs to look at the
camera and the attendance is automatically marked in the face recognition attendance system.

6. Keep Track ofthe Members

Several churches across the world are using face recognition technology to
keep a track of the church-goers. The places include India, Indonesia, and Portugal. The
CCTV footages of the churchgoers are matched against a database of high-resolution images
which a church has to compile on its own.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 9
Attendance system based on Face Recognition using LBPH 2020

7. Threats and Concerns

According to several civil right groups and privacy campaigners, the face
identification takes away the right of the people to remain anonymous. According to these
people, the government agencies and private companies are unwilling to accept the fact that
they should necessarily seek permission first before using data like face recognition as these
will leave people identifiable wherever they go. Not just this, all the scattered bits of data left
behind everywhere due to our digital presence can be put together to find out every minute
detail of us as a person, which may include our taste, preference, friends, habits and
movement. In Europe and Canada, the organizations will have to seek permission before
using face recognition technology.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 10
Attendance system based on Face Recognition using LBPH 2020

Chapter-3
REQUIREMENTS AND TECHNICAL DESCRIPTION

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 11
Attendance system based on Face Recognition using LBPH 2020

3.1 System Requirements

3.1.1 System Requirements

System requirements are the configuration that a system must have in order for a hardware or
software application to run smoothly and efficiently. Failure to meet these requirements can
result in installation problems or performance problems. The former may prevent a device or
application from getting installed, whereas the latter may cause a product to malfunction or
perform below expectation or even to hang or crash.

We can specify the system requirements in terms of hardware and software system
requirements. Hardware system requirements often specify the operating system version,
processor type, memory size, available disk space and additional peripherals, if any, needed.
Software system requirements, in addition to the aforementioned requirements, may also
specify additional software dependencies (e.g., libraries, driver version, framework version).

HARDWARE REQUIREMENTS:
Processor intel core i5 8th Gen

Graphics Processing Unit

(GPU) NVIDIA GEFFORCE
Random Access Memory (RAM) 4GB

Hard Disk 500GB

Table: 3.a Hardware Used

SOFTWARE DEPENDENCIES:
Requirement Version
Open CV 4.3.0
tkinter GUI 8.6
NumPy 1.18.1
pandas 1.0.3
PIL 1.1.7
Table: 3.b Dependencies Used

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 12
Attendance system based on Face Recognition using LBPH 2020

SOFTWARE REQUIREMENTS:
Operating system Windows 10
Language Python 3.6 version
Editor ANACONDA NAVIGATOR
Spyder
Design Tool Star UML

Table: 3.c Software Used

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 13
Attendance system based on Face Recognition using LBPH 2020

3.2 Technological description

The technology selected for implementing Face Recognition based attendance management
systems are open CV, python and tkinter GUI interface.

3.2.1 OpenCV:
 OpenCV (Open Source Computer Vision) is a library for computer vision that includes
numerous highly optimized algorithms that are used in Computer vision tasks.
 OpenCV supports a wide variety of programming languages such as C++, Python, Java
etc. Support for multiple platforms including Windows, Linux, and MacOS.
 OpenCV Python is nothing but a wrapper class for the original C++ library to be used
with Python. Using this, all of the OpenCV array structures gets converted to/from
NumPy arrays.
 This makes it easier to integrate it with other libraries which use NumPy. For example,
libraries such as SciPy and Matplotlib.

Basic operations of OpenCV:

 Access pixel values and modify them

 Access image properties
 Setting Region of Image (ROI)
 Splitting and Merging images
 Change an image colour

Face detection using OpenCV:

This seems complex at first but it is very easy. Let me walk you through the entire process
and you will feel the same.
Step 1: Considering our prerequisites, we will require an image, to begin with. Later we need
to create a cascade classifier which will eventually give us the features of the face.
Step 2: This step involves making use of OpenCV which will read the image and the features
file. So, at this point, there are NumPy arrays at the primary data points.
All we need to do is to search for the row and column values of the face NumPy ndarray.
This is the array with the face rectangle coordinates.
Step 3: This final step involves displaying the image with the rectangular face box.

Check out the following image,

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 14
Attendance system based on Face Recognition using LBPH 2020

Fig 3.2.1: Face detection using OpenCV

3.2.2 Python:

Python is an interpreted, object-oriented, high-level programming language with dynamic

semantics.
Its high-level built in data structures, combined with dynamic typing and dynamic binding,
make it very attractive for Rapid Application Development, as well as for use as a scripting
or glue language to connect existing components together.
The Python interpreter and the extensive standard library are available in source or binary
form without charge for all major platforms, and can be freely distributed.
Python is a multi-paradigm programming language because of we can use in Web
development, AI, ML, Data analyst, Data science and networking
Python is a popular selection for use as a scripting language for many software developments
processes. Similar to many other interpretative languages, Python provides more flexibility
than compiled languages, and it can be economically utilized to integrate disparate systems
together.
Often, programmers fall in love with Python because of the increased productivity it
provides. Since there is no compilation step, the edit-test-debug cycle is incredibly fast.
Debugging Python programs is easy: a bug or bad input will never cause a segmentation
fault. Instead, when the interpreter discovers an error, it raises an exception. When the
program doesn't catch the exception, the interpreter prints a stack trace. A source level
debugger allows inspection of local and global variables, evaluation of arbitrary expressions,
setting breakpoints, stepping through the code a line at a time, and so on. The debugger is
written in Python itself, testifying to Python's introspective power. On the other hand, often
the quickest way to debug a program is to add a few print statements to the source: the fast
edit-test-debug cycle makes this simple approach very effective.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 15
Attendance system based on Face Recognition using LBPH 2020

Python Syntax compared to other programming languages

 Python was designed for readability, and has some similarities to the English language
with influence from mathematics.
 Python uses new lines to complete a command, as opposed to other programming
languages which often use semicolons or parentheses.
 Python relies on indentation, using whitespace, to define scope; such as the scope of
loops, functions and classes. Other programming languages often use curly-brackets for
this purpose.

Python Features
Python's features include –
Easy-to-learn − Python has few keywords, simple structure, and a clearly defined
syntax. This allows the student to pick up the languagequickly.
Easy-to-read − Python code is more clearly defined and visible to the eyes.
Easy-to-maintain − Python's source code is fairly easy-to-maintain.
A broad standard library − Python's bulk of the library is very portable and cross-
platform compatible on UNIX, Windows, and Macintosh.
Interactive Mode − Python has support for an interactive mode which allows
interactive testing and debugging of snippets of code.
Programming − Python supports GUI applications that can be created and ported to
many system calls, libraries and windows systems, such as Windows MFC, Macintosh,
and the X Window system ofUnix.
Scalable − Python provides a better structure and support for large programs than shell
scripting.
Portable − Python can run on a wide variety of hardware platforms and has the same
interface on all platforms.
Extendable − You can add low-level modules to the Python interpreter. These modules
enable programmers to add to or customize their tools to be more efficient.
Databases − Python provides interfaces to all major commercial databases.

Python Indentation:
Indentation refers to the spaces at the beginning of a code line.
Where in other programming languages the indentation in code is for readability only,
the indentation in Python is very important.
Python uses indentation to indicate a block of code.
Ex: if 5>2:
print (“5 is greater than 2”)

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 16
Attendance system based on Face Recognition using LBPH 2020

Python will give you an error if you skip the indentation

Import module
Import in python is similar to #include header file in C/C++. Python modules can get
access to code from another module by importing the file/function using import. The
import statement is the most common way of invoking the import machinery, but it is
not the only way.
import module name

When import is used, it searches for the module initially in the local scope by calling
import () function. The value returned by the function are then reflected in the output of
the initial code.

