INTELLECTUAL ANALYSIS OF STUDENT'S OBSERVATION USING DATA MINING AND PATTERN MATCHING A PROJECT REPORT Submitted by PRADHEEBA.B (422711104060) SASIREKA.R (422711104082) VANMATHI.S (422711104100) In partial fulfilment for the award of the degree of BACHELOR OF ENGINEERING in COMPUTER SCIENCE AND ENGINEERING V.R.S. COLLEGE OF ENGINEERING AND TECHNOLOGY ARASUR ANNA UNIVERSITY::CHENNAI 600 025 APRIL 2015 ANNA UNIVERSITY:CHENNAI 600 025 BONAFIDE CERTIFICATE
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
INTELLECTUAL ANALYSIS OF STUDENT'S OBSERVATION
USING DATA MINING AND PATTERN MATCHING
A PROJECT REPORT
Submitted by
PRADHEEBA.B (422711104060)
SASIREKA.R (422711104082)
VANMATHI.S (422711104100)
In partial fulfilment for the award of the degree
of
BACHELOR OF ENGINEERING
in
COMPUTER SCIENCE AND ENGINEERING
V.R.S. COLLEGE OF ENGINEERING AND TECHNOLOGY
ARASUR
ANNA UNIVERSITY::CHENNAI 600 025
APRIL 2015
ANNA UNIVERSITY:CHENNAI 600 025
BONAFIDE CERTIFICATE
Certified that this project report “INTELLECTUAL ANALYSIS OF
STUDENT'S OBSERVATION USING DATA MINING AND PATTERN
MATCHING”is the bonafide work of R.SASIREKA
[422711104082] who carried out the project work under my supervision.
SIGNATURE SIGNATURE
Mr. A.PARTHASARATHY, Prof. J.K.JOTHIKALPANA,
M.E., MBA., (Ph.D.,) M.Tech., (Ph.D.,)
HEAD OF THE DEPARTMENT SUPERVISOR
Associate Professor, Professor,
Department of Computer Department of Computer
Science and Engineering Science and Engineering
V.R.S. College of Engineering V.R.S. College of Engineering
and Technology, and Technology,
Arasur - 607107. Arasur - 607107.
Submitted for the University Examination held on 8.4.2015
INTERNAL EXAMINER EXTERNAL EXAMINER
ACKNOWLEDGEMENT
We express our sincere deep sense of gratitude to our project guide
Prof.J.K.Jothi Kalpana M.Tech.,(Ph.D.,) Associate Professor, Department
of Computer Science and Engineering, for her proficient and meticulous to
consummate our project.
We acknowledge our grateful and sincere thanks to our project co-
coordinator and Head of the Department Mr.A.Parthasarathy M.E,
M.B.A.,(Ph.D)., Computer Science and Engineering for his valuable
suggestions and help toward us.
With profoundness, we are indebted to our Principal
Dr.N.Anbazhaghan M.E.,Ph.D., for giving constant motivation in
succeeding our goal.
We extend our deep sense of thanks to our Chief Executive Officer
Er.M.Saravanan M.E (Ph.D)., for providing us an opportunity to take up his
valuable advice to develop technical knowledge in planning our project
confidently.
We express our extreme gratitude and heart full thanks to our Chair
Person Tmt.Vijaya Muthuvanan Secretary and Correspondent
Rtn.S.R.Ramanathan and Director, Board of Governor
Thiru.N.Muthuvanan for providing facilities to do our project successfully.
We wish to express our sincere thanks to all those who helped us in
making this project successful.
ABSTRACT
In this project a fatigue detection technique is based on
computer vision. Fatigue is detected from face and facial features of
student. Hybrid method is used for face and facial feature detection which
not only increase the accuracy of the system but also decrease the
processing time. Skin colour pixels detection and viola Jones methods is
used for face detection and knowledge based division method is used to
increase the accuracy of facial feature detection. Also a dynamic
threshold value is used for yawning and eyes status detection.
This also addresses two issues for mitigating student
distraction/inattention by using novel video analysis techniques: (a) inside
an ego class room, student inattention is monitored through first tracking
students face/eye region using particle filters, followed by recognition of
dynamic eye states using computer vision system. Frequencies of eye
blinking and eye closure are used as the indication of sleepy and warning
sign is then generated for recommendation; (b) outside an ego class room
is analysed. Surrounding class rooms (in both directions) are tracked, and
their states are analyzed by sensors. These pieces of information are
provided for mitigating student’s inattention. The main novelties of the
proposed scheme include facial geometry based eye region detection for
eye closure identification, combined tracking and detection of class
rooms.
