You are on page 1of 9

DECLARATION BY THE CANDIDATE

I, the undersigned, solemnly declare that the report of the thesis work entitled
“FOGGY IMAGE CLEARANCE AND VEHICLE NUMBER PLATE
IDENTIFICATION USING PYTHON” is based on my own work carried out during
the course of my study under the supervision of Sachin Harne, Assistant Professor
(Computer Science & Engineering).
I assert that the statements made and conclusions drawn are an outcome of the
project work. I further declare that to the best of my knowledge and belief that the
report does not contain any part of any work which has been submitted for the award of
any other degree/diploma/certificate in this university/deemed university of India or any
other country.

_______________________

(Signature of the Candidate)


Kavita Patel
Roll No: 502902218001
Enrollment No.:AN4793

_______________________
(Signature of the Supervisor)
Sachin Harne
Asst. Proff. (CSE),
RSR RCET, Bhilai (C.G.)

I
CERTIFICATE OF THE SUPERVISOR

This is to certify that the report of the thesis entitled “FOGGY IMAGE CLEARANCE
AND VEHICLE NUMBER PLATE IDENTIFICATION USING PYTHON” is a record
of bonafide research work carried out by Kavita Patel, bearing Roll No.: 502902218001 &
Enrollment No. : AN4793 under my guidance and supervision for the award of Degree of
Master of Technology in Computer Science & Engineering of Chhattisgarh Swami
Vivekanand Technical University, Bhilai (C.G.), India.

To the best of my knowledge and belief the thesis

 Embodies the work of the candidate himself,


 Has duly been completed,
 Fulfills the requirement of the Ordinance relating to the Master of Technology degree of
the University, and
 Is up to the desired standard both in respect of contents and language for being referred
to the examiners.

_______________________

(Signature of the Supervisor)


Sachin Harne
Asst. Proff.(CSE),
RSR RCET, Bhilai (C.G.)

Forwarded to Chhattisgarh Swami Vivekanand Technical University Bhilai

_______________________
(Signature of the Principal)
Dr. S. V Deshmukh
Principal
RSR RCET, Bhilai (C.G.)

II
CERTIFICATE BY THE EXAMINERS

The thesis entitled “FOGGY IMAGE CLEARANCE AND VEHICLE NUMBER PLATE
IDENTIFICATION USING PYTHON”, submitted by Kavita Patel (Roll No.:
502902218001 & Enrollment No: AN4793) has been examined by the undersigned as a part
of the examination and is hereby recommended for the award of the degree of Master of
Technology in Computer Science & Engineering of Chhattisgarh Swami Vivekanand
Technical University, Bhilai (C.G).

Internal Examiner External Examiner


Date: Date:

III
ACKNOWLEDGEMENT
I would like to thank my guide Sachin Harne, Assistant Professor (Computer
Science & Engineering) for his immense support and enlightened guidance for my
project which I have developed as an M. Tech. Scholar. I am very grateful for the
inspiring discussions with all my faculties. Their valuable support and path-guiding
suggestions have helped me to develop this project.

I owe the greatest debt and special respectful thanks to Shree Sanjay Rungta Ji,
Chairman, Mr. Saket Rungta, Director, Mohd. Shajid Ansari, Assistant Director, Dr.
S. V. Deshmukh, Principal, RSR Rungta College of Engineering and Technology,
Bhilai, for their inspiration and constant encouragement that enabled me to present my
work in this form.

I would like to take this opportunity to express my thanks towards everyone in


the Computer Laboratory of the RSR Rungta College of Engineering and Technology,
Bhilai.

I specially thank my colleagues, batch mates, and friends for their support and
help that they offered me during the course of development of this project.

_______________________

(Signature of the Candidate)


Kavita Patel
RSR Rungta College of Engineering &
Technology, Bhilai (C.G.)

IV
ABSTRACT

Because of enormous development of communication media and technology, today it's


Number plate detection algorithm is mainly categorized into three classes: edge-based, color
based and texture based. License plate location algorithm based on edge detection and
morphology are describe to locate the number plate, first identify whether any noise is present
in the plate. In the field of computer and machine vision, haze and fog lead to image
degradation through various degradation mechanisms including but not limited to contrast
attenuation, blurring and pixel distortions. This limits the efficiency of machine vision
systems such as video surveillance, target tracking and recognition. Various single image dark
channel dehazing algorithms have aimed to tackle the problem of image hazing in a fast and
efficient manner. Such algorithms rely upon the dark channel prior theory towards the
estimation of the atmospheric light which offers itself as a crucial parameter towards
dehazing. This paper describes the use of sobel technique and image morphing for number
plate detection and ocr technique is used to extract the number of the vehicle.