Ex: import math

print (pi)

Installing and using Python on Windows 10 is very simple. The installation procedure
involves just three steps:
1. Download thebinaries
2. Run the Executableinstaller
3. Add Python to PATH environmentalvariables

To install Python, you need to download the official Python executable installer. Next,
you need to run this installer and complete the installation steps. Finally, you can
configure the PATH variable to use python from the commandline.

3.2.3 tkinter GUI interface:

Python offers multiple options for developing GUI (Graphical User Interface). Out of all the
GUI methods, tkinter is the most commonly used method. Tkinter is actually an
inbuilt Python module used to create simple GUI apps. It is the most commonly used module
for GUI apps in the Python.

Importing tkinter is same as importing any other module in the Python code.

Ex: Import tkinter

Creating a GUI using tkinter is an easy task.

Fig 3.2.3: steps for creating tkinter GUI

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 17
Attendance system based on Face Recognition using LBPH 2020

To start out with, we first import the Tkinter model. Followed by that, we create the main
window. It is in this window that we are performing operations and displaying visuals and
everything basically. Later, we add the widgets and lastly, we enter the main event loop.

There are 2 main key words used which the user needs to remember while creating interface
with this GUI. They are Widgets and main event loop.

 Widgets: Widgets are something like elements in the HTML. You will find different
types of widgets to the different types of elements in the tkinterlike buttons, labels, radio
buttons, checkbox, entry button…etc.
 Main event loop:There is a method known by the name mainloop () is used when your
application is ready to run. mainloop () is an infinite loop used to run the application, wait
for an event to occur and process the event as long as the window is not closed.

Tk (screenName=None, baseName=None, className=’Tk’, useTk=1): To create a main

window, tkinter offers a method ‘Tk (screenName=None, baseName=None,
className=’Tk’, useTk=1)’. To change the name of the window, you can change the
className to the desired one. The basic code used to create the main window of the
application is:

Ex: m=tkinter.Tk()
#where m is the name of the main window object
Sample example:

import tkinter
m = tkinter. Tk()
'''
widgets are added here
'''
m.mainloop()

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 18
Attendance system based on Face Recognition using LBPH 2020

CHAPTER-4

DESIGN

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 19
Attendance system based on Face Recognition using LBPH 2020

4.DESIGN

4.1 Objective
The overall design objective is to provide an efficient, modular design that will reduce the
system’s complexity, facilitate change and result in an easy implementation. This will be
accomplished by designing strongly cohesion system with minimal coupling. In addition, this
document will provide interface design models that are consistent, user friendly and will
provide straight forward transition through the various system functions.

The purpose of the design phase is to develop a clear understanding of what the
developer wants people to gain from his/her project. As the developer work on the project,
the test for every design decision should be “Does this feature fulfill the ultimate purpose of
the project?”. The design document will verify that the current design meets all of the explicit
requirements contained in the system model as well as the implicit requirements desired .

4.2 UML Diagrams

Unified Modelling Language (UML) is a general-purpose modelling language. The main aim
of UML is to define a standard way to visualize the way a system has been designed. It is
quite similar to blueprints used in other fields of engineering.

UML is not a programming language; it is rather a visual language. We use UML diagrams to
portray the behaviour and structure of a system. UML helps software engineers, businessmen
and system architects with modelling, design and analysis. The Object Management Group
(OMG) adopted Unified Modelling Language as a standard in 1997. It’s been managed by
OMG ever since. International Organization for Standardization (ISO) published UML as an
approved standard in 2005. UML has been revised over the years and is reviewed
periodically.

Goals of UML:

The primary goals in the design of the UML were:

1. Provide users with a ready-to-use, expressive visual modelling language so they

can develop and exchange meaningful models.
2. Provide extensibility and specialization mechanisms to extend the core concepts.
3. Be independent of particular programming languages and development processes.
4. Provide a formal basis for understanding the modelling language.
5. Support higher-level development concepts such as collaborations, frameworks,
patterns and components.
6. Integrate best practice

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 20
Attendance system based on Face Recognition using LBPH 2020

4.2.1 The conceptual model of UML

A conceptual model can be defined as a model which is made of concept and their
relationships.
A conceptual model is the first step before drawing UML diagrams. It helps to
understand the entities in the real world and how they interact with each other.
To understand how the UML works, we need to know the three elements:

1. UML basic buildingblocks

2. Rules to connect the building blocks (Rules for how these building blocks
may be put together).
3. Common mechanisms that apply throughout in theUML.

4.2.2 Types of Diagrams

UML diagrams are divided into three different categories such as,

 Structural diagram
 Behavioral diagram
 Interaction diagram

Structural diagrams

Structural diagrams are used to represent a static view of a system. It represents a part of a
system that makes up the structure of a system. A structural diagram shows various objects
within the system.

Following are the various structural diagrams in UML:

 Class diagram
 Object diagram
 Package diagram
 Component diagram
 Deployment diagram

Behavioral diagrams

Any real-world system can be represented in either a static form or a dynamic form. A system
is said to be complete if it is expressed in both the static and dynamic ways. The behavioural
diagram represents the functioning of a system.

UML diagrams that deals with the static part of a system are called structural diagrams. UML
diagrams that deals with the moving or dynamic parts of the system are called behavioural
diagrams.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 21
Attendance system based on Face Recognition using LBPH 2020

Following are the various behavioural diagrams in UML:

 Activity diagram
 Use case diagram
 State machine diagram

Interaction diagrams

Interaction diagram is nothing but a subset of behavioural diagrams. It is used to visualize the
flow between various use case elements of a system. Interaction diagrams are used to show
an interaction between two entities and how data flows within them.

Following are the various interaction diagrams in UML:

 Timing diagram
 Sequence diagram
 Collaboration diagram

4.3 Use case diagram:

Use Case Diagram captures the system's functionality and requirements by using actors and
use cases. Use Cases model the services, tasks, function that a system needs to perform. Use
cases represent high-level functionalities and how a user will handle the system. Use-cases
are the core concepts of Unified Modelling language modeling.

A Use Case consists of use cases, persons, or various things that are invoking the features
called as actors and the elements that are responsible for implementing the use cases. Use
case diagrams capture the dynamic behavior of a live system. It models how an external
entity interacts with the system to make it work. Use case diagrams are responsible for
visualizing the external things that interact with the part of the system.

Fig 5.1: Use Case Diagram

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 22
Attendance system based on Face Recognition using LBPH 2020

4.4 Class diagram:

Class diagram gives an overview of a software system by displaying classes, attributes,

operations, and their relationships. This Diagram includes the class name, attributes, and
operation in separate designated compartments.

Class Diagram defines the types of objects in the system and the different types of
relationships that exist among them. It gives a high-level view of an application. This
modelling method can run with almost all Object-Oriented Methods. A class can refer to
another class. A class can have its objects or may inherit from other classes.

Class Diagram helps construct the code for the software application development.

Fig 5.2: Class Diagram

4.5 Sequence Diagram:

UML Sequence Diagrams are interaction diagrams that detail how operations are carried
out. They capture the interaction between objects in the context of a collaboration.
Sequence Diagrams are time focus and they show the order of the interaction visually by
using the vertical axis of the diagram to represent time what messages are sent and when.

Sequence Diagrams captures:

 The interaction that takes place in a collaboration that either realizes a use case or
an operation (instance diagrams or generic diagrams)
 High-level interactions between user of the system and the system, between the
system and other systems, or between subsystems (sometimes known as system
sequence diagrams)

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 23
Attendance system based on Face Recognition using LBPH 2020

Sequence diagrams can be useful references for businesses and other organizations. Try
drawing a sequence diagram to:

 Represent the details of a UML use case.

 Model the logic of a sophisticated procedure, function, or operation.
 See how objects and components interact with each other to complete a process.
 Plan and understand the detailed functionality of an existing or future scenario.

