A

Minor Project Report

On

DRIVER DROWSINESS DETECTION

SYSTEM
Submitted
in partial fulfillment
for the award of the Degree of
Bachelor of Technology
In
Computer Engineering

Submitted To: Submitted By:

Er. Pradeep Jha Aman Anand (16EAYCS008)
Associate prof. & Head Kuldeep Vaishnav (16EAYCS038
Computer Science &Engineering Manish Sharma (16EAYCS047)

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

ARYA COLLEGE OF ENGINEERING & RESEARCH CENTRE
SP-40, RIICO INDUSTRIAL AREA, KUKAS, JAIPUR, RAJASTHAN
RAJASTHAN TECHNICAL UNIVERSITY, KOTA
[2016-2020]

ABSTRACT

i|P a g e
 The face is one of the easiest ways to distinguish the individual identity of each other.
Face recognition is a personal identification system that uses personal characteristics of a
person to identify the person's identity. Human face recognition procedure basically consists
of two phases, namely face detection, where this process takes place very rapidly in humans,
except under conditions where the object is located at a short distance away, the next is the
introduction, which recognize a face as individuals. Stage is then replicated and developed as
a model for facial image recognition (face recognition) is one of the much-studied biometrics
technology and developed by experts. There are two kinds of methods that are currently
popular in developed face recognition pattern namely, Eigenface method and Fisherface
method. Facial image recognition Eigenface method is based on the reduction of face-
dimensional space using Principal Component Analysis (PCA) for facial features. The main
purpose of the use of PCA on face recognition using Eigen faces was formed (face space) by
finding the eigenvector corresponding to the largest eigenvalue of the face image. The area of
this project face detection system with face recognition is Image processing. The software
requirements for this project is Pycharm software.

Keywords: face detection, Eigen face, PCA, Pycharm

Extension: There are vast number of applications from this face detection project, this project
can be extended that the various parts in the face can be detect which are in various directions
and shapes.

Candidate’s Declaration

ii | P a g e
We hereby declare that the work, which is being presented in the minor project, entitled
“Driver Drowsiness Detection System” in partial fulfilment for the award of Degree of
“Bachelor of Technology” in Department of Computer Science & Engineering with
Specialization in Computer Engineering, and submitted to the Department of Computer
Science & Engineering, Arya Institute of Engineering & Technology, is a record of our
own investigations carried out under the Guidance of Er. Pradeep Jha, Head of
Department, & Er. Kiran Ahuja, Asst. Professor Department of Computer Science &
Engineering.

Aman Anand (16EAYCS008)

Kuldeep Vaishnav (16EAYCS038)

Manish Sharma (16EAYCS047)

iii | P a g e
 TABLE OF CONTENTS
CONTENTS PAGE NO:
COVER PAGE…………………………………………………………………....i
ABSTRACT…………………………………………………………………........ii
Candidate’s Declaration…………………………………………......iii
LIST OF FIGURES……………………………………………………………...vii

1. CHAPTER 1: INRODUCTION…………………………………………..…...1
1.1. FACE RECOGNIZATION…………………………………………………...1
1.1.1 GEOMWTRIC……………………………………………………....1
1.1.2 PHOTOMETRIC………………………………………………........1
1.2 FACE DETECTION………………………………………………………..2
1.2.1 PRE-PROCSSING…………………………………………………...2
1.2.2 CLASSIFICATION………………………………………………….3
1.2.3 LOCALIZATION…………………………………………………....3
2. CHAPTER 2:LITERATURE SURVEY……………………………………..4
2.1.FEATURE BASE APPROCH……………………………………………....4
2.1.1 DEFORMABLE TEMPLATES……………………………………......5
2.1.2 POINT DISTRIBUTION MODEL(PDM)……………………………..6
2.2. LOW LEVEL ANALYSIS…………………………………………………..6
2.3.MOTION BASE……………………………………………………………...8
2.3.1 GRAY SCALE BASE……………………………………………….8
2.3.2 EDGE BASE…………………………………………………………9
2.4 FEATURE ANALYSIS……………………………………………………....9
2.4.1 FEATURE SEARCHING………………………………………..…..9
2.5 CONSTELLATION METHOD………………………………………………10
2.5.1 NEURAL NETWORK………………………………………...……..10
2.6 LINEAR SUB SPACE METHOD…………………………………………...11
2.7 STASTICAL APPROCH………………………………………………….…12
3. CHAPTER 3:DIGITAL IMAGE PROCESSING…………………...………13
3.1. DIGITAL IMAGE PROCESSING………………………………………....13
3.2. FUNDAMENTAL STEPS IN IMAGE PROCESSING……..……………..14
3.3. ELEMENTS OF DIGITAL IMAGE PROCESSING SYSTEM………..….15
3.3.1. A SIMPLE IMAGE FORMATION MODEL………………..…….15
4. CHAPTER 4:FACE DETECTION…………………………………………......….17

