RUNNING VEHICLE NUMBER PLATE DETECTION

Candidate Name : VASA DEVA NAGA YESU BABU

Regd.No : 2141129
RUNNING VEHICLE NUMBER PLATE DETECTION
Report Submitted to
D.N.R. COLLEGE, P.G. COURSES (AUTONOMOUS)
for the award of the degree

of

MASTER OF COMPUTER APPLICATIONS

by
VASA DEVA NAGA YESU BABU
REGD. No: 2141129

Under the Guidance of

Sri.K.Rambabu MCA,M.Tech
HOD,Assistant Professor

DEPARTMENT OF COMPUTER APPLICATIONS

D.N.R COLLEGE, P.G. COURSES (AUTONOMOUS)
(AFFILIATED TO ADIKAVI NANNAYA UNIVERSITY)
BHIMAVARAM-534202
SEPTEMBER-2023
 DEPARTMENT OF COMPUTER APPLICATIONS
D.N.R COLLEGE, P.G. COURSES (AUTONOMOUS)
(AFFILIATED TO ADIKAVI NANNAYA UNIVERSITY)
BHIMAVARAM-534202

CERTIFICATE
This is to certify that the project Report entitled, “Running vehicle number plate detection”
submitted by Mr. “Vasa Deva Naga Yesu Babu” to “D.N.R. College, P.G. Courses (Autonomous)”,
affiliated to “Adikavi Nannaya University”, Rajahmahendravaram, Andhra Pradesh, India, is a record
of bonafide Project work carried out by him/her under my/our supervision and guidance and is worthy
of consideration for the award of the degree of Master of Computer Applications.

Date:

Internal Guide Head of the Department

External Examiner Internal Examiner

 DECLARATION

I certify that
a. The work contained in this report is original and has been done by me under the guidance of my
supervisor(s).
b. The work has not been submitted to any other Institute for any degree or diploma.
c. I have followed the guidelines provided by the university in preparing the report.
d. I have conformed to the norms and guidelines given in the Ethical Code of Conduct of the Institute.
e. Whenever I have used materials (data, theoretical analysis, figures, and text) from other sources, I
have given due credit to them by citing them in the text of the report and giving their details in the
references. Further, I have taken permission from the copyright owners of the sources, whenever
necessary.

(Vasa Deva Naga Yesu Babu)

Regd.No: 2141129
 ACKNOWLEDGEMENT

I would like to take the privilege of the opportunity to express my gratitude into Project work of
“Running Vehicle Number Plate Detection project” enabled me to express my thanks to
Mr. K.Rambabu,HOD, Assistant Professor, Department of Computer Applications, D.N.R College,
P.G. Courses, for guidance since the project started. I feel that it is a great privilege of completing my
project under his/her guidance.
I owe my gratitude to Mr.K.Rambabu MCA,M.Tech, our beloved Head of the Department,
Department of Computer Applications, D.N.R College, P.G. Courses, for being a source of
inspiritinand encouraging me in successful completion of the project work.
I am thankful to our Honorable Principal , D.N.R College , P.G. Courses, Smt.
Dr.B.S.Santha Kumari ,Who has shown keen interest and encouraged me by providing all the
facilities to complete my project successful.
I wish to express my sincere thanks to our Management by providing all the facilities and
infrastructure to complete my project successfully and I wish to express my sincere thanks to all
Teaching and Non-Teaching staff of Department of Computer Applications, D.N.R College, P.G.
Courses.
I am very thankful to all my friends and my family members who had given me good co-
operation and Suggestion throughout this project and helped me in successful completion.

