VISVESVARAYA TECHNOLOGICAL UNIVERSITY

JNANASANGAMA, BELAGAVI, KARNATAKA-590018

An Internship Report
on
“INTERNSHIP TITLE”

Submitted in partial fulfillment towards award of the degree of

BACHELOR OF ENGINEERING
in
Computer Science and Engineering

Submitted by

MANAVI M U
4GW18CS044

Internship carried out at

PIE INFOCOMM
Sector E, Aliganj, Lucknow, Uttar Pradesh

Internal Guide External Guide

Guide Name designation Guide Name with designation

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

(Accredited by NBA, New Delhi, Validity: 01.07.2017 – 30.06.2020 & 01.07.2020 – 30.06.2023)

GSSS INSTITUTE OF ENGINEERING & TECHNOLOGY FOR WOMEN

(Affiliated to VTU, Belagavi, Approved by AICTE, New Delhi & Govt. of Karnataka)
(Accredited with Grade ‘A’ by NAAC)
K.R.S Road, Metagalli, Mysuru-570016, Karnataka
2021-2022
 Geetha Shishu Shikshana Sangha (R)
GSSS INSTITUTE OF ENGINEERING & TECHNOLOGY FOR WOMEN
(Affiliated to VTU, Belagavi, Approved by AICTE -New Delhi & Govt. of Karnataka)
K.R.S Road, Mysuru-570016, Karnataka
Accredited with Grade ‘A’ by NACC

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

(Accredited by NBA, New Delhi, Validity 01.07.2017 to 30.06.2020 & 01.07.2020 to 30.06.2023)

CERTIFICATE

This is to certify that the 8th Semester Internship titled “FACE DETECTION” is a
bonafide work carried out by MANAVI M U (4GW18CS044), in partial fulfillment
for the award of Degree of Bachelor of Engineering in Computer Science and
Engineering of the Visvesvaraya Technological University, Belagavi, during the year
2021-22. The Internship Report has been approved as it satisfies the academic
requirements with respect to the Internship work prescribed for Bachelor of
Engineering Degree.

Signature of Guide Signature of HOD Signature of the Principal

Dr. Raviraj P Dr. S Meenakshi Sundaram Dr. Shivakumar M
Professor Professor and Head Principal

Examiners

Internal Examiner External Examiner

Name: ………………………………. …………………………………

Signature: ……………………………… ………………………………...

 ACKNOWLEDGEMENT

I sincerely owe my gratitude to all the persons who helped and guided me to
carry out the internship.

I am thankful to Mrs. Vanaja B Pandit, Honorary Secretary, GSSSIETW,

Mysuru, for having supported in my academic endeavors.

I am thankful to Dr. Shivakumar M, Principal, GSSSIETW, Mysuru, for all

the support he has rendered.

I thank Dr. S Meenakshi Sundaram, Professor and Head, Department of

Computer Science and Engineering, for his constant support and encouragement
throughout the tenure of this seminar work.

I would like to thank Mr.XXXX ----Thank the External Guide who guided the
internship work at company

I would like to sincerely thank my guide Dr. Raviraj P, Professor, Department

of Computer Science and Engineering, for providing relevant information, valuable
guidance and encouragement to complete this seminar work.

I am extremely pleased to thank my parents, family members and friends for

their continuous support, inspiration and encouragement, for their helping hand and
also last but not the least, I thank all the members who supported directly or indirectly
in the seminar work process.

