A

Project Report On

REAL TIME FACE RECOGNITION AUTOMATIC STUDENTS

ATTENDENCE MANAGEMENT (Software with chatbot)

Submitted To

G H Raisoni College Of Arts, Commerce & Science Affiliated To

Savitribai Phule Pune University

For
Bachelor Of Business Administration (Computer Application)

Submitted By:

Pritish Pawar

Roll No: 36

Shubham Bhosale

Roll No: 12

SEMESTER VI (2023-24)

Under The Guidance Of

Prof. Priyanka Deshmukh

(Project Guide)
 CERTIFICATE

This is to certify that the project report entitles

College Placement Cell System

Submitted by

Pritish Ramesh Pawar

Shubham Rajdeep Bhosle

“REAL TIME FACE RECOGNITION AUTOMATIC STUDENTS ATTENDENCE

MANAGEMENT( Software with chatbot)” is a bonafide student of this institute and the work
has been carried out by him/her under the supervision of Prof. Priyanka Deshmukh and it is
approved for the partial fulfillment of the requirement of G.H RAISONI COLLEGE OF ARTS,
COMMERCE AND SCIENCE , for the award of the degree of Bachelor of Computer Application.

Mrs. Priyanka Deshmukh

(Project Guide)

Internal Examiner Department of Computer

Application

External Examiner

Director,

Dr. H. R. Kulkarni
G H RAISONI COLLEGE OF ARTS,
COMMERCE AND SCIENCE, PUNE

Place : Wagholi

Date:
 Acknowledgement

We express our pleasure in submitting this project entitled

“REAL TIME FACE RECOGNITION AUTOMATIC STUDENTS
ATTENDENCE MANAGEMENT SOFTWARE” to
G H RAISONI COLLEGE OF ARTS, COMMERCE AND SCIENCE

We express our deep sense of gratitude towards

Prof. Priyanka Deshmukh for his valuable guidance and his interest,
we are able to complete this project in scheduled time.

We are indebted to our honorable principle who has been a constant source of
motivation and co-operating in bringing this project in very short time.

Lastly we are thankful to all other staff members of G.H RAISONI

COLLEGE OF ARTS, COMMERCE AND SCIENCE and our colleagues who
have directly or indirectly helped us while completing this project report.

Projected By
1. Pritish Ramesh Pawar
2.Shubham Rajdeep Bhosale

Students Signature

________________ _________________

Pritish Pawar Shubham Bhosale

 ABSTRACT

In the era of modern technologies emerging at rapid pace there

is no reason why a crucial event in educational sector such as
attendance should be done in the old boring traditional way.

Attendance monitoring system will save a lot of time and

energy for the both parties students as well as the class

teachers. Attendance will be monitored by the face recognition

algorithm by recognizing only the face of the students from the

rest of the objects and then marking them as present. The

system will be pre feed with the images of all the students and

with the help of this pre feed data the algorithm will detect them

who are present and match the features with the already saved

images of them present in the database.

 INDEX

SR. NO CHAPTERS

ABSTRACT

1 INTRODUCTION

2 LITERATURE SURVEY

3 SOFTWARE REQUIREMENTS SPECIFICATION

4 HAAR CASCADE ALGORITHM

5 LBPH ALGORITHM

6 OTHER SPECIFICATION

7 CONCLUSION AND FUTURE WORK

 LIST OF FIGURES

fig 1. Flow chart ................................................................................................................................18

fig 2. haar cascade feature ............................................................................................. ………………21

fig 3. image detection using haar cascade .......................................................................................22

fig 4. image detection using haar cascade ........................................................................................26

fig 5. Radius of central pixel ..............................................................................................................28

fig 6. Histogram generation ................................................................................................................29

fig 7. face alignment and feature extraction ......................................................................................32

LIST OF TABLES

Table 1. LITERATURE SURVEY...................................................................................................... 12

 Chapter-1

INTRODUCTION
1. Introduction

The purpose of the attendance monitoring system using face

recognition is to ease the attendance process which consumes lot of
time and efforts, it is a convenient and easy way for students and
teacher. The system will capture the images of the students and using
face recognition algorithm mark the attendance in the sheet. This way
the class-teacher will get their attendance marked without actually
spending time in traditional attendance marking.