CHAPTER NO. TITLE
PAGE NO.
ABSTRACT
i
LIST OF FIGURES
ii
LIST OF TABLES
iii
LIST OF ABBREVATIONS
iv
1 INTRODUCTION
1
1.1 Objectives
1
2 LITERATURE REVIEW
2
2.1 EXISTING SYSTEM
2
2.1.1 Demerits of Existing System
2
2.2 PROPOSED SYSTEM
2
2.2.1Merits of Proposed System
3
2.3 APPLICATIONS
3
2.4 BLOCK DIAGRAM
4
TABLE OF CONTENTS
4 SOFTWARE PROFILE
6
4.1 INTRODUCTION
6
4.2 DEFINITION OF MATLAB
7
4.2.1 Starting MATLAB
7
4.2.2 Setting your initial current
directory
8
4.2.3 Setting up MATLAB
environment options
8
4.2.4 Configuration certain
products
8
4.2.5 Excel link versions
9
4.2.6 Finding information about
MATLAB
10
4.2.7 Syntax 11
3 SYSTEM REQUIREMENTS 5
3.1HARDWARE REQUIREMENT
5
3.2 SOFTWARE REQUIREMENT 5
4.2.8 Variables
11
4.2.9 Vectors/Matrices 12
4.2.10 Graphical User Interface
Programming
15
4.2.11Object Oriented
Programming
17
4.2.12 Interfacing with other
Languages
17
4.2.13 License 18
4.2.14 Alternatives 19
5 COMPUTER VISION TOOL
BOX
20
5.1COMPUTER VISION SYSTEM
TOOL BOX
20
5.2 IMAGE PROCESSING TOOL
BOX
21
5.3REGION OF INTEREST 22
6 MODULE DESCRIPTION
23
6.1 DETECTED FACIAL
FEATURES IN FACE REGION
23
6.2 DETECTION OF OPEN EYES 24
6.3DETECTION OF CLOSED 26
EYES
6.4 FACE AND MOUTH
DETECTION
28
7 CONCLUSION
34
8 FUTURE ENHANCEMENT
35
APPENDIX I
36
APPENDIX II
39
REFERENCES
43
LIST OF FIGURES
FIGURES NO. TITLE PAGE NO.
2.4 Block Diagram 04
4.1 Three dimensional
graphics
15
4.2 Normalized sinc function 16
4.3 Unnormalized sinc
function
16
6.1 Detected Facial Feature
In Face Region
24
6.2 Detection of Open Eyes 25
6.3 Detection of Closed Eyes 28
6.4 Face detection using
viola Jones method on
from skin color region.
31
6.5 Face and facial feature
detection.
32
ii
LIST OF TABLES
TABLE NO. TITLE PAGE NO.
4.1 Product and
Commands
9
4.2 Excel file used with
Excel Version
9
4.3 Finding information
about matlab
10
6.3 Yawning state 27
6.6 Detection of yawning
state of test users.
33
6.7 Closed Eyes Detection of
Test Users.
34
iii
LIST OF ABBREVATIONS
MATLAB MATrix LABoratory
GPU Graphics Processing Unit
DCT Discrete Cosine Transform
FFT Fast Fourier Transform
LINPACK Linear Pack
EISPACK EIgen System PACKage
LAPACK Linear Algebra PACKage
IDL Interactive Data Language
APL Applied Physics Letter
IL ILlinois
GUIDE GUI Development Environment
CHAPTER 1
INTRODUCTION
Now a days the students’ mentality is changed based on their interest in
studies. In the class room the staff members going to deliver lecture class and
observe how the students’ can understand the concept. For students the class
should be interesting and more interactive when the staff delivers the lecture.
From this we can analyze the average student face and their eyes; finally we
conclude both the qualitative and quantitative results.
When a face image is act as a input to the system, face detection will be
performed to locate the rough face region. The second step is to locate two
rough regions of eyes in the face. There are two default eye states: open and
closed. In our project we are going to discuss about four different stages like
Partially opened, Fully opened, and Fully closed. If a man can see something, it
is considered that his eyes are open. Our criterion is that if the iris and the white
of eye are visible, the eye is open. Otherwise, the eye is closed. The student data
is compared with student eye. The CGPA (Cumulative Grade Point Average)
attribute in the data set contains a large number of continuous values. For
example, we grouped all GPAs into five categorical segments; Excellent, Very
good, Good, Average and Poor.