Vasa Deva Naga Yesu Babu

Regd.No: 2141129
 INDEX
S.No CONTENT PAGE.No
ABSTRACT
1. INTRODUCTION 1
2. LITERATURE SURVEY 4
2.1 INTRODUCTION 5
2.2 PAPER 1 5
2.3 PAPER 2 6
2.4 PAPER 3 8
2.5 PAPER 4 9
2.6 PAPER 5 10
3. SYSTEM DESIGN AND ANALYSIS 12
3.1 SYSTEM DESIGN 13
3.2 EXISTING SYSTEM 16
3.3 PROPOSED SYSTEM 19
3.4 PROJECT REPORT METHODOLOGY 21
3.5 SYSTEM REQUIREMENT AND SPECIFICATION 22
3.6 FUNCTIONAL REQUIREMENT 23
3.6.1 NON-FUNCTIONAL REQUIREMENT 23
3.6.2 HARDWARE REQUIREMENT 24
3.7 SOFTWARE REQUIREMENT 25
3.8 FEASI ILITY STUDY 27
3.8.1 ECONOMICAL STUDY 27
3.8.2 TECHNICAL STUDY 27
3.8.3 SOCIAL STUDY 27
3.9 INPUT DESIGN 28
3.10 OUTPUT DESIGN 29
4. IMPLEMENTATION 30
4.1 SOFTWARE REQUIREMENT 31
4.1.1 DIGITAL IMAGE PROCESSING 31
4.1.2 OPTICAL CHARACTER RECOGNIZATION 34
4.1.3 WEB CRAWKER 37
4.1.4 DATABASE 38
4.1.5 GUI 43
4.1.6 OPEN CV 45
4.1.7 TESSERACT ENGINE 48
4.2 SAMPLE CODE 49
4.2.1 ALGORITHM 49
4.2.2 MAIN PROGRAM 51
5. SYSTEM TESTS AND SCREENSHOTS 56
5.1 SYSTEM TESTING 57
5.1.1 UNIT TESTING 57
5.1.2 INTEGRATION TESTING 57
5.1.3 FUNCTIONAL TESTING 57
5.1.4 SYSTEM TESTING 58
5.1.5 WHITE BOX TESTING 58
5.1.6 BLACK BOX TESTING 58
5.2 SCREENSHOTS 60
6. CONCLUSION AND FUTURESCOPE 63
7. REFERENCES 65
 LIST OF FIGURES

Figure No. Figure Name Page No.

2.2 Performance Matrix Diagram 7

3.1 System Architecture Diagram 13

3.1.1 Use Case Diagram 15

3.1.2 Data Flow Diagram 15

4.1.7 Tesseract Architecture Diagram 47

 LIST OF SCREENSHOTS

FIGURE FIGURE NAME PAGE

NO. NO.
5.2.1 Input from video or photo 54
5.2.2 Input dividing into no. of frames 55
5.2.3 Output screens 56
RUNNING VEHICLE NUMBER PLATE DETECTION
ABSTRACT
ABSTRACT

The Number Plate Recognition System using OpenCV is a Python-based project that utilizes
the OpenCV library to detect and identify license plates in images and videos. The system
employs a trained Haar cascade model provided by OpenCV specifically designed for license
plate detection. The project consists of two main components: readimage.py and readvideo.py.

The readimage.py file is responsible for detecting number plates from an input image. It applies
the trained Haar cascade model to locate the license plate, draws a boundary around it, and
blurs the plate for privacy. The system then extracts the text from the plate using optical
character recognition (OCR) techniques, enabling the identification of the license plate's
content.

Similarly, the readvideo.py file extends the functionality to process video files. It analyzes each
frame of the video, detects license plates, and performs the same identification process as in the
image detection module. This enables the system to recognize license plates in real-time video
footage.

To use the system, ensure you have Python 3.7 or later installed, along with the necessary
dependencies such as OpenCV (version 4 or above) and NumPy. The project includes a pre-
trained Haar cascade model, haarcascade_russian_plate_number.xml, which is used for license
plate detection.