Fig 5.3: Sequence Diagram

4.6 Activity Diagram:

Activity diagram is defined as a UML diagram that focuses on the execution and
flow of the behavior of a system instead of implementation. It is also called object-oriented
flowchart. Activity diagrams consist of activities that are made up of actions which apply to
behavioral modeling technology.

An activity diagram portrays the control flow from a start point to a finish point
showing the various decision paths that exist while the activity is being executed. We can
depict both sequential processing and concurrent processing of activities using an activity
diagram. They are used in business and process modelling where their primary use is to
depict the dynamic aspects of a system. An activity diagram is very similar to a flowchart.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 24
Attendance system based on Face Recognition using LBPH 2020

The basic usage of activity diagram is similar to other four UML diagrams. The
specific usage is to model the control flow from one activity to another. This control flow
does not include messages.
Activity diagram is suitable for modelling the activity flow of the system. An application
can have multiple systems. Activity diagram also captures these systems and describes the flow from
one system to another. This specific usage is not available in other diagrams. These systems can be
database, external queues, or any other system

Fig 5.4: Activity Diagram

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 25
Attendance system based on Face Recognition using LBPH 2020

CHAPTER-5
IMPLEMENTATION

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 26
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

5.Implementation

Methodology:
a) Local Binary Pattern Histogram (LBPH)
b) Haar Cascade Classifier
The project deployed on Haar Cascade classifier to find the positive and negative of the
face and LBPH (Local binary pattern histogram) algorithm for face recognition by using
python programming and OpenCV library.

5.1 Local Binary Pattern Histogram (LBPH):

A local binary pattern (LBP) is a type of visual descriptor used for classification in
computer vision. LBP is the particular case of the Texture Spectrum model proposed in 1990.
LBP was first described in 1994. It has since been found to be a powerful feature for texture
classification; it has further been determined that when LBP is combined with the Histogram
of oriented gradients (HOG) descriptor, it improves the detection performance considerably
on some datasets. A comparison of several improvements of the original LBP in the field of
background subtraction was made in 2015 by Silva et al. A full survey of the different
versions of LBO can be found in Bouwmans. Python mahotas, an open source computer
vision package which includes an implementation of LBPs. Open CV’s cascade classifiers
support LBPs as of version2. LBP Library is a collection of eleven local binary patterns
(LBP) algorithms developed for background subtraction problem.

In the Local Binary Patterns Histogram algorithm (LBPH) for face recognition. It is
based on local binary operator and is one of the best performing texture descriptors. The need
for facial recognition systems is increasing day by day. They are being used in entrance
control, surveillance system, Smartphone unlocking etc. In this project we will use LBPH to
extract features from an input test image and match them with the faces in system’s database.
Local Binary Pattern Histogram algorithm was proposed in 2006. It is based on local binary
operator. It is widely used in facial recognition due to its computational simplicity and
discriminative power. The steps involved to achieve this are:

 Creating dataset
 Face acquisition
 Feature extraction
 Classification
The LBPH algorithm is a part of OpenCV.

Steps:

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 27
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

Fig 5.1: Process involved in LBPH

 Suppose we have an image having dimensions N x M.

 We divide it into regions of same height and width resulting in m x m dimension for
every region.

 Local binary operator is used for every region. The LBP operator is defined in
window of 3x3.

here '(Xc,Yc)' is central pixel with intensity 'Ic'. And 'In' being the intensity of the the
neighbour pixel

 Using median pixel value as threshold, it compares a pixel to its 8 closest pixels using
this function.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 28
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

 If the value of neighbour is greater than or equal to the central value it is set as 1
otherwise it is set as 0.
 Thus, we obtain a total of 8 binary values from the 8 neighbours. 
 After combining these values, we get an 8 bit binary number which is translated to
decimal number for our convenience.
 This decimal number is called the pixel LBP value and its range is 0-255. 

Fig 5.2: LBP pixel value

 Later it was noted that a fixed neighbourhood fails to encode details varying in scale.
The algorithm was improved to use different number of radius and neighbors, now it
was known as circular LBP.

 The idea here is to align an arbitrary number of neighbors on a circle with a variable
radius. This way the following neighborhoods are captured: 

 For a given point (Xc, Yc) the position of the neighbour (Xp, Yp), p belonging to P
can be calculated by:

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 29
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

here R is radius of the circle and P is the number of sample points.

 If a point coordinate on the circle doesn’t correspond to image coordinates, it gets

interpolated generally by bilinear interpolation: 

 The LBP operator is robust against monotonic gray scale transformations. 

Fig 5.3: monotonic grey scale transformations

 After the generation of LBP value histogram of the region is created by counting the
number of similar LBP values in the region. 

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 30
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

 After creation of histogram for each region all the histograms are merged to form a
single histogram and this is known as feature vector of the image. 

Fig 5.4: Feature vector of the image

 Now we compare the histograms of the test image and the images in the database and
then we return the image with the closest histogram.
( This can be done using many techniques like Euclidean distance, chi-square,
absolute value etc)
 The Euclidean distance is calculated by comparing the test image features with
features stored in the dataset. The minimum distance between test and original image
gives the matching rate.

 As an output we get an ID of the image from the database if the test image is
recognised.
LBPH can recognise both side and front faces and it is not affected by illumination variations
which means that it is more flexible.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 31
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

Implementation:
The dataset can be created by taking images from webcam or from saved images. We will
take many samples of a single person. A unique ID or a name is a given to a person in the
database.

#import the necessary libraries

Import cv2

Import OS

 Creating LBPH model and training it with the prepared data

model = cv. face. Create LBPH Face Recognizer ()
model. train (faces, np. array (labels))
 Testing the trained model using a test image
def predict_image (test_image)
img = test_image. Copy ()
face, bounding_ box = face_detection (img)
label = model. Predict (face)
label_text = database [label-1]
print (label)
print (label_text)
(x, y, w, h) = bounding_box
cv2.rectangle (img, (x, y), (x + w, y + h), (0,255, 0), 2)
cv2.Font_HERSHEY_PLAIN, 1.5, (0, 255, 0), 2)
Return img
test1 = cv2. imread (“test/tom.jpg”)
predict1 =predict_image (test1)
cv2.imshow (‘Face Recognition’, predict1)
cv2.waitkey (0)
cv2.destroyAllWindows ()
Advantages of LBPH Algorithm:

 It can represent local features in the images.

 LBPH can recognize both side and front faces.
 LBPH method will probably work better on our training and testing dataset.
 Raw intensity data are used directly for learning and recognition without any significant
low -level or mid-level processing.
 Data compression is achieved by the low-dimensional subspace representation.
 Recognition is simple and efficient compared to other matching approaches.
 No knowledge of geometry and reflectance of faces are required.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 32
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

5.2 Haar Cascade:

Haar Cascade is a machine learning object detection algorithm used to identify objects in an
image or video and based on the concept of features proposed by Paul Viola and Michael
Jones in their paper “Rapid Object Detection using a Boosted Cascade of simple Features in
2001. It is a machine learning based approach where a cascade function is trained from a lot
of positive and negative image. It is then used to detect objects in their images. Luckily,
OpenCV offers predefined Haar Cascade algorithm, organized into categories depending on
the images they have been trained on.

Now let’s see how this algorithm concretely works. The idea of Haar Cascade is
extracting features from images using a kind of ‘filter’, similar to the concept of the
convolutional kernel. These filters are called Haar features.