1.1 OBJECTIVE
The main objective of our project was to analyze the student performance
in a class room. From this we are going to track the face, detect the eye region,
detect the mouth region whether the eye is opened or not and mouth is
yawning.
CHAPTER 2
LITERATURE REVIEW
2.1 EXISTING SYSTEM
In the existing system the Riemannian Manifold is impossible to give
the output and this give more time for the calculation. For differentiable
manifolds, it is impossible to define the derivatives of the curves on the
manifold.
2.1.1 Demerits of Existing System
• Speculiar output is impossible
• More time efficient should take for calculations
• This cannot be designed for any other objects
2.2 PROPOSED SYSTEM
In the proposed system we are using the students face for the analysis.
From this analysis the student face is tracked and eye is detected for the
execution. We are using the Viola-Jones algorithm for the face tracking
system.
The fatigue detection system consists of 6 levels which can be classified
as
• Image acquisition
• Face detection
• Facial features detection
• Eyes status detection
• Yawning status detection
• Drowsiness detection
2.2.1 Merits of Proposed System
• Extremely fast feature computation.
• Efficient feature selection.
• Scale and location invariant detector.
• Instead of scaling the image itself (e.g. pyramid-filters), we scale
the features.
2.3 APPLICATIONS
• It can be used in schools ,colleges and other institutions.
• It is used in railways, airways and roadways.
• It is used for analysis of face.
2.4 BLOCK DIAGRAM
Fig. 2.4 Block Diagram
CHAPTER 3
REQUIREMENTS SPECIFICATION
3.1 HARDWARE REQUIREMENTS
The hardware requirements may serve as the basis for a contract for the
implementation of the system and should therefore be a complete and consistent
specification of the whole system. It is used by software engineers as the
starting point for the system design. It should what the system do and how it
should be implemented.
• Processor : core i3
• RAM : 5.2 GHz
• Hard Disk : 40 GB and Above.
• Monitor : 15" COLOR
• Web Camera : 9 megapixels(MP)
3.2 SOFTWARE REQUIREMENTS
The software requirement document is the specification of the system. It
should include both a definition and a specification of requirements. The basis
of creating the software. It is useful in estimating cost, planning team activities,
performing tasks and tracking the teams and tracking the team progress
throughout the development activity.
• MATLAB 8.1.0 Version R2013a
• Window 7
CHAPTER 4
SOFTWARE PROFILE
4.1 INTRODUCTION
Cleve Moler, the chairman of the computer science department at the
University of New Mexico, started developing MATLAB in the late 1970s. He
designed it to give his students access to LINPACK and EISPACK without
them having to learn Fortran. It soon spread to other universities and found a
strong audience within the applied mathematics community. Jack Little, an
engineer, was exposed to it during a visit Moler made to Stanford University in
1983. Recognizing its commercial potential, he joined with Moler and Steve
Bangert. They rewrote MATLAB in C and founded MathWorks in 1984 to
continue its development. These rewritten libraries were known as JACKPAC.
In 2000, MATLAB was rewritten to use a newer set of libraries for matrix
manipulation, LAPACK.
MATLAB was first adopted by researchers and practitioners in control
engineering, Little's specialty, but quickly spread to many other domains. It is
now also used in education, in particular the teaching of linear algebra,
eye=rgb2gray(eye); eye=im2bw(eye,.15); %imshow(eye); [m,n]=size(eye); White_pix=0; Black_pix=0; for j=1:n
for i=1:m if eye(i,j)==1 White_pix=White_pix+1; else Black_pix=Black_pix+1; end end end
Black_pix
mouth=rgb2gray(mouth); mouth=im2bw(mouth,.15); %imshow(eye); [mm,nn]=size(mouth); White_pix1=1; Black_pix1=1; for j=1:nn for i=1:mm if mouth(i,j)==1 White_pix1=White_pix1+3; else Black_pix1=Black_pix1+3; end end end Black_pix1 if Black_pix < 1000 || Black_pix1 < 1000 msgbox('Alert! Alert!'); end
pause(.100)
nFrame = nFrame+1; end %% Clearing Memory release(hVideoIn); % Release all memory and buffer used release(vidDevice);