You are on page 1of 10

ACKNOWLEDGEMENT

No Endeavour is possible in Solitude. It requires help, guidance and moral


support at each step. Therefore, we would like to thank our Head of
Department, Mr. Pradyut Kala for providing us with the right platform to
work on this project. We would thank our Official Project Guide, Mr.Sachin
Tyagi, who helped us clearing all our doubts while doing this project.
We would also like to thank the faculty of the CMC Ltd. for all the help they
provided to us.
Lastly, we would thank our families for all the moral support they provided
to us, for the successful completion of our project.

Harsh Gupta

Arjun Singh

Amit Bhati

iii

TABLE OF CONTENTS
CHAPTER NO.

1.

2.

3.

TITLE

PAGE NO.

LIST OF TABLES

vii

LIST OF FIGURES

viii

ABSTRACT

xi

INTRODUCTION

1.1

Introduction

1.2

Need of This Project

1.3

Significance of This Project

1.4

The General Proposed System

1.4.1 Input Image From Camera

1.4.2 Preprocessing

1.4.3 Number Plate Localisation

1.4.4 Character Segmentation

1.4.5 Character Recognition

1.4.6 Display Output

LITERATURE REVIEW

2.1

License Plate Detection

2.2

Character Segmentation

2.3

Character Recognition

FUNDAMENTALS OF IMAGE PROCESSING

12

3.1

Reading Images

12

3.2

Displaying Images

14

3.3

Writing Images

16

3.4

Classes

17

3.5

Image Types

17
iv

3.5.1 Grayscale Images

17

3.5.2 Binary Images

18

Format of Images

18

3.6.1 RGB Format

18

3.6.2 YCbCr Format

18

MATLAB IMPLEMENTATION

20

4.1 Introduction

20

4.2 Convert a Color Image into Gray Image

21

4.3 Dilate an Image

22

4.4 Preprocessing

22

4.5 Segmentation

23

4.6 Region of Interest Extraction

24

GRAPHICAL USER INTERFACE

25

5.1 Theory

25

AUTOMATIC NUMBER PLATE RECOGNITION

32

6.1 Module 1: Input Image

32

6.2 Module 2: Pre-Processing

35

6.3 Module 3: Number Plate Localization

38

6.4 Module 4: Character Segmentation

40

6.5 Module 5: Character Recognition

43

6.6 Module 6: Display Output

44

7.

CONCLUSION

48

8.

FUTURE SCOPE

49

A1.

RGB Color Sensing Technique

47

1.1 What is RGB

47

1.2 Color Identification

48

1.3 Color and Light

49

1.4 Color Sensor

49

1.5 True Color Recognition

50

1.6 Color Mark Detection

50

3.6

4.

5.
6.

A2.

A3.

A4.

1.7 Sorting

50

1.8 Color Sensing Applications

51

HOUGH TRANSFORMATION

53

2.1 Introduction

53

2.2 Implementation

54

2.3 Result

60

MATHEMATICAL MORPHOLOGY

62

3.1 Introduction

62

3.2 Binary Morphology

63

3.3 Basic Operators

63

3.4 Grayscale Morphology

67

3.5 Mathematical Morphology on Complete Lattices

68

RADIAL BASED FUNCTION NEURAL NETWORK 70


4.1 Introduction

70

4.2 RBFNN Classification

70

4.2.1 Radial Basis Function

70

4.2.2 Radial Basis Function Network

71

4.2.3 Network Architecture

72

4.3 Normalized Architecture

74

vi

LIST OF TABLES

TABLE NO.

TITLE

PAGE NO.

Table 3.1

Tools Associated With Image Tool

16

Table 3.2

Classes used for image processing in MATLAB

17

Table 5.1

GUI Control Elements

25

vii

LIST OF FIGURES

FIGURE NO.

TITLE

PAGE NO.