Algorithm:

import numpy as np

import cv2

face_cascade = cv2. Cascade Classifier (“haarcascade_frontalface_default. Xml”)

eye_cascade =cv2.CascadeClassifier (1’haarcascade_eye.xml”)

img = cv2. imread (“image .jpg”)

gray =cv2. CvtColor (img, cv2.COLOR_BGR2GRAY)

faces = face_cascade. detectMultiScale (gray, 1.3, 5)

for (x, y, w, h) in faces:

img = cv2.rectangle (img, (x, y), (x+w, y+h), (255, 0, 0), 2)

roi_gray = gray [y: y+h, x: x+w]

roi_color = img[y: y+h, x: x=w]

eyes = eye_cascade.detectMultiScale (roi_gray)

for (ex, ey, ew, eh) in eyes:

cv2.rectangle (roi_color, (ex, ey), (ex+ew, ey+eh), (0, 255, 0), 2)

cv2 .imshow (‘img’, img)

cv2.Waitkey (0)

cv2.destroyAllWindows ()

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 33
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

Initially, the algorithm needs a lot of positive images of faces and negative images
without faces to train the classifier. Then we need to extract features from it. First step is to
collect the Haar features.

 Haar Feature Selection

 Creating Integral images
 Adaboost Training
 Cascading Classifiers
As you can see, our algorithm worked pretty well! If you explore the whole library of Haar
Cascade algorithm, you will see that their specific models improve trained on different
features of the human’s physical aspect, hence you can your model by adding more features
detection.

But among all these features we calculated, most of them are irrelevant. For example,
consider the image. Top row shows two good features. The first feature selected seems to
focus on the property that the region of the eyes is often darker than the region of the nose
and cheeks. The second feature selected relies on the property that the eyes are darker than
the bridge of the nose. But the same windows applying on cheeks or any other place is
irrevalant. So how do we select the best features out of 160000+ features? It is achieved by
Adaboost.

For this, we can apply each and every feature on all the training images. For each feature, it
finds the best threshold which will classify the faces to positive and negative. But obviously,
there will be errors rate misclassifications. We select the features with minimum error rate,
which means they are the features that best classifies the face and non-face images.

Haar Cascade classifier is based on the Haar Wavelet technique to analyze pixels in the
images into squares by function. This uses “integral images” concepts to compute the”
features” detected. Haar Cascades use the Adaboost learning algorithm which selects a small
number of important features from a large to give an efficient result of classifiers then use
cascading techniques to detect face in an image. Haar Cascade classifier is based on Viola
Jones detection algorithm which is trained in given some input faces and non-faces and
training a classifier which identifies a face. Viola Jones face detection algorithm is trained
and weights are stored in the disk. All we do is take the features from the file and apply to our
image; it faces is present in the image we get the face location.

A Haar Cascade is basically a classifier which is used to detect the object for which it has
been trained for, from the source. Better results are obtained by using high quality images and
increasing the amount of stages for which the classifier is trained. So, face recognition can be
made done easy representing by using haar cascade classifier algorithm.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 34
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

CHAPTER-6
CODING

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 35
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

Train.py
import tkinter as tk

from tkinter import Message, Text

import cv2, os

import shutil

import csv

import numpy as np

from PIL import Image, ImageTk

import pandas as pd

import datetime

import time

import tkinter.ttk as ttk

import tkinter.font as font

window = tk.Tk()

#helv36 = tk.Font(family='Helvetica', size=36, weight='bold')

window.title("Face_Recogniser")

dialog_title = 'QUIT'

dialog_text = 'Are you sure?'

#answer = messagebox.askquestion(dialog_title, dialog_text)

#window.geometry('1280x720')

window.configure(background='blue')

#window.attributes('-fullscreen', True)

window.grid_rowconfigure(0, weight=1)

window.grid_columnconfigure(0, weight=1)

#path = "profile.jpg"

#Creates a Tkinter-compatible photo image, which can be used everywhere Tkinter expects an image object.

#img = ImageTk.PhotoImage(Image.open(path))

#The Label widget is a standard Tkinter widget used to display a text or image on the screen.

#panel = tk.Label(window, image = img)

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 36
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
#panel.pack(side = "left", fill = "y", expand = "no")

#cv_img = cv2.imread("img541.jpg")

#x, y, no_channels = cv_img.shape

#canvas = tk.Canvas(window, width = x, height =y)

#canvas.pack(side="left")

#photo = PIL.ImageTk.PhotoImage(image = PIL.Image.fromarray(cv_img))

# Add a PhotoImage to the Canvas

#canvas.create_image(0, 0, image=photo, anchor=tk.NW)

#msg = Message(window, text='Hello, world!')

# Font is a tuple of (font_family, size_in_points, style_modifier_string)

message = tk.Label(window, text="Face-Recognition-Based-Attendance-Management-System" ,bg="Green"

,fg="white" ,width=50 ,height=3,font=('times', 30, 'italic bold underline'))

message.place(x=200, y=20)

lbl = tk.Label(window, text="Enter ID",width=20 ,height=2 ,fg="red" ,bg="yellow" ,font=('times', 15, ' bold ')
)

lbl.place(x=400, y=200)

txt = tk.Entry(window,width=20 ,bg="yellow" ,fg="red",font=('times', 15, ' bold '))

txt.place(x=700, y=215)

lbl2 = tk.Label(window, text="Enter Name",width=20 ,fg="red" ,bg="yellow" ,height=2 ,font=('times', 15, '
bold '))

lbl2.place(x=400, y=300)

txt2 = tk.Entry(window,width=20 ,bg="yellow" ,fg="red",font=('times', 15, ' bold ') )

txt2.place(x=700, y=315)

lbl3 = tk.Label(window, text="Notification : ",width=20 ,fg="red" ,bg="yellow" ,height=2 ,font=('times', 15, '
bold underline '))

lbl3.place(x=400, y=400)

message = tk.Label(window, text="" ,bg="yellow" ,fg="red" ,width=30 ,height=2, activebackground =

"yellow" ,font=('times', 15, ' bold '))

message.place(x=700, y=400)

lbl3 = tk.Label(window, text="Attendance : ",width=20 ,fg="red" ,bg="yellow" ,height=2 ,font=('times', 15, '
bold underline'))

lbl3.place(x=400, y=650)

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 37
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
message2 = tk.Label(window, text="" ,fg="red" ,bg="yellow",activeforeground = "green",width=30 ,height=2
,font=('times', 15, ' bold '))

message2.place(x=700, y=650)

def clear():

txt.delete(0, 'end')

res = ""

message.configure(text= res)

def clear2():

txt2.delete(0, 'end')

res = ""

message.configure(text= res)

def is_number(s):

try:

float(s)

return True

except ValueError:

pass

try:

import unicodedata

unicodedata.numeric(s)

return True

except (TypeError, ValueError):

pass

return False

def TakeImages():

Id=(txt.get())

name=(txt2.get())

if(is_number(Id) and name.isalpha()):

cam = cv2.VideoCapture(0)

harcascadePath = "haarcascade_frontalface_default.xml"

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 38
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
detector=cv2.CascadeClassifier(harcascadePath)

sampleNum=0

while (True):

ret, img = cam.read()

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

faces = detector.detectMultiScale(gray, 1.3, 5)

for (x,y,w,h) in faces:

cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)

#incrementing sample number

sampleNum=sampleNum+1

#saving the captured face in the dataset folder TrainingImage

cv2.imwrite("TrainingImage\ "+name +"."+Id +'.'+ str(sampleNum) + ".jpg", gray[y:y+h,x:x+w])

#display the frame

cv2.imshow('frame',img)

#wait for 100 miliseconds

if cv2.waitKey(100) & 0xFF == ord('q'):

break

# break if the sample number is morethan 100

elifsampleNum>60:

break

cam.release()

cv2.destroyAllWindows()

res = "Images Saved for ID : " + Id +" Name : "+ name

row = [Id , name]

with open('StudentDetails\StudentDetails.csv','a+') as csvFile:

writer = csv.writer(csvFile)

writer.writerow(row)

csvFile.close()

message.configure(text= res)