V
LIST OF FIGURES

S.NO FIGURE DESCRIPTION PAGE. NO.


1 Figure 1.5 Rain streak removal from a single image 2
2 Figure 4.1 masks used by the sobel operator 19
3 Figure 5.1 Result of dehaze number plate 36
4 Figure 5.2 Image processing using sobel technique 36
5 Figure 5.3 Thresholding the given image 37
6 Figure 5.4 Morphed the image to extract the number plate 37
7 Figure 5.5 Extracted number plate 37
8 Figure 5.6 Result of dehaze number plate 38

VI
LIST OF ABBREVIATIONS

DCP Dark Channel Prior


SDCP Simplified Dark Channel Prior
HT Hough Transform
CHT Circular Hough Transform
DIP Digital Image Processing
MRF Markov Random Field
RGB Red, Green, Blue
BGIF Basic Guided Image Filter
PAF Proposed Adaptive Filter
OEA Object Extraction Algorithm
LLF Local Laplacian Filter
WGIF Weighted Guided Image Filter
GD Gaussian Distribution
CCD Charge-Coupled Device

VII
TABLE OF CONTENTS
DECLARATION BY THE CANDIDATE I
CERTIFICATE OF THE SUPERVISOR II
CERTIFICATE BY THE EXAMINERS III
ACKNOWLEDGEMENT IV
ABSTRACT V
LIST OF FIGURES VI
LIST OF TABLES VII
LIST OF ABBREVIATIONS VIII
TABLE OF CONTENTS IX
Chapter 1
INTRODUCTION 1-18
1.1 Overview 1
1.2 Single Image De-raining 2
1.3 Layer Separation Methods 3
1.4 Sparsity-based Methods 3
1.5 Security Services in Detail 4
1.6 Gaussian Mixture Model-based Methods 4
1.7 Deep Learning-based Methods 4
1.8 Single Image Dehazing 5
1.9 Honey Encryption 6
1.10 Password Management in Honey Encryption 6
1.11 Heterogeneous Face Recognition 7
1.12 Generative Adversarial Networks (GANs) 9
1.12.1 Applications of GANs 10
1.12.2 Perceptual Loss Function 10
1.12.3 Low-rank Representation-based Methods 11
1.12.4 Gaussian Mixture Model-based Methods 11
1.12.5 Deep Learning-based Methods 12
1.13 Single Image Dehazing 12
1.14 Heterogeneous Face Recognition 13
Chapter 2

LITREATURE REVIEW 16-21


Chapter 3

VIII
PROBLEM IDENTIFICATION 22-23
3.1 Security Problems Identified in Message Communication 16
3.1.1Brute Force attack 16
3.1.2 Impersonation attack 16
3.1.3 Man in middle attack 16
3.1.4 Side channel attack 16
3.2 Security Threats 17
3.2.1 Privacy Issues 17
3.2.2 Identity Issues 17
3.2.3 Malware in Transferred Files 17
3.2.4 Client Security Bugs 17
Chapter 4
PROPOSED METHODOLOGY 24-32
4.1 Design Challenges 24
4.2 Data collection 24
4.3 Expected Impact 25
4.4 Fog removal approach 25
4.4.1 Koschmieder’s law 26
4.4.2 Beer law for transparent objects 26
4.4.3 Edge detection 27
4.4.4 Circle detection 27
4.4.5 Car detection 28
4.5 Image Processing 29
4.6 Image dehazing 30
4.7 Morphing 30
Chapter 5
IMPLEMENTATION AND RESULT ANALYSIS 33-39
5.1 Implementing Proposed Messaging Application in Android 33
5.2 Experimental Results 36
Chapter 6
CONCLUSION 40
Chapter 7
FUTURT SCOPE 41
LIST OF PUBLICATIONS 42
REFERENCES 43-47

IX

You might also like