Fig 1.1

Basic BLOCK Diagram

Fig 2.1

Three Step Framework

Fig 3.1

Image Appears on MATLAB Desktop

14

Fig 3.2

The Image Tools

15

Fig 3.3

Representation of Pixels in RGB Format

18

Fig 3.4

Representation of Pixels in YCbCr Format

19

Fig 4.1

Flowchart of License Plate Detection Algorithm

20

Fig 4.2

Original Colored Image

21

Fig 4.3

Gray Image

21

Fig 4.4

Dilated Image

22

Fig 4.5

Input Image without Noise

23

Fig 4.6

Output of Segmentation

23

Fig 4.7

Segmented License Plate

24

Fig 5.1

Basic GUI

26

Fig 5.2

Interface Window

26

Fig 5.3

Tools

27

Fig 5.4

GUI Consists of Static Text

27

Fig 5.5

Property Inspector Window(a)

27

Fig 5.6

Property Inspector Window(b)

28

Fig 5.7

Property Inspector Window(c)

28

Fig 5.8

Modified GUI

28

Fig 5.9

Editor Window

30

Fig 5.10

MATLAB GUI(a)

30
viii

Fig 5.11

MATLAB GUI(b)

31

Fig 5.12

MATLAB GUI(c)

31

Fig 6.1

Image after Initialization of camera

33

Fig 6.2

Image after Binarization

35

Fig 6.3

Image after Noise Removal

37

Fig 6.4

Extracted License Plate

39

Fig 6.5

Segmented License Plate (a)

41

Fig 6.6

Segmented License Plate(b)

41

Fig 6.7

Segmented License Plate(c)

41

Fig 6.8

Recognized Characters

43

Fig 6.9

Final Output Screen

44

Fig A1.1

Spectrum of Light

49

Fig A2.1

Coordinate System

54

Fig A2.2

Plot for r>0 & 0<<2

55

Fig A2.3

Combined Plot

56

Fig A2.4

Input Image

60

Fig A2.5

Result

61

Fig A3.1

A shape (in blue) and its morphological dilation

62

(in green) and erosion (in yellow) by a diamondshaped structuring element


Fig A3.2

The erosion of the dark-blue square by a disk,

63

resulting in the light-blue square


Fig A3.3

The dilation of the dark-blue square by a disk,

64

resulting in the light-blue square with rounded


corners
Fig A3.4

The opening of the dark-blue square, resulting in

65

the light-blue square with round corners


Fig A3.5

The closing of the dark-blue shape (union of two


squares) by a disk, resulting in the union of the
dark blue shape and the light-blue areas
ix

65

Fig A3.6

Watershed of the gradient of the cardiac image

67

Fig A4.1

Architecture of RBFNN

71

Fig A4.2

Two unnormalized radial basis functions in one

72

input dimension. The basis function centers are


located at c1=075 and c2= 3.25
Fig A4.3

Two normalized radial basis functions in one

73

input dimension. The basis function centers are


located at c1=0.75 and c2=3.25
Fig A4.4

Three normalized radial basis functions in one

73

input dimension. The additional basis function


has center at c3=2.75
Fig A4.5

Four normalized radial basis functions in one


input dimension. The fourth basis function has
center at c4=0

73

ABSTRACT
With the increasing number of vehicles on roads, it is getting difficult to
manually enforce the laws and traffic rules. For smooth traffic flow, the
Automatic Vehicle Identification techniques for prosecuting offenders are
used. Toll-booths are constructed on freeways and parking structures, where
the car has to stop to pay the toll or parking fees. Also, Traffic Management
systems are installed on freeways to check for vehicles moving at speeds not
permitted by law. All these processes have a scope of improvement. In the
centre of all these systems lies a vehicle. In order to automate these
processes and make them more effective, a system is required to easily
identify a vehicle.
Vehicles in each country have a unique license number, which is written on
its license plate. This number distinguishes one vehicle from the other, which
is useful especially when both are of same make and model.
Automatic Vehicle Identification (AVI) has many applications in traffic
systems (highway electronic toll collection, red light violation enforcement,
border and customs checkpoints, etc.). License Plate Recognition is an
effective form of AVI systems. In this study, a smart and simple algorithm is
presented for vehicles license plate recognition system. The proposed
algorithm consists of three major parts: Extraction of plate region,
segmentation of characters and recognition of plate characters. For extracting
the plate region, edge detection algorithms and smearing algorithms are
used. In segmentation part, smearing algorithms, filtering and some
morphological algorithms are used. And finally statistical based template
matching is used for recognition of plate characters. The performance of the
proposed algorithm has been tested on real images. Based on the
experimental results, we noted that our algorithm shows superior
performance in car license plate recognition.
xi

xii