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 39
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
else:

if(is_number(Id)):

res = "Enter Alphabetical Name"

message.configure(text= res)

if(name.isalpha()):

res = "Enter Numeric Id"

message.configure(text= res)

def TrainImages():

recognizer = cv2.face_LBPHFaceRecognizer.create()#recognizer =
cv2.face.LBPHFaceRecognizer_create()#$cv2.createLBPHFaceRecognizer()

harcascadePath = "haarcascade_frontalface_default.xml"

detector =cv2.CascadeClassifier(harcascadePath)

faces,Id = getImagesAndLabels("TrainingImage")

recognizer.train(faces, np.array(Id))

recognizer.save("TrainingImageLabel\Trainner.yml")

res = "Image Trained"#+",".join(str(f) for f in Id)

message.configure(text= res)

def getImagesAndLabels(path):

#get the path of all the files in the folder

imagePaths=[os.path.join(path,f) for f in os.listdir(path)]

#print(imagePaths)

#create empth face list

faces=[]

#create empty ID list

Ids=[]

#now looping through all the image paths and loading the Ids and the images

for imagePath in imagePaths:

#loading the image and converting it to gray scale

pilImage=Image.open(imagePath).convert('L')

#Now we are converting the PIL image into numpy array

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 40
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
imageNp=np.array(pilImage,'uint8')

#getting the Id from the image

Id=int(os.path.split(imagePath)[-1].split(".")[1])

# extract the face from the training image sample

faces.append(imageNp)

Ids.append(Id)

return faces,Ids

def TrackImages():

recognizer = cv2.face.LBPHFaceRecognizer_create()#cv2.createLBPHFaceRecognizer()

recognizer.read("TrainingImageLabel\Trainner.yml")

harcascadePath = "haarcascade_frontalface_default.xml"

faceCascade = cv2.CascadeClassifier(harcascadePath);

df=pd.read_csv("StudentDetails\StudentDetails.csv")

cam = cv2.VideoCapture(0)

font = cv2.FONT_HERSHEY_SIMPLEX

col_names = ['Id','Name','Date','Time']

attendance = pd.DataFrame(columns = col_names)

while True:

ret, im =cam.read()

gray=cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)

faces=faceCascade.detectMultiScale(gray, 1.2,5)

for(x,y,w,h) in faces:

cv2.rectangle(im,(x,y),(x+w,y+h),(225,0,0),2)

Id, conf = recognizer.predict(gray[y:y+h,x:x+w])

if(conf < 50):

ts = time.time()

date = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d')

timeStamp = datetime.datetime.fromtimestamp(ts).strftime('%H:%M:%S')

aa=df.loc[df['Id'] == Id]['Name'].values

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 41
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
tt=str(Id)+"-"+aa

attendance.loc[len(attendance)] = [Id,aa,date,timeStamp]

else:

Id='Unknown'

tt=str(Id)

if(conf > 75):

noOfFile=len(os.listdir("ImagesUnknown"))+1

cv2.imwrite("ImagesUnknown\Image"+str(noOfFile) + ".jpg", im[y:y+h,x:x+w])

cv2.putText(im,str(tt),(x,y+h), font, 1,(255,255,255),2)

attendance=attendance.drop_duplicates(subset=['Id'],keep='first')

cv2.imshow('im',im)

if (cv2.waitKey(1)==ord('q')):

break

ts = time.time()

date = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d')

timeStamp = datetime.datetime.fromtimestamp(ts).strftime('%H:%M:%S')

Hour,Minute,Second=timeStamp.split(":")

fileName="Attendance\Attendance_"+date+"_"+Hour+"-"+Minute+"-"+Second+".csv"

attendance.to_csv(fileName,index=False)

cam.release()

cv2.destroyAllWindows()

#print(attendance)

res=attendance

message2.configure(text= res)

clearButton = tk.Button(window, text="Clear", command=clear ,fg="red" ,bg="yellow" ,width=20 ,height=2

,activebackground = "Red" ,font=('times', 15, ' bold '))

clearButton.place(x=950, y=200)

clearButton2 = tk.Button(window, text="Clear", command=clear2 ,fg="red" ,bg="yellow" ,width=20

,height=2, activebackground = "Red" ,font=('times', 15, ' bold '))

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 42
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
clearButton2.place(x=950, y=300)

takeImg = tk.Button(window, text="Take Images", command=TakeImages ,fg="red" ,bg="yellow" ,width=20

,height=3, activebackground = "Red" ,font=('times', 15, ' bold '))

takeImg.place(x=200, y=500)

trainImg = tk.Button(window, text="Train Images", command=TrainImages ,fg="red" ,bg="yellow"

,width=20 ,height=3, activebackground = "Red" ,font=('times', 15, ' bold '))

trainImg.place(x=500, y=500)

trackImg = tk.Button(window, text="Track Images", command=TrackImages ,fg="red" ,bg="yellow"

,width=20 ,height=3, activebackground = "Red" ,font=('times', 15, ' bold '))

trackImg.place(x=800, y=500)

quitWindow = tk.Button(window, text="Quit", command=window.destroy ,fg="red" ,bg="yellow" ,width=20

,height=3, activebackground = "Red" ,font=('times', 15, ' bold '))

quitWindow.place(x=1100, y=500)

copyWrite = tk.Text(window, background=window.cget("background"), borderwidth=0,font=('times', 30, 'italic

bold underline'))

copyWrite.tag_configure("superscript", offset=10)

copyWrite.insert("insert", "Developed by Ashish","", "TEAM", "superscript")

copyWrite.configure(state="disabled",fg="red" )

copyWrite.pack(side="left")

copyWrite.place(x=800, y=750)

window.mainloop()

Setup.py
from cx_Freeze import setup, Executable

import sys,os

PYTHON_INSTALL_DIR = os.path.dirname(os.path.dirname(os. file ))

os.environ['TCL_LIBRARY'] = os.path.join(PYTHON_INSTALL_DIR, 'tcl', 'tcl8.6')

os.environ['TK_LIBRARY'] = os.path.join(PYTHON_INSTALL_DIR, 'tcl', 'tk8.6')

base = None

if sys.platform == 'win32':

base = None

executables = [Executable("train.py", base=base)]

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 43
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH
packages = ["idna","os","sys","cx_Freeze","tkinter","cv2","setup",

"numpy","PIL","pandas","datetime","time"]

options = {

'build_exe': {

'packages':packages,

},

setup(

name = "ToolBox",

options = options,

version = "0.0.1",

description = 'Vision ToolBox',

executables = executables

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 44
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

Chapter-7

SCREENSHOTS

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 45
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

1) Front view (GUI):

2) Capturing the image of student

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 46
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

3) After capturing the image. Images are stored in Training Image folder.

4) After completion of process. It shows the notification i.e., image saved for particular
student with id and name

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 47
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

5) Clicking
on Train image button, it displays a notification message like “Image
Trained”(means images of the detected face)

6) On clicking the track image button, it recognizes the face (which is already trained) and
displays the name and id of the particular person.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 48
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

7) On clicking quit button, attendance is updated and shown in the attendance bar as well as
kernel console.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 49
Attendance system based on Face Recognition using LBPH 2020
Recognition using LBPH

8) After recognizing the face, attendance of particular student is updated in the attendance
folder

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 50
Attendance system based on Face Recognition using LBPH 2020

Chapter-8
TESTING

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 51
 Attendance system based on Face Recognition using LBPH 2020

8.TESTING
8.1 Introduction
Once source code has been generated, software must be tested to uncover (and correct) as
many errors as possible before delivery to customer. Our goal is to design a series of test
cases that have a high likelihood of finding errors. To uncover the errors software techniques
are used. These techniques provide systematic guidance for designing test that
(1) Exercise the internal logic of software components and
(2) Exercise the input and output domains of the program to uncover errors in
program function, behavior and performance
Steps:
Software is tested from two different perspectives:
(1) Internal program logic is exercised using ―White box test case
design Techniques.
(2) Software requirements are exercised using ―block box testcase
Design techniques. In both cases, the intent is to find the maximum number of errors with
the Minimum amount of effort and time.
Testing should be made at every level of performing the task. By making testing we can
know what our mistakes are. So, testing should be done and it is very primary aspect. There
are different types of testing methods. These testing methods were divided into two types.
1. White box testing
2. Black box testing
1. White Box Testing
White box testing requires access to the source code. White box testing requires
knowing what makes software secure or insecure, how to think like an attacker, and how to
use different testing tools and techniques. The first step in white box testing is to comprehend
and analyze source code, so knowing what makes software secure is a fundamental
requirement. Second, to create tests that exploit software, a tester must think like an attacker.
Third, to perform testing effectively, testers need to know the different tools and techniques
available for white box testing.
In this testing only the output is checked for correctness. The logical flow of the data
is not checked. In my project. I tested the source code, in that all independent paths have been
executed. And all loops at their boundaries and within their operational.