MANAVI M U
[4GW18CS044]

i
COMPANY CERTIFICATE

ii
ABSTRACT

iii
 TABLE OF CONTENTS

Acknowledgement i
Company Certificate ii
Abstract iii
List of Figures iv
List of Tables v

1. COMPANY PROFILE 1

1.1 About the company

1.2 History of the company
1.3 Founders of the company
1.4 Activities organized by the company
1.5 Sevices offered by company
1.6 Organization of the Report

2. INTRODUCTION
2.1 Objectives
2.2 Problem Statement
2.3 Proposed Solution

3. AREAS OF LEARNING
4. ABOUT THE PROJECT
4.1 Overview of the Project
4.2 System Requirement Specification
4.3 Circuit Diagram
4.4 Implementation Code
4.5 Testing

5. RESULTS AND DISCUSSION

SNAPSHOTS
CONCLUSION
REFERENCES

LIST OF FIGURES
iv
 FIGURE PAGE
DESCRIPTION
NUMBER NUMBER

Figure 1.1

LIST OF TABLES

TABLE NUMBER DESCRIPTION PAGE

NUMBER

Table 1

v
 Face Detection

Chapter 1
COMPANY PROFILE

Figure 1.1: Logo of Pie Infocomm private limited company

Figure 1.1 shows the Logo of PIE Infocomm Private Limited is a non-govt company,
incorporated on 23 Mar, 2011. It's a private unlisted company and is classified as'company
limited by shares.Company's authorized capital stands at Rs 1.0 lakhs and has 100.0% paid-up
capital which is Rs 1.0 lakhs. PIE Infocomm Private Limited is majorly in Business Services
business from last 11 years and currently, company operations are strike off. Current board
members & directors are VIJAY KUMAR JAISWAL and SHAKTI JAISWAL. Company is
registered in Kanpur (Uttar Pradesh) Registrar Office. PIE Infocomm Private Limited registered
address is A-1, NEHRU VIHAR RINGROAD, KALYANPUR LUCKNOW Lucknow UP
226001 IN.

Vision
Pie Infocomm Pvt. Ltd. provides internships both online and offline in many domains like
robotics, IOT, Embedded Systems, AutoCAD, Catia etc. The instructors are highly qualified. I
did my internship in Embedded Systems and it was very good. Working on industrial based
components has helped me broaden my knowledge. I really loved how the concepts were
explained. We started from basics to more advanced levels in just a month. I really thank Pie
infocomm for giving me the opportunity to work as an intern in their esteemed organization.
Mission
• Providing quality education on latest technologies and develop products which are of great
need to the society.

• They also involve distribution and sales of latest electronic innovation products developed all
over the globe to our customers.

Dept of CSE 1 GSSSIETW, Mysuru

 Face Detection

Chapter 2

About the department

The department has established training placements and research labs such as Embedded Lab,
IOT Lab, Intel Lab and Wireless Communication Lab with the latest technical tools for
encouraging students and research scholars in updating their knowledge on the latest technology.
The department has signed Memorandum of Understanding’s with many companies such as
Kaaya Tech Inc., Mysuru, Kayne’s Technology, Mysuru, Advanced Electronic Systems,
Bengaluru, Rob guru Mysuru with an initiative to organize workshops, seminars, faculty
development programs and internships. VTU recognized Research Center is established in the
department which facilitates faculty members to pursue their PhD. About ten faculty members are
pursuing their PhD in various domains such as Image Processing, Nano Technology, VLSI,
Antennas, Wireless Sensor Networks and Computer Network Engineering, Communication
systems.

Vision

"To foster professional level competence in all areas of Electronics and Communication
Engineering and to benchmark the Department as a center for nurturing Women Engineers in the
Country"

Mission

M1: To impart value based technical education and training.

M2: To impart Theoretical Knowledge, Practical Knowledge and Entrepreneurship Skills.

M3: To develop Innovation and Creativity in Students.

M4: To conduct Application oriented research.

M5: To sensitize the Students regarding Social, Moral and Professional ethics.

M6: To provide sufficient Industry exposure to the students.

M7: To provide special skills training to the students to make them eligible for Placement.

Dept of CSE 2 GSSSIETW, Mysuru

 Face Detection

Chapter 3
TASK PERFORMED

3.1 INTRODUCTION

In this report, we focus on image-based face recognition. Given a picture taken from a digital
camera, we’d like to know if there is any person inside, where his/her face locates at, and who
he/she is. Towards this goal, we generally separate the face recognition procedure into three
steps: Face Detection, Feature Extraction, and Face Recognition.