The identification process to determine the presence of a person in

a room or building is currently one of the routine security activities.
Every person who will enter a room or building must go through
several authentication processes first, that later these information’s
can be used to monitor every single activity in the room for a
security purpose. Authentication process that is being used to
identify the presence of a person in a room or building still vary.
The process varies from writing a name and signatures in the
attendance list, using an identity card, or using biometric methods
authentication as fingerprint or face scanner.
 1.1 MOTIVATION

Nowadays many educational institutes are

using a manual monitoring system and most of
the time they accidentally loss their attendance
sheet so that they cannot properly monitor the
attendance of their students. Therefore, it is
important to design software which will help
these institutes to mark the attendance of the
students by face recognition which will save
their time.
 1.2 PROBLEM DEFINITION

Automatic Face recognition

attendance management using
Machine Learning

A real-world student attendance system

which recognize face of student and
attendance of the respective student will
be marked automatically on excel sheet.
 Chapter-2

LITERATURE
SURVEY
 2.LITERATURE SURVEY

Table 1. LITERATURE SURVEY

Sr. Paper Publication Methodology Conclusion

No. Name/Author Year

The Existing system is a

1. Monica.C, Nithya.R, The design is expressed manual entry for the Admin
Prarthana.M, 2017 in sufficient detail so as and also
Sonika.S.V, to enable all the Faculty. Here the attendance
Dr.M.Ramakrishna developers to will be
understand the carried out in the hand
underlying architecture written registers.
of Attendance system. Maintaining the records for
the
Faculty is a tedious job

Abdoulrahmaine In this we study it The new system has been

Mohammad, 2018 capable of eliminating designed as per the user
2. Mohammad Elmi time wasted during requirements so as to fulfill
Hassan, manual collection of almost all them.
Muslim Musa attendance and for the -User friendly
educational -Report Generation
administration -Less paper work
 Chapter-3

SOFTWARE
REQUIRMENTS
SPECIFICATION
 3.SOFTWARE REQUIREMENTS AND SPECIFICATION
3.1 INTRODUCTION
3.1.1 Project Scope

The scope of the system is to reduce the time of the teacher as well as student which
they wasted by doing traditional attendance.

3.1.2 User Classes and Characteristics

Identify the various user classes that you anticipate will use this product. User
classes may be differentiated based on frequency of use, subset of product
functions used, technical expertise, security or privilege levels, educational
level, or experience. Describe the pertinent characteristics of each user class.
Certain requirements may pertain only to certain user classes. Distinguish the
most important user classes for this product from those who are less important
to satisfy.

3.1.3 Assumptions and Dependencies

This document will provide a general description of our project, including user

requirements, product perspective, and overview of requirements, general

constraints. In addition, it will also provide the specific requirements and
functionality needed for this project such as interface, functional requirements
and performance requirement

FUNCTIONAL REQUIREMENTS

Functional user requirements may be high-level statements of what the system should do but
functional system requirements should also describe clearly about the system services in
detail.
3.2 EXTERNAL INTERFACE REQUIREMENTS
3.2.1 User Interfaces

The user interface for the software shall be compatible to any

windows, android version by which user can access to the system.
The user interface shall be implemented using any tool or software
package like Visual Studio, Android Studio, MYSQL etc.

3.2.2 Hardware Interfaces

Since the application must run over the internet, the hardware shall
require to connect internet to the hardware which is android
device/computer-system for the system.

3.2.3 Software Interfaces

This system is a Single-user, multi-tasking environment. It enables

the user to interact with the server and attain interact with the
server to show the animal information also leaves a record in the
inbuilt database. It uses Python(Tkinter) as the front end
programming tool and MySQL as the back end application tool.

3.2.4 Communication Interfaces

The e-store system shall use the HTTP protocol for communication
over the internet and for the intranet communication will be
through TCP/IP protocol suite.
 NON FUNCTIONAL REQUIREMENTS:

3.2.5 Performance Requirements

• System can produce results faster on 2GB/4GB of RAM.

• It may take LESS time for peak loads at main node.

• The system will be available 100% of the time. Once there is a fatal

error, the system will provide understandable feedback to the user.

3.2.6 Safety and Security Requirements

• The system is designed in modules where errors can be detected and

fixed easily.

3.2.7 Software Quality Attributes

• Reliability: The Client machine will change the status of data indicating

successful data transmission.

• Usability: The application should be easy to use through interactive

interface.

• Maintainability: The system will be developed using the standard

software development conventions to help in easy review and redesigning of

the system.

• Support ability: The system will be able to support to transfer different

types of

SQL queries.