2. Black Box Testing

Black box testing treats the software as a “black box”, examining functionality without
any knowledge of internal implementation. The tester is only aware of what the software is
supposed to do, not how it does. Black box testing methods include: equivalence partitioning,
boundary value analysis, all-pairs testing, state transition tables, decision table testing, fuzz
testing, model-based testing, use case testing, exploratory testing and specification-based
testing.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 52
Attendance system based on Face Recognition using LBPH 2020

8.2 Testing Methodologies:

A strategy for software testing must accommodate low-level tests that are necessary to verify
that a small source code segment has been correctly implemented as well as high-level tests
that validate major system functions against customer requirements. A strategy must provide
guidance for the practitioner and a set of milestones for the manager. Because the steps of the
test strategy occur at a time when deadline pressure begins to rise, progress must be
measurable and problems must surface as early as possible. Following testing techniques are
well known and the same strategy is adopted during this project testing.

Unit testing:
Unit testing focuses verification effort on the smallest unit of software design- the software
component or module. The unit test is white-box oriented. The unit testing implemented in
every module of student attendance management System. by giving correct manual input to
the system, the data are stored in database and retrieved. If you want required module to
access input or get the output from the End user. any error will accrue the time will provide
handler to show what type of error will accrued.

System testing:
System testing is actually a series of different tests whose primary purpose is to fully
exercise the computer-based system. Below we have described the two types of testing
which have been taken for this project. it is to check all modules worked on input basis. If
you want change any values or inputs will change all information. so specified input is must.

8.3 Test cases

Test case is an object for execution for other modules in the architecture does not represent
any interaction by itself. A test case is a set of sequential steps to execute a test operating on a
set of predefined inputs to produce certain expected outputs. There are two types of test cases:
- Manual and automated.
A manual test case is executed manually while an automated test case is executed using
automation. In system testing, test data should cover the possible values of each parameter
based on the requirements. Since testing every value is impractical, a few values should be
chosen from each equivalence class. An equivalence class is a set of values that should all be
treated the same. Ideally, test cases that check error conditions are written separately from the
functional test cases and should have steps to verify the error messages and logs.
Realistically, if functional test cases are not yet written, it is ok for testers to check for error
conditions when performing normal functional test cases. It should be clear which test data, if
any is expected to trigger errors.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 53
Attendance system based on Face Recognition using LBPH 2020

Test cases:

S.NO TEST CASE EXPECTED ACTUAL RESULT

DESCRIPTION VALUE VALUE

Camera opens after

clicking the take
1 Camera is Camera is opened Pass
image button.
opened
After opening After opening the
the camera, camera, image is
2 Capturing of image Pass
image is captured
captured

Notification
message showed in
3 Notification is Notification is Pass
the notification bar
showed showed
after capturing the
image
Check whether id Details are Details are stored
and name are stored stored in the in the CSV file
4 Pass
in Students Details CSV file (Students Details)
file. (Students
Details)
Checking of image
samples are stored in
5 Images are Images are stored Pass
Training image
stored
folder

check the images Images are Images are trained

trained or not after trained and a and a notification
6
clicking train image notification message is
button message is displayed on the Pass
displayed on Notification bar
the
Notification
bar
Check whether the
camera opens after
7 Camera is Camera is opened Pass
clicking the track
opened
image button

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 54
Attendance system based on Face Recognition using LBPH 2020

Check whether Attendance is Attendance is

attendance stored in stored stored
8 Pass
the attendance folder
after quitting.
Detecting multiple Multiple faces Multiple faces are
faces at once are detected detected
9 Pass

Update attendance Update Attendance is

for multiple people attendance for updated for only
10 Fail
at once all faces are some persons
detected
Check whether the Name and id Name and id of
camera recognizes of the the recognized
11 Pass
the detected faces or recognized person is
not person is displayed
displayed
Check whether space is Either of the two
space and special allowed but no are not allowed
12 Fail
character symbols special while entering the
are allowed while characters are name
entering the name of allowed while
the student entering the
name

Table No:8.3

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 55
Attendance system based on Face Recognition using LBPH 2020

Chapter-9
CONCLUSION AND FUTURE SCOPE

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 56
 Attendance system based on Face Recognition using LBPH 2020

9. CONCLUSION AND FUTURE SCOPE

9.1 Conclusion:
Thus, the aim of our project is to capture the images of the students, convert it into frames,
relate it with the database to ensure their presence or absence, mark attendance to the
particular student to maintain the record. The Automated face Recognition Attendance
System helps in increasing the accuracy and speed ultimately achieve the high-precision real-
time attendance to meet the need for automatic classroom evaluation. This system is designed
to minimize the human effort for taking the attendance manually that take place in every
college. As the attendance marking process is done without any human interference, which is
the main scope in the system.

9.2 Future scope:

Besides, we can simplify the system and make more efficient by taking advantage of multiple
face detections to mark attendance of all the visible faces in single attempt. This will be
economical and more efficient use of face recognition for attendance marking. We also
consider to develop an android application for this system in near future.

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 57
Attendance system based on Face Recognition using LBPH 2020

CHAPTER – 10
BIBLIOGRAPHY

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 58
 Attendance system based on Face Recognition using LBPH 2020

10. BIBLIOGRAPHY
1. Machine learning based approach for Face Recognition based Attendance System by
Shubhobrata Bhattacharya, Gowtham Sandeep Nainala, Prosenjit Das and
AurobindaRoutray.

Weblinks:
1. https://towardsdatascience.com/computer-vision-detecting-objects-using-haar-
cascade-classifier-4585472829a9
2. https://iq.opengenus.org/lbph-algorithm-for-face-recognition/

3. https://github.com/ashishdubey10/Face-Recognition-Based-Attendance-
System/blob/master/haarcascade_frontalface_default.xml
4. https://www.edureka.co/blog/python-opencv-tutorial/
5. https://www.edureka.co/blog/tkinter-tutorial/

Dept.ofCSE,AITAM,Tekkali.[Autonomous] Page 59
www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

ATTENDANCE SYSTEM BASED ON FACE

RECOGNITION USING LBPH
1
Dr.B.Kameswara Rao, 2Anusha Baratam, 3Gudla Shiridi Venkata Sai, 4 B.Radhika, 5 A.Vineeth
1
Associate Professor, 2 U.G.Student, 3 U.G.Student, 4 U.G.Student, 5 U.G.Student
1, 2,3,4,5
Department of Computer Science and Engineering,
Aditya Institute Of Technology And Management, Srikakulam, India

Abstract:

In the traditional system, it is hard to be handle the attendance of huge students in a classroom. As it is time-consuming and has a
high probability of error during the process of inputting data into the computer. Real-Time Face Recognition is a real-world
solution which comes with day to day activities of handling a bulk of student’s attendance. Face Recognition is a process of
recognizing the students face for taking attendance by using face biometrics. In this project, a computer system will be able to
find and recognize human faces fast that are being captured through a surveillance camera. Numerous algorithms and techniques
have been developed for improving the performance of face recognition but our proposed system uses Haar cascade classifier to
find the positive and negative of the face and LBPH (Local binary pattern histogram) algorithm for face recognition by using
python programming and OpenCV library. Here we use the tkinter GUI interface for user interface purpose.