Face Feature Face Verification

/
Imag
Detectio Extractio Recognitio Identificatio
e
n n n n
Figure 3.1: Configuration of a general face recognition structure

Figure 3.1 shows the Block diagram of general face recognition procedure.
Input image must contain faces that are represented by sufficient pixel data. In general, each
face you want to detect in an image should be at least 100x100 pixels.

Face Detection where a photo is searched to find a face, then the image is processed to crop and
extract the person’s face for easier recognition.

Face Extraction An extraction is the process of clearing a clogged or compacted pore by manual
or mechanical means. Extractions are often performed as part of a facial.

Face Recognition where that detected and processed face is compared to a database of known
faces, to decide who that person is. Since 2002, face detection can be performed fairly easily and
reliably with Intel’s open-source framework called OpenCV.

Facial verification technology confirms that your physical face matches the one in the ID
document, and that you are real and completing this application.

Dept of CSE 3 GSSSIETW, Mysuru

 Face Detection

3.2OBJECTIVE

1. The objective of face recognition is, from the incoming image, to find a series of data of the
same face in a set of training images in a database. The great difficulty is ensuring that this
process is carried out in real-time, something that is not available to all biometric facial
recognition software providers.

2. As the need for larger amounts of security rises, innovation will undoubtedly swell to satisfy these
necessities.

3. Any new growth, endeavor, or advancement ought to be uncomplicated and satisfactory for end
clients with the end goal to spread around the world.

4. This solid interest for easy-to-use frameworks which can anchor our advantages and ensure our
security without losing our character in an ocean of numbers, caught the eye and investigations of
researchers toward what's called biometrics.

5. There is a more2 logical Mathematical Introduction for Face Recognition: Pixel Arithmetic for
pursuers who are occupied with the numerical point of view and portrayal of pixels in face
acknowledgment applications.

6. The connection additionally contains a VB.NET usage of the Pixel class.

7. Biometrics is the developing zone of bioengineering; it is the computerized technique for

perceiving individual dependent on a physiological or social trademark.

8. To provide or develop a system that will use the camera of the computer or the system that
would detect and recognize the person's face.

9. The face of the individual using the tool in OpenCV called as the Open Face and python
programming language in deep learning domain.

Dept of CSE 4 GSSSIETW, Mysuru

 Face Detection

3.3 LITERATURE SURVEY

This section is a basic overview of the major techniques used in the face recognition system that
apply mostly to the front face of the human being. The methods include neural networks,
hidden Markov model, face matching done geometrically and template matching.

Eigenface is one of the most widely used methods in face recognition and detection which are
broadly called as the principle components in mathematical terms. [1]
The eigenvectors are
ordered to represent different amounts of the variations in the faces. Neural networks are highly
used in the face recognition and detection systems. An [2]
ANN (artificial neural network) Was
used in face recognition which contained a single layer Which shows adaptiveness in crucial
face recognition systems. The face verification is done using a double layer of WISARD in
neural networks.

Graph matching is other option for face recognition. [3]

The object as well as the face recognition
can be formulated using graph matching performed by optimization of a matching function.
Hidden Markov Models is the way by which stochastic modeling of nonstationary vector time
series based on HMM model applied to the human face recognition wherein the faces gets
divided into parts such as the eyes, nose, ears, etc. [4] The face recognition and correct matching
is 87% correct as it always gives out the best and right choice of face detection through stored
dataset. Or else the relevant model reveals the identity of the face.

The geometrical feature matching is the technique which is based on the geometrical shapes of
the face. The geometrical face configuration has sufficient dataset for face detection and
recognition system. This is one of the commonly used methods of the face recognition and
detection. This system apparently gives satisfactory results. Template matching is one of the
techniques through which the test image is represented as a two- dimensional array of values
which can be compared using Euclidean distance with single template representing the whole
face. This method can also use more than one face template from different points of view to
represent an individual face [5].