4|P a g e
 4.1 FACE DETECTION IN IMAGE…………………………………………..…….17
4.2 REAL TIME FACE DETECTION………………………………………..……..18
4.3 FACE DETECTION PROCESS…………………………………………..……..20
4.4 FACE DETETION ALGORITHM……………………………………….………23
5. CHAPTER 5: FACE RECOGNITION……………………………………………..25
5.1 FACE RECOGNITION USING GEOMETRICAL FEATURES………..……....25
5.1.1 FACE RECOGNITION USING TEMPLATE MATCHING……...……..26
5.2. PROBLEM SCOPE AND SYSTEM SPECIFICATIONS……….....…..………27
5.3 BRIEF OUTLINE OF THE IMPLEMENTED SYSTEM……..…………....…..27
5.4 FACE RECOGNITION DIFFICULTIE………………….………………….….29
5.4.1 INTER CLASS SIMILARITY……………….………………………......30
5.4.2 INTRA CLASS SIMILARITY………….…………………………….….30
5.5 PRINCIPAL COMPONENT ANALYSIS……………………………………….31
5.6 UNDER STANDING EIGEN FACES……..…………………………………….31
5.7 IMPROVING FACE DETECTION USING RECONSTRUCTION………….....35
5.8 POSE INVARIENT FACE RECOGNITION…………………………………….36

6. CHAPTER 6: TECHNOLOGIES USED……………………………………………37

6.1 OPENCV……………………………………………………………………….…37
6.1.1 HISTORY………………………………………………………………...…37
6.1.2 APPLICATION……………………………………………………………..37
6.1.3 PROGRAMMING APPLICATION……………………………………...…38
6.2 KERAS……………………………………………………………………………38
6.2.1 FEATURES…………………………………………………………………39
6.3 TENSORFLOW…………………………………………………………………...39
6.3.1 HISTORY………………………………………………………………...…39
6.3.2 TENSOR PROCESSING UNIT…………………………………………….40
6.3.3 FEATURES…………………………………………………………………41
6.4 PYGAME………………………………………………………………………....41
6.4.1 HISTORY…………………………………………………………………...41
6.4.2 DEVELOPMENT OF VERSION 2………………………………………...41
6.4.3 FEATURES………………………………………………………………....41
6.5 PyCHARM IDE…………………………………………………………………...42
6.5.1 FEATURES………………………………………………………………….42
6.5.2 PLUGINS……………………………………………………………………42
6.5.3 HISTORY………………………………………………………………...…42

5|P a g e
 6.5.4 LICENSING……………………………………………………………….42
7. CHAPTER 7:CODING……………………………………………………………...44
7.1 DROWNINESS CODING………………………………………………………..45
7.2 MODEL CODING………………………………………………………………..45

8. CONCLUSION………………………………………………………………………47

9. REFERENCES ………………………………………………………………………49

6|P a g e
 LIST OF FIGURES
1.2 FACE DETECTION ALGORITHM……………………………………..………...2
2.1 DETECTION METHODS……………………………………...………..…….......4
2.2 FACE DETECTION…………………………………………........………..…........7
3.1 FUNDAMENTAL STEPS IN DIGITAL IMAGE PROCESSING…………..…...14
3.2 ELEMENTS OF DIGITAL IMAGE PROCESSING SYSTEM………………….15
5.1 A SUCCESSFUL FACE DETECTION IN AN IMAGE WITH A FRONTAL
VIEW OF A HUMAN……………..........................................................………….….....17
5.2.1 FRAME 1 FROM CAMERA……………………………………………………..19
5.2.2 FRAME 2 FROM CAMERA……………………………………………….…….19
5.2.3 SPATIO - TEMPORALLY FILTERED IMAGE………….………………….….19
5.3 FACE DETECTION……………………… ………………………………..…....20
5.3.1 AVERAGE HUMAN FACE IN GREY-SCALE………………………………...20
5.3.2 AREA CHOSEN FOR FACE DETECTION………………………………….…21
5.3.3: BASIS FOR A BRIGHT INTENSITY INVARIANT SENSITIVE TEMPLATE21
5.3.4 SCANED IMAGE DETECTION……………………………….....…………..….22
5.4 FACE DETECTION ALGORITHM……………………………..……….………23
5.4.1 MOUTH DETECTION…………………………………………....……………...23

5 .4.2 NOISE DETECTION………………………………………..…………...………23

5.4.3 EYE DETECTION……………………………………………………….……….24

6.1.1 FACE RECOGNITION USING TEMPLATE MATCHING…………...….....…26

6.3 IMPLEMENTED FULLY AUTOMATED FRONTAL VIEW FACE DETECTION

MODEL………………………………………………………………………..…………..27

6.3.1: PRINCIPAL COMPONENT ANALYSIS TRANSFORM FROM 'IMAGE SPACE'

TO 'FACE SPACE'…………………………………………………………..…………….28
6.3.2 FACE RECOGNITION……………………………………………………..………………..29
6.4.1 FACE RECOGNITION TWINS AND FATHER AND SON……..………………………..30
6.6.0 A 7X7 FACE IMAGE TRANSFORMED INTO A 49 DIMENSION VECTOR..….31
6.6.1 EIGENFACES…………………………………………………………………...…...32
6.6.3 POSE INVARIANT FACE RECOGNITION…………………………………..……..34

7|P a g e
8|P a g e