Keywords: - Haar cascade classifier, LBPH algoritham

I. INTRODUCTION

The technology aims in imparting tremendous knowledge oriented technical innovations these days. Machine Learning
is one among the interesting domain that enables the machine to train itself by providing some datasets as input and provides an
appropriate output during testing by applying different learning algorithms. Nowadays Attendance is considered as an important
factor for both the student and the teacher of an educational organization. With the advancement of the Machine learning
technology the machine automatically detects the attendance performance of the students and maintains a record of those
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). Manual Student Attendance Management system is a process
where a teacher concerned with the particular subject need to call the students name and mark the attendance manually. Manual
attendance may be considered as a time-consuming process or sometimes it happens for the teacher to miss someone, or students
may answer multiple times on the absence of their friends. So, the problem arises when we think about the traditional process of
taking attendance in the classroom. To solve all these issues, we go with Automatic Attendance System (AAS). There are so
many advantages using this technology. Some of them are as follows –

 Automation simplifies time tracking, and there is no need to have personnel to monitor the system 24 hours a day. With
automated systems, human error is eliminated.
 A time and attendance system using facial recognition technology can accurately report attendance, absence, and
overtime with an identification process that is fast as well as accurate.
 Facial recognition software can accurately track time and attendance without any human error
 Facial biometric time tracking allows you to not only track employees but also add visitors to the system so they can be
tracked throughout the worksite.

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 25

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

1.1 Drawbacks of various Attendance systems:

Types of the Attendance systems Drawback

RFID-based Fraudulent usage

Time consuming for students to wait and give their

Fingerprint-based attendance

Iris-based Invades the privacy of the user

Wireless-based Poor performance if topography is bad

There are two phases in Face Recognition Based Attendance System: -

1.2 Face Detection:

Face Detection is a method of detecting faces in the images. It is the first and essential step needed for face recognition. It mainly
comes under object detection like for example car in an image or any face in an image and can use in many areas such as security,
bio-metrics, law enforcement, entertainment, personal safety, etc.

1.3 Face Recognition:

Face Recognition is a method of identifying or verifying a person from images and videos that are captured through a camera. Its
Key role is to identify people in photos, video, or in real-time.

II. LITERATURE SURVEY

There were many approaches used for dealing with disparity in images subject to illumination changes and these
approaches were implemented in object recognition systems and also by systems that were specific to faces. Some of the
approaches as follows: -

A method for coping with such variations was using gray-level information to extract a face or an object from shading approach
[1]. The more reason gray scale representations are used for extracting descriptors instead of operating on color images directly
and also gray scale simplifies the algorithm and reduces computational requirements. Here in our case, color is of limited benefit
and introducing unnecessary information could increase the number of coaching data required to attain good performance [2].
Being an ill-posed problem, these proposed solutions assumed either the item shape and reluctance properties or the illumination
conditions [3]. These assumptions made are too strict for general beholding, and so, it didn’t persuade be sufficient for face
recognition.

The second approach is the edge map [4] of the image which could be a useful object representation feature that's insensitive to
illumination changes to certain event. Edge images might be used for recognition and to realize similar accuracy as gray level
pictures. The edge map information approach owns the advantage of feature-based approaches, like invariance to illumination and
low memory requirement. It integrates the structural information with spatial information of a face image which can be done by
grouping pixels of face edge map to line segments. After thinning the edge map, a polygonal line fitting process is applied to
come back up with the edge map of a face [5] [6] [7] There is one another approach through which the image disparities because
of illumination differences are handled; it's by employing a model of several images [8] of the identical face which is taken under
various illumination conditions. During this kind of approach, the pictures captured may be used as independent models or as a
combined model-based recognition system [9] [10].

Smart Attendance Monitoring System: A Face Recognition based Attendance System for Classroom Environment [11] proposed
an attendance system that overcomes the problem of the manual method of existing system. It is face recognition method to take
the attendance. The system even captures the facial expression lighting and pose of the person for taking attendance.

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 26

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

Class Room Attendance System using the automatic face recognition System [12] a replacement approach a3D facial model
introduced to spot a student's face recognition within a classroom, which can be used for the attendance system. Using these
analytical researches will help to produce student's recognition in automated attendance system. It recognizes face from images or
videos stream for record their attendance to gauge their performance.

RFID based attendance system is used to record attendance, need to place RFID [13]and ID card on the card reader based on the
RFID based attendance to save the recorded attendance from the database and connect the system to the computer, here RS232 is
used. The problem of fraudulent access is going to be rise from this method. For instance, someone like every hacker will
authorize using ID card and enters into the organization.

III. METHODOLOGY

 Haar Cascade Classifier

 Local Binary Patterns Histogram

These two methodologies come under OpenCV. OpenCV comes with a trainer and as well as a detector. So, if you want to train
your classifier for any object then you can use this classifier called Haar Cascade Classifier.

3.1 Haar Cascade Classifier:

Detecting objects with the help of Haar cascade classifiers is an effective method proposed by Paul Viola and Michael
Jones in their paper, "Rapid Object Detection using a Boosted Cascade of Simple Features" in 2001. Object Detection comes
under machine learning based approach where a cascade function is trained from lots of positive and negative images.

Now what are these positive and negative images?

A classifier (namely cascade of boosted classifiers working with haar like features) which is trained with many samples of a
specific object (i.e., a face or a car), called positive example. So, whatever you want to detect if you train your classifier with
those kinds of values. For example, if you want to detect face then you need to train your classifier with number of images which
contain faces. So, these are called positive images which contain the object which you want to detect.

Similarly, we want to train the classifier with negative images that means the images which doesn’t contain object that you want
to detect. For example, if we want to detect the face then the image which doesn’t contain the face is called negative image. In the
same way if the image contains face or number of faces then it is called positive images.

After a classifier is trained it can be applied to the region of interest in an input image and classifier outputs 1 if the region is
likely to show the object or 0 otherwise.

Here we will work with face detection. Initially, in order to train the classifier, the cascade function needs a lot of positive images
(images which contains faces) and negative images (images without faces). Then we need to extract features from it. For this, we
use Haar features shown in the below image are used. They are just like our convolutional kernel. Each feature is claimed to be
one value which is obtained by subtracting the sum of pixels under the white rectangle from the sum of pixels under the black
rectangle.

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 27

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

Now to calculate lots of features, all possible sizes and locations of each kernel are used. (Just imagine how much computation it
needs? Even a 24x24 window results over 160000 features). In order to calculate each feature, we need to find the sum of the
pixels under white and black rectangles. To get over from it, they introduced the integral image. Calculation depends upon the
size of the image if How large your image, it reduces the calculations for a given pixel to an operation involving just four pixels.
Nice, isn't it? It makes things super-fast.

But among all these features most of them are irrelevant that we calculated. For example, consider the image below. The top row
shows two good features. In the first feature it focuses on the region of the eyes which is commonly darker than the region of the
nose and cheeks. When comes to the second feature it focuses on the property that the eyes are often darker than the bridge of the
nose. But if it is applied to cheeks or any other place is irrelevant that you can observe in the image. By using Adaboost we select
the best features out of 160000+ features.

In the same way, we have to apply each and every feature on all the training images. It finds the best threshold for each and every
feature which will classify the faces to positive and negative. Obviously, there will be errors or misclassifications. We only select
the features with minimum error rate because they are the features that most accurately classify the face and non-face images.
(The process is not as simple as this. Each and every image is given an equal weight in the beginning. After each classification,
there will be a change in weights in which weights of misclassified images are increased. Then the same process is done again.
New error rates and new weights are calculated. The process will be continued until the required accuracy or error rate is achieved
or the required number of features is found).