Dept of CSE 5 GSSSIETW, Mysuru

 Face Detection

3.4 METHODOLOGY

Figure 3.2: Methodology

Figure 3.2 Describes Methodological approach. Methodology refers to the overarching strategy
and rationale of project. It involves studying the methods used in field and the theories or
principles behind them, in order to develop an approach.

The concept of OpenCV was put forth by Gary Bradski which had the ability to perform on
multi-level framework. OpenCV has a number of significant abilities as well as utilities which
appears from the outset. The OpenCV helps in recognizing the frontal face of the person and
also creates XML documents for several areas such as the parts of the body.

Input image must contain faces that are represented by sufficient pixel data. In general, each
face you want to detect in an image should be at least 100x100 pixels.

Face Detection where a photo is searched to find a face, then the image is processed to crop and
extract the person’s face for easier recognition.

Dept of CSE 6 GSSSIETW, Mysuru

 Face Detection

Face Recognition where that detected and processed face is compared to a database of known
faces, to decide who that person is. input image or any other relevant picture and the second
being giving the best outputs or the results of the image of the picture.

Data base When benchmarking an algorithm, it is recommendable to use a standard test data set
for researchers to be able to directly compare the results. We would be using dlib facial
recognition framework that would be the easy way to organize the face evaluation. The two main
significant libraries used in the system are dlib and face recognition.

Python being a very powerful programming languages and one of the programming languages
that are being used all over the world has proven to give best result s in the face recognition and
detection systems. Together face recognition and detection becomes very easy and fruitful with
the help of the python programming language and OpenCV.

Need of an automated system

Due to the rising need for the systems which can help in the areas such as surveillance as well as
security this kind of individual authentication can no longer be done using simple handmade
methods hence there is a rising need of the automated systems that can easily rectify the faults
and process the human face recognition. When the work is done by machines it can perform
tasks efficiently in very less duration of time and cuts off the major mistakes occurred by
humans. A real time GUI based face recognition system built can ease this work of face
detection and can be achieved in various ways.

Graphical User Interface

The graphical user interface (GUI) is the platform that will allow the inputs from the user ends a
kind of interaction with the system. GUIs are used in mobiles, media players, games and many
others. We can design visual composition and the temporal behaviour of the GUI in any of the
software application as well as programming in the areas of the human computer interaction.
The GUI for this project will be widely based on the training and the testing phase which in turn
will allow the capture and train of the image.

Dept of CSE 7 GSSSIETW, Mysuru

 Face Detection

3.5 Problem Statement

However, detecting a person’s face when that person is viewed from an angle is usually harder,
sometimes requiring 3D Head Pose Estimation. Also, lack of proper brightness of an image can
greatly increase the difficulty of detecting a face, or increased contrast in shadows on the face, or
maybe the picture is blurry, or the person is wearing glasses, etc.

 A general statement of face recognition problem can be formulated as follows: Given still

or video images of a scene, identify or verify one or more persons in the scene using a
stored database of faces.
 Over the past decade face detection and recognition have transcended from esoteric to
popular areas of research in computer vision and one of the better and successful
applications of image analysis and algorithm-based understanding.
 The intrinsic nature of the problem, computer vision is not only a computer science area
of research, but also the object of neuroscientific and psychological studies also, mainly
because of the general opinion that advances in computer image processing and
understanding research will provide insights into how our brain work and vice versa.
 A general Statement of the face recognition problem in computer vision can be
formulated as follows:
1. Video images of a scene
2. Identify or verify one or more persons in the scene using to stored data . Facial
recognition generally involves two stages:

Face Detection where a photo is searched to find a face, then the image is processed to crop and
extract the person’s face for easier recognition.