Portability: This software is portable to any system with the requirements

specified. There must also be a server where the database can be set-up.
 SYSTEM REQUIREMENT

3.2.8 Software Requirements Platform :

1. Operating System : Windows OS

2. Platform: Visual Studio

3. Programming Language : PHYTON

4. Database : MySql

3.2.9 Hardware Requirements

1. Processor: INTEL Pentium 4 Processor

Core

2. Hard Disk: 40 GB (min)

3. RAM: 256 MB or higher

 3.3 BASIC FLOWCHART DIAGRAM

Attendance
Add
students Database is Open the Face with date
information trained in camera for recognition and time
and face in backend recognition done saved in
database database

fig 1 .Flow chart

 Select_security roll email
Security_ans course
_ans
address
dep
emai Registeration
l Sends Student_details
year
data
Iname Fname gender
name
Dob
Phone_no
pwd phone
Student_id

photoSample

Std_date

Std_time Student_Attendance
Std_name

Std_id Std_roll_no Std_attendance

ERD Digram
 Chapter-4

SYSTEM
DESIGN
4. HAAR CASCADE ALGORITHM
The core basis for Haar classifier object detection is the Haar-like features. These features,
rather than using the intensity values of a pixel, use the change in contrast values between
adjacent rectangular groups of pixels. The contrast variances between the pixel groups are used
to determine relative light and dark areas. Two or three adjacent groups with a relative contrast
variance form a Haar-like feature. Haar-like features as shown in figure are used to detect an
image. Haar features can easily be scaled by increasing or decreasing the size of the pixel group
being examined. This allows features to be used to detect objects of various sizes. The
cascading of the classifiers allows only the sub-images with the highest probability to be
analyzed for all Haar-features that distinguish an object. It also allows one to vary the accuracy
of a classifier. One can increase both the false alarm rate and positive hit rate by decreasing the
number of stages. The inverse of this is also true. Viola and Jones were able to achieve a 90%
accuracy rate for the detection of a human face using only 100 simple features. Detecting
human facial features, such as the mouth, eyes, and nose require that Haar classifier cascades
first are trained. In order to train the classifiers, this gentle AdaBoost algorithm and Haar feature
algorithms must be implemented. Fortunately, Intel developed an open source library devoted
to easing the implementation of computer vision related programs called Open Computer
Vision Library (OpenCV). The OpenCV library is designed to be used in conjunction with
applications that pertain to the field of HCI, robotics, biometrics, image processing, and other
areas where visualization is important and includes an implementation of Haar classifier
detection and training. Thus with help of this algorithm system will detect the person’s face in
the video. Face of the person gets Green Square as an indication of detection process. As soon
as the face gets detected user can paused the video and enters the data of detected person such
as person’s name, address, profession, criminal record if any. If the detected person has criminal
record then it can be defined as suspect. Check box option is given in the system where user
can tick whether the person is suspect on not. This is the working of first module in which
sample video is browsed and face is detected.

Fig 3. Haar Features

5. Local Binary Pattern Histogram (LBPH):

5.1.Introduction to LBPH algorithm

Local Binary Pattern (LBP) is a simple yet very efficient texture operator which labels the
pixels of an image by thresholding the neighborhood of each pixel and considers the result as
a binary number.
The first computational step of the LBPH is to create an intermediate image that describes the
original image in a better way, by highlighting the facial characteristics. To do so, the algorithm
uses a concept of a sliding window, based on the parameters radius and neighbors.

5.1 Applying the LBP operation:

The first computational step of the LBPH is to create an intermediate image that describes the
original image in a better way, by highlighting the facial characteristics. To do so, the algorithm
uses a concept of a sliding window, based on the parameters radius and neighbors.
The image below shows this procedure:

Fig 4. Applying the LBP operation

5.2. Performing the face recognition:

• In this step, the algorithm is already trained. Each histogram created is used to represent each
image from the training dataset. So, given an input image, we perform the steps again for this
new image and creates a histogram which represents the image.

• So to find the image that matches the input image we just need to compare two histograms and
return the image with the closest histogram.

• We can use various approaches to compare the histograms (calculate the distance between two
histograms), for example: Euclidean distance, chi-square, absolute value, etc. In this example,
we can use the Euclidean distance (which is quite known) based on the following formula:

• So the algorithm output is the ID from the image with the closest histogram. The
algorithm should also return the calculated distance, which can be used as a ‘confidence’
measurement. Note: don’t be fooled about the ‘confidence’ name, as lower confidences
are better because it means the distance between the two histograms is closer.

• We can then use a threshold and the ‘confidence’ to automatically estimate if the
algorithm has correctly recognized the image. We can assume that the algorithm has
successfully recognized if the confidence is lower than the threshold defined.
 5.3 TRAINING THE ALGORITHM:
First, we need to train the algorithm. To do so, we
need to use a dataset with the facial images of the
people we want to recognize. We need to also set an
ID (it may be a number or the name of the person)
for each image, so the algorithm will use this
information to recognize an input image and give
you an output.
Images of the same person must have the same ID.
With the training set already constructed, let’s see
the LBPH computational steps.