The final classifier is obtained by weighted sum of these weak classifiers. It is then called weak classifier because it alone can't
classify the image, but together with others forms a strong classifier.

3.2 Local Binary Patterns Histogram:

Local Binary Patterns Histogram algorithm (LBPH) is for face recognition. It is based on local binary operator, and it
is one of the best performing textures descriptor. The need for facial recognition systems increasing day by day as
per today's busy schedule. They are being used in entrance control, surveillance systems, smartphone unlocking etc. In
this article, we will use LBPH to extract features from an input test image and match them with the faces in system's database.

Local Binary Patterns Histogram algorithm was proposed in 2006. It is based on local binary operator. It is widely used in facial
recognition due to its computational simplicity and discriminating power. The steps involved to achieve this are:
 creating datasets
 face acquisition
 feature extraction
 classification

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 28

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

3.2.1 Steps involved in LBPH:

 Suppose consider an image which having dimensions N x M.

 For every region in an image we have to divide it into regions of same height and width resulting in m x m dimension
 Local binary operator is used for every region. The LBP operator is defined in window size of 3x3

Here '(Xc,Yc)' considered as central pixel with intensity 'Ic'. And 'In' being considered as the intensity of the neighbor pixel

 It compares a pixel to its 8 closest pixels, by setting median pixel value as threshold.

 If the value of neighbor is greater than or equal to the central value it is set as 1 otherwise it is set as 0.
 Thus, we obtain a total of 8 binary values from the 8 neighbors.
 After combining these values, we get an 8 bit binary number which is translated to decimal number for our convenience.
 The obtained decimal number is said to be the pixel LBP value and its range is 0-255.

 After the generation of LBP value histogram for each region of the image is created by counting the number of similar
LBP values in the region.
 After creation of histogram for each region all the histograms are merged to form a single histogram and this is known as
feature vector of the image.
 Now we compare the histograms of the test image and the images in the database and then we return the image with the
closest histogram.
 We can use various kinds of approaches to compare the histograms (calculate the distance between two histograms), for
example: Euclidean distance, chi-square, absolute value, etc.

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 29

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

 The Euclidean distance is calculated by comparing the test image features with features stored within the dataset. The
minimum distance between test and original image gives the matching rate.

 As an output we get an ID of the image from the database if the test image is recognized.

 LBPH can recognize both side and front faces and it is not affected by illumination a variation which means that it is
more flexible

3.2.2 Let us consider an example [14]:-

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 30

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

3.3 System Flow Diagram:

Step 1: First of all, it captures the input image

Step 2: After capturing the image it will preprocess the image and coverts the image into gray scale Image.
Step 3: By using Haar Cascade Classifier face detection will be done and extracts features from the image and then stored in
trained set database.
Step 4: Similarly face recognition is done by using Local Binary Patterns Histogram.
Step 5: And then extracted features will be compared with the trained data set.
Step 6: If it matches attendance will be updated in the attendance folder.
Step 7: If not matches attendance will not be updated in the attendance folder.

3.4 How our Proposed System works?

When we run the program, a window is opened and asks for Enter Id and Enter Name. After entering respective
name and id fields then we have to click Take Images button. By clicking the Take Images button, a camera of running computer
is opened and it starts taking image samples of person. This Id and Name is stored in Student Details folder and file name is saved
as Student Details.csv. It takes 60 images as sample and stores them in Training Image folder. After completion it notifies that
images saved. After taking image samples in order to train the image samples we have to click Train Image button. Now it takes
few seconds to train the machine for the images and creates a Trainner.yml file and stores them in TrainingImageLabel folder.
Now all initial setups are done. After completion of take images and Train images we have to click Track images button which is
used to track the faces. If the face of particular student is recognized by the camera then Id and Name of person is shown on
Image. Press Q (or q) for quit this window. After coming out of it, attendance of particular person will be stored in Attendance
folder as csv file with name, id, date and time and it is also available in window.

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 31

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

IV. SAMPLE OUTPUT:

1. Front view

2. Captures image of particular student

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 32

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

3. A notification message displayed like image saved for particular student with id and name

4. Clicking on Train image button, it displays a notification message like “Image Trained”

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 33

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

5. On clicking the track image button, it recognizes the face (which is already trained) and displays the name and id of the
particular person.

6. On clicking quit button, attendance is updated as shown in the attendance bar.

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 34

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

7. Attendance of particular student is updated in the “Attendance folder”.

V. CONCLUSION:

We have implemented an attendance management system for student’s attendance. It helps to reduce time and effort, especially in
the case of large number of students marked attendance. The whole system is implemented in Python programming language.
Facial recognition techniques used for the purpose of the student attendance. And also, this record of student attendance can
further be used mainly in exam related issues like who are attending the exams and who are not attending. On this project, there is
some further works remained to do like installing the system in the classrooms. It can be constructed using a camera and
computer.

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 35

www.ijcrt.org © 20XX IJCRT | Volume X, Issue X Month Year | ISSN: 2320-2882

VI. REFERENCES:

[1] B.K.P. Horn and M. Brooks, Seeing Shape from Shading. Cambridge, Mass.: MIT Press, 1989
[2] Kanan C, Cottrell GW (2012) Color-to-Grayscale: Does the Method Matter in Image Recognition?
https://doi.org/10.1371/journal.pone.0029740
[3] Grundland M, Dodgson N (2007) Decolorize: Fast, contrast enhancing, color to grayscale conversion. Pattern Recognition 40:
2891-2896.
[4] F. Ibikunle, Agbetuvi F. and Ukpere G. “Face Recognition Using Line Edge Mapping Approach.” American Journal of
Electrical and Electronic Engineering 1.3(2013): 52-59
[5] T. Kanade, Computer Recognition of Human Faces. Basel and Stuttgart: Birkhauser Verlag 1997.
[6] K. Wong, H. Law, and P. Tsang, “A System for Recognizing Human Faces,” Proc. ICASSP, pp. 1,6381,642, 1989.
[7] V. Govindaraju, D.B. Sher, R. Srihari, and S.N. Srihari, “Locating Human Faces in Newspaper Photographs,” Proc. CVPR 89,
pp. 549-554; 1989
[8] N. Dalal, B. Triggs “Histograms of oriented gradients for Human Detection”, IEEE Computer Society Conference on
Computer Vision and Pattern Recognition, Vol. 1, 2005, pp. 886 – 893.
[9] Modern Face Recognition with Deep learning. Website Reference: https://medium.com/@ageitgey/machine-learning-is-fun-
part-4-modern-face-recognitionwith-deep- learning.
[10] S.Edelman, D.Reisfeld, and Y. Yeshurun, “A System for Face Recognition that Learns from Examples,” Proc. European
Conf. Computer Vision, S. Sandini, ed., pp. 787-791. Springer- Verlag, 1992.
[11] Shubhobrata Bhattacharya, Gowtham Sandeep Nainala, Prosenjit Das and Aurobinda Routray, Smart Attendance Monitoring
System : A Face Recognition based Attendance System for Classroom Environment, 2018 IEEE 18th International Conference on
Advanced Learning Technologies, pages 358-360,2018.
[12] Abhishek Jha, "Class room attendance system using facial recognition system", The International Journal of Mathematics,
Science, Technology and Management (ISSN : 2319-8125) Volume: 2,Issue: 3,2014

.[13] T. Lim, S. Sim, and M. Mansor, "RFID based attendance system", Industrial Electronics Applications, 2009. ISIEA 2009.
IEEE Symposium on, volume: 2, pages 778-782, IEEE 2009.

[14] https://towardsdatascience.com/face-recognition-how-lbph-works-90ec258c3d6b

IJCRT1601009 International Journal of Creative Research Thoughts (IJCRT) www.ijcrt.org 36