Face Recognition where that detected and processed face is compared to a database of known
faces, to decide who that person is. Since 2002, face detection can be performed fairly easily and
reliably with Intel’s open-source framework called OpenCV. This framework has an inbuilt Face
Detector that works in roughly 90-95% of clear photos of a person looking forward at the
camera. However, detecting a person’s face when that person is viewed from an angle is usually
harder, sometimes requiring 3D Head Pose Estimation.

Dept of CSE 8 GSSSIETW, Mysuru

 Face Detection

3.6 Project Architecture

Figure 3.3: face recognition system design using python and OpenCV

From the figure 3.3, Architecture of the Application gives a system that is used to abstract the
overall outline of the software system and the relationships, constraints, and boundaries between
components.

Data Gathering: First, you need a dataset or even create one of your own. Just make sure to
arrange all images in folders with each folder containing images of just one person.The very first
task we perform is detecting faces in the image or video stream. Now that we know the exact
location/coordinates of face, we extract this face for further processing ahead.

Train the Recognizer: Using the unique measurements of each face, a final ML algorithm will
match the measurements of the face against known faces in a database. Whichever face in your
database comes closest to the measurements of the face in question will be returned as the match.

Recognition: we are going to implement face recognition using OpenCV and Python. OpenCV
is a video and image processing library and it is used for image and video analysis, like facial
detection, license plate reading, photo editing, advanced robotic vision, and many more.

Machine Learning

The resulting data is fed into a machine learning model. To find the optimal procedure and
parameters for the model, we will mostly employ K-fold Cross-Validation and the
GridSearchCV approach. It turns out that the linear regression model produces the best results
for our data, with a score of more than 80%, which is not terrible.

Dept of CSE 9 GSSSIETW, Mysuru

 Face Detection

3.7 EXPERIMENTAL SETUP

Step to Create Model
1. Import Libraries such as OpenCV, Python, dlib.
2. Load Dataset, here libraries are used to load the data.
3. Import cv2. import os.
4. Feature Engineering: Adding new features
5. Initialize the classifier: cascPath=os.
6. Data Visualization involves representation of the data.
7. Test the Model for few properties
8. Run the project file.

Tools used

Hardware Tools

1. Processor i3: is a dual-core computer processor, available for use in both desktop and
laptop computers.
2. Hardware 10 GB: A 10GB data plan will allow you to browse the internet for around 120
hours, to stream 2,000 songs or to watch 20 hours of standard-definition video.
3. RAM 8 GB: RAM 8GB Typically installed in entry-level notebooks. This is fine for
basic Windows gaming at lower settings, but rapidly runs out of steam.

Software Tools

1. Platform Windows, Linux or MacOS: Microsoft Platform means any current and future
Microsoft operating system products, Microsoft run-time technologies.
2. Operating system Windows, Linux or MacOS: Linux is a Unix-like, open source and
community-developed operating system OS for computers, servers, mainframes, mobile
devices and embedded devices.
3. IDE PyCharm: With PyCharm, you can access the command line, connect to a database.

Dept of CSE 10 GSSSIETW,

Mysuru
 Face Detection

3.8 Technologies used

PYTHON

Python an interpreted high-level general-purpose programming language. Its design philosophy

is emphasizing code readability with its use of significant indentation. Its language constructs as
well as its object-oriented approach aim to help programmers write clear, logical code for small
and large-scale projects.

Python is dynamically-typed and garbage-collected. It supports multiple programming

paradigms, including structured (particularly, procedural), object-oriented and functional
programming. It is often described as a "batteries included" language due to its comprehensive
standard library.

Guido van Rossum began working on Python in the late 1980s, as a successor to the ABC
programming language, and first released it in 1991 as Python 0.9.0. Python 2.0 was released in
2000 and introduced new features, such as list comprehensions and a cycle- detecting garbage
collection system (in addition to reference counting). Python 3.0 was released in 2008 and was a
major revision of the language that is not completely backward- compatible. Python 2 was
discontinued with version 2.7.18 in 2020.