5.4 APPLYING LBH OPERATIONS

The first computational step of the LBPH is to create

an intermediate image that describes the original
image in a better way, by highlighting the facial
characteristics. To do so, the algorithm uses a
concept of a sliding window, based on the
parameters radius and neighbors.
 IMPORTANT POINTS

• Suppose we have a facial image in grayscale.

• We can get part of this image as a window of 3x3 pixels.

• It can also be represented as a 3x3 matrix containing the intensity of each pixel (0~255).

• Then, we need to take the central value of the matrix to be used as the threshold.

• This value will be used to define the new values from the 8 neighbors.
For each neighbor of the central value (threshold), we set a new binary value. We set 1 for values
equal or higher than the threshold and 0 for values lower than the threshold.

Fig.6 Radius of central pixel

5.4 EXTRACTING THE HISTOGRAM

Now, using the image generated in the last step, we can use the Grid X and Grid Y parameters
to divide the image into multiple grids, as can be seen in the following image
 Based on the image above, we can extract the histogram of each region as follows:

• As we have an image in grayscale, each histogram (from each grid) will contain only 256 positions

(0~255) representing the occurrences of each pixel intensity.

• Then, we need to concatenate each histogram to create a new and bigger histogram. Supposing

we have 8x8 grids, we will have 8x8x256=16.384 positions in the final histogram. The final

histogram represents the characteristics of the image original image.

No table of figures entries found.

In this step, the algorithm is already trained. Each histogram created is used to represent each
image from the training dataset. So, given an input image, we perform the steps again for this new
image and creates a histogram which represents the image.
So to find the image that matches the input image we just need to compare two histograms and
return the image with the closest histogram.
We can use various approaches to compare the histograms (calculate the distance between two
histograms), for example: Euclidean distance, chi-square, absolute value, etc. In this example,
we can use the Euclidean distance (which is quite known) based on the following formula:

So the algorithm output is the ID from the image with the closest histogram. The algorithm should also
return the calculated distance, which can be used as a ‘confidence’ measurement. Note: don’t be fooled

• ‘confidence’ name, as lower confidences are better because it means the distance between the two

histograms is closer.

• We can then use a threshold and the ‘confidence’ to automatically estimate if the algorithm has

correctly recognized the image. We can assume that the algorithm has successfully recognized if

the confidence is lower than the threshold defined.

fig 8. Face alignment and feature extraction
 Chapter-6

OTHER
SPECIFICATONS
 6.OTHER SPECIFICATIONS

6.1Advantages:

1. It is trouble-free to use.

2. It is a relatively fast approach to enter attendance.

3. Is highly reliable, approximate result from user .

4. Best user Interface .

5. Can obtain accuracy upto 85 percent.

6.2Limitations:

1) While training there generates nearly 100 of copies of sample image.

2) While dealing with high volume of data system required the powerful processor

which is more costly

6.3Applications:

1. It is very useful for educational institutes to get attendance easily.

We can get attendance of students as well as teachers without doing conventional attendance
 Chapter-7

CONCLUSION
AND
FUTURE WORK
 7.CONCLUSION AND FUTURE WORK

Conclusion:

• The Attendance Management System is developed using

Machine Learning meets the objectives of the system which it has

been developed. The system has reached a steady state where all

bugs have been eliminated. The system is operated at a high level

of efficiency. The system solves the problem. It was intended to

solve as requirement specification.

• The system can recognize and identify the face well with an

accuracy of 85 %, at a face distance 40 cm from the camera with

adequate lighting.

Future Work:

We have planned to create the application for multiple college

campuses and for the multiple schools.
We have planned to create the application for android
systems.
Outputs:
Installation
1) Open the setup file (.exe)

2) Choose the location/directory where to install

the software.
3) Wait until installation gets completed

4) Moved to the installation directory, opened the application file. Done.

Chat Bot
 8.REFERENCES:

1) G.Satyanarayana Reddy,Rallabandi
Srinivasu,Srikanth Reddy Rikkula,Vuda
Sreenivasa Rao,” Management Information
System To Help Managers For Providing
Decision Making In An Organization”,
International Journal of Reviews in
Computing.
2) Learning OpenCV –Computer Vision with
the OpenCV Library O’Reilly Publication
3) http://www.wordpress.org/
4) http://www.academia.edu/
5) http://www.stackoverflow.com/
6) http://www.iproject.com