Python consistently ranks as one of the most popular programming languages.

3.9 About the project

Face Detection

This Face Recognition project detects faces and places a frame around them and identifies the
face based on those in a given list. It works by analyzing a photo and comparing it to the faces in
the list to determine if it is a match or if it is an unknown identity. We will build this project in
Python using OpenCV. Face Recognition is a technology in computer vision. In Face recognition
or detection, we locate and visualize the human faces in any digital image. It is a subdomain of
Object Detection, where we try to observe the instance of semantic objects. These objects are of

Dept of CSE 11 GSSSIETW,

Mysuru
 Face Detection

particular class such as animals, cars, humans, etc. Face Detection technology has importance in
many fields like marketing and security.

Importing Libraries

Import libraries such as

OpenCV: OpenCV is a video and image processing library and it is used for image and video
analysis, like facial detection, license plate reading, photo editing, advanced robotic vision, and
many more. To install OpenCV, type in command prompt 

pip install opencv-python

First, install Anaconda and then use this command in your command prompt:

conda install -c conda-forge dlib

Next to install face_recognition, type in command prompt

pip install face_recognition

In the next file we will compare the faces with the existing the recognise faces in images and
next we will do the same but recognise faces in live webcam feed.

 Dlib: The dlib library contains our implementation of ‘deep metric learning’ which is used to
construct our face embeddings used for the actual recognition process.
 Face recognition: The face_recognition library is super easy to work with and we will be
using this in our code. First, remember to install dlib library before you install
face_recognition.
To install OpenCV, dlib, and face recognition type the following snippets in the command
prompt.

pip install opencv-python

Dept of CSE 12 GSSSIETW,

Mysuru
 Face Detection

conda install -c conda-forge dlib

pip install face_recognition

Image data manipulation allocation, release, copying, setting, conversion. Positive images
– These images contain the images which we want our classifier to identify.
Negative Images – Images of everything else, which do not contain the object we want to
detect.

Screenshot

Figure 3.4: Image detection

ode.

Face recognition is a method of identifying or verifying the identity of an individual using

their face. There are various algorithms that can do face recognition but their accuracy might

Dept of CSE 13 GSSSIETW,

Mysuru
 Face Detection

vary. Here I am going to describe how we do face recognition using OpenCV.

Face recognition however is much less reliable than face detection, with an accuracy of 30-70%
in general. Face recognition has been a strong field of research since the 1990s, but is still a far
way away from a reliable method of user authentication. More and more techniques are being
developed each year. The Eigenface technique is considered the simplest method of accurate face
recognition, but many other (much more complicated) methods or combinations of multiple
methods are slightly more accurate.

Figure 3.5: Video detection

Figure 3.5: Describes how the video is detected using OpenCV with python ML code.In today’s
tutorial, we’ll learn how we can apply deep learning and OpenCV together with no other libraries
other than scikit-learn to:

Dept of CSE 14 GSSSIETW,

Mysuru
 Face Detection

1.Detect faces

2.Compute 128-d face embeddings to quantify a face

3.Train a Support Vector Machine (SVM) on top of the embeddings. Recognize faces in images

and video streams.

Face recognition however is much less reliable than face detection, with an accuracy of 30-70%
in general. Face recognition has been a strong field of research since the 1990s, but is still a far
way away from a reliable method of user authentication. More and more techniques are being
developed each year. The Eigenface technique is considered the simplest method of accurate face
recognition, but many other (much more complicated) methods or combinations of multiple
methods are slightly more accurate.

Figure 3.6: Graph for Face Detection reliability

The figure 3.6 shows the reliability of the Face detection using python machine learning with the
support of OpenCV.

Dept of CSE 15 GSSSIETW,

Mysuru
 Face Detection

Where,
AP_50 = Precision when overlap between Ground Truth and predicted bounding box is at least
50%(IoU=50%)
AP_75 = Precision when overlap between Ground Truth and predicted bounding box is at least
75%(IoU=75%)
AP_Small = Average Precision for small size faces (Average of IoU = 50% to 95%)

Chapter 4

REFLECTION NOTES

NON-TECHNICAL OUTCOME:

1. Being organized
Face Recognition using the unique measurements of each face, a final ML algorithm will
match the measurements of the face against known faces in a database. Whichever face in
your database comes closest to the measurements of the face in question will be returned as
the match. Facial recognition can be used to find missing persons and victims of human
trafficking. Suppose missing individuals are added to a database. In that case, law
enforcement can be alerted as soon as they are recognized by face recognition — whether it
is in an airport, retail store, or other public space.

2. Teamwork

Teamwork motivates unity in the workplace and a collaborative climate foster friendship
and loyalty. When you work as a team, you can complete tasks quiker and more effectively
than if you worked alone on the project. Good teamwork and collaboration systems allow
for a diversity of thinking, imagination, insights,opportunities,and problem-solving
methods in your organization.working in a team increases everyone’s responsibility and
accountability.

3. Personality Development

Dept of CSE 16 GSSSIETW,

Mysuru
 Face Detection

• An internship offers the chance to learn and also gain valuable experience and
accomplishments to add to our resume and /or enhance our application to graduate.

• Internship creates advantage over job.

• Internships help to master professional soft skills such as problem solving, critical thinking
and time management. These are skills that are keys for success at a job and college.

• Internship gives us the chance to use the skills that we’ve learnt in the classroom in a real-
world setting. We can learn new skills that add to our knowledge base and gain confidence in
our abilities by giving presentation on every task or the assignments that were carried out.

4. SKILLS DEVELOPED

Critical thinking

Critical thinking refers to ability to analyze and evaluate a situation or issue and form a
judgment. The tendency to think critically can be demonstrated by a willingness to ask
questions in order to understand an issue from all possible angles, and to pose creative
solutions to challenges. Organization skill refers to ability tostay focused on different
tasks and utilize energy, strength, mental capacity etc. effectively and efficiently in order
to achieve the desired outcome.

Problem solving

Problem solving is the act of defining a problem, determining the cause of the problem,
identifying, prioritizing, and selecting alternatives for a solution, and Implementing a
solution

TECHNICAL OUTCOME:

1. Python Machine learning

The machine learning libraries are extremely technical and written in low level languages
for speed. Data scientists tend to be more mathematicians than engineers. Python is a
very approachable language that lets those mathematicians express their requirements to
the ML libraries without learning a lot of complex code.

Dept of CSE 17 GSSSIETW,

Mysuru
 Face Detection

2. Database Management
Facial recognition is a technology that can recognize a person only by looking at them. It
uses machine learning techniques to identify, collect, store, and evaluate face
characteristics so that they can be matched to photos of people in a database. The DBMS
accepts a request made for data from an application and instructs the OS to provide
specific required data. In large systems, a DBMS helps users to store and retrieve data at
any given point of time

Chapter 5

CONCLUSION

The computational models, which were implemented in this project, were chosen after extensive
research, and the successful testing results confirm that the choices made by the researcher were
reliable. The system with manual face detection and automatic face recognition did not have a
recognition accuracy over 90%, due to the limited number of eigenfaces that were used for the
PCA transform.

This system was tested under very robust conditions in this experimental study and it is
envisaged that real-world performance will be far more accurate. The fully automated frontal
view face detection system displayed virtually perfect accuracy and in the researcher's opinion
further work need not be conducted in this area. The fully automated face detection and
recognition system was not robust enough to achieve a high recognition accuracy. The only
reason for this was the face recognition subsystem did not display even a slight degree of
invariance to scale, rotation or shift errors of the segmented face image.

However, if some sort of further processing, such as an eye detection technique, was
implemented to further normalize the segmented face image, performance will increase to levels
comparable to the manual face detection and recognition system. Implementing an eye detection
technique would be a minor extension to the implemented system and would not require a great
deal of additional research. All other implemented systems displayed commendable results and

Dept of CSE 18 GSSSIETW,

Mysuru
 Face Detection

reflect well on the deformable template and Principal Component Analysis strategies. The most
suitable real-world applications for face detection and recognition systems are for mugshot
matching and surveillance. There are better techniques such as iris or retina recognition and face
recognition using the thermal spectrum for user access and user verification applications since
these need a very high degree of accuracy. The real-time automated pose invariant face detection
and recognition system proposed in chapter seven would be ideal for crowd surveillance
applications. If such a system were widely implemented its potential for locating and tracking
suspects for law enforcement agencies is immense.

REFERENCES

[1] L. Zhi-fang, Y. Zhi-sheng, A.K.Jain and W. Yun-qiong, 2003, “Face Detection And Facial
Feature Extraction In Color Image”, Proc. The Fifth International Conference on
Computational Intelligence and Multimedia Applications (ICCIMA’03), pp.126-130,
Xi’an, China.

[2] Lin, 2005, “Face Detection by Color and Multilayer Feedforward Neural Network”, Proc.
2005 IEEE International Conference on Information Acquisition, pp.518-523, Hong
Kong and Macau, China.

[3] S. Kherchaoui and A. Houacine, 2010, “Face Detection Based on A Model of The Skin
Color With Constraints And Template Matching”, Proc. 2010 International Conference
on Machine and Web Intelligence, pp. 469 - 472, Algiers, Algeria.

[4]. Design of a Face Recognition System (PDF Download Available). Available from:
https://www.researchgate.net/publication/262875649_Design_of_a_Face_Recognition_S
ystem.

[5]. Face Detection and Tracking using OpenCV. S.V.Viraktamath, Mukund Katti, Aditya
Khatawkar, Pavan Kulkarni. 3, s.l.: SIJ, July-August 2013, The Standard International
Journals (The SIJ), Vol. 1, pp. 45-50. ISSN: 2321 – 2403

Dept of CSE 19 GSSSIETW,

Mysuru
 Face Detection

[6] http://www.sourceforge.net/projects/opencvlibrar y Computer VisionHomepage

[7] http://www-2.cs.cmu.edu/~cil/vision.html

[8] R. Szeliski. Computer Vision: Algorithms and Applications. Springer 2011.

[9] http://opencv.willowgarage.com/wiki/

[10] http://en.wikipedia.org/wiki/BSD_license [6] R. Laganière. OpenCV 2 Computer

Vision Application Programming Cookbook. Packt Publishing 2011

[11] Python with deep learning, https://www.tutorialspoint.c

[12] Face Detection and Tracking using OpenCV. S.V.Viraktamath, Mukund Katti, Aditya
Khatawkar, Pavan Kulkarni. 3, s.l.: SIJ, July-August 2013, The Standard International
Journals (The SIJ), Vol. 1, pp. 45-50. ISSN: 2321 – 2403

[13] John G Daugman. Uncertainty relation for resolution in space, spatial frequency, and
orientation optimized by two-dimensional visual cortical filters. JOSA A, 2(7):1160–
1169, 1985.

[14] S Marˆcelja. Mathematical description of the responses of simple cortical cells. JOSA,
70(11):1297– 1300, 1980.

[15] Rainer Lienhart and Jochen Maydt. An extended set of haar-like features for rapid object
detection. In Image Processing. 2002. Proceedings. 2002 International Conference on,
volume 1, pages I–I. IEEE, 2002.

[16] John P Lewis. Fast template matching. In Vision interface, volume 95, pages 15–19, 1995.

5] Wikipedia, Three-dimensional face

recognition,
5] Wikipedia, Three-dimensional face
recognition,
5] Wikipedia, Three-dimensional face
recognition,

Dept of CSE 20 GSSSIETW,

Mysuru
 Face Detection

Dept of CSE 21 GSSSIETW,

Mysuru