The project provides a practical implementation of license plate recognition using computer
vision techniques. It can be utilized for various applications, including traffic monitoring,
parking management, and law enforcement.
1. INTRODUCTION:

1
INTRODUCTION:
Automatic Number Plate Recognition or ANPR is a technology that uses pattern recognition
to 'read' vehicle number plates. In simple terms ANPR cameras 'photograph' the number plates of
the vehicles that pass them. This 'photograph' is then fed in a computer system to find out details
about the vehicle itself. ANPR consists of cameras linked to a computer. As a vehicle passes,
ANPR 'reads' Vehicle Registration Marks – more commonly known as number plates - from
digital images, captured through cameras located either in a mobile unit, in-built in traffic
vehicles or viaClosed Circuit Television (CCTV). The digital image is converted into data, which
is processed through the ANPR system. We proposed a method mainly based on edge detection,
OCR operationand Finding Rectangles in a Vehicle Image.

Owning a vehicle today is not merely a symbol of luxury but has become a necessity. However,
considering vehicles, any catastrophic situation can take place. Therefore there is always an urgent
need to arrange appropriate measures to increase the safety, security as well as monitor the vehicles
to avoid any mishap. It would help us in the situations such as: Instantaneously obtain vehicle
details using image processing. Allowing an agency to detect the location of its vehicles.
Automatically notify the user if there are traffic violations registered to the vehicle. One such
measure is the use of a vehicle tracking system using the GPS (Global Position System). Such a
tracking system includes a mechanized device that is equipped in a vehicle. Using software present
at an operational base, it helps track the location of the vehicle. This base station is used for
monitoring purposes. It is accompanied by maps such as Google maps, Here maps, Bing maps etc
for the representation of the location.

ANPR can be used to store the images captured by the cameras as well as the text from the license
plate, with some configurable to store a photograph of the driver. Systems commonly use infrared
lighting to allow the camera to take the picture at any time of the day. A powerful flash is included
in at least one version of the intersection monitoring cameras, serving both to illuminate the picture

2
and to make the offender aware of his or her mistake. ANPR technology tends to be region-
specific, owing to plate variation from place to place.

Vehicle growth in India

The acquisition of digital image usually suffers from undesirable camera shakes and due to
unstable random camera motions. Hence image enhancement algorithms are required to remove
these unwanted camera shakes. . Python is used as the main programming language.

We have connected to the http://vahan.nic.in with the ANPR system to extract all the vehicle and
owner details. We extract the information and save the data in JSON format for further
processingand analysis.

3
2. LITERATURE SURVEY:

4
LITERATURE SURVEY:

2.1 INTRODUCTION:

Literature survey is the process in which a complete and comprehensive review is conducted
encompassing both the published and unpublished work from other alternative sources of
information. This review is conducted in the domains of specific interest to the person or
researcher. Further, the results of this process are documented. This entire process comes in aid of
the researcher to address the important and relevant aspects of the research that had not been
addressed prior to the conduction of this research. Therefore it can be understood that the
conduction of literature survey is necessary for the process of gathering secondary data for the
research which might prove to be extremely helpful in the research and also designing the
architecture of the project. There can be multiple reasons behind the purpose of conducting
literature survey.
2.2 PAPER 1:

Title:

Amninder Kaur, Sonika Jindal ,Richa Jindal “License Plate Recognition Using Support Vector
Machine (SVM)” Dept. Of Computer Science, International Journal of Advanced Research in
Computer Science and Software Engineering, Volume 2, Issue 7.
Context:

ANPR is a mass surveillance system that captures the image of vehicles and recognizes their
license number. In this paper, A system is proposed that incorporates to successfully locate and
read Indian vehicle number plates in digital images by using SVM. In this proposed model pre-
processing and number plate localization is performed by using ―Otsu’s methods and ―feature
based localization methods respectively. It gives reliability and time optimization. Finally, the
character reorganization performs using the Support Vector Machine.

In this paper, another algorithm to number recognition is proposed. This technique uses a Support
Vector Machine (SVM) to train character samples and obtain the rules that are used to recognize

5
the numbers on number plates. SVM is forcefully competing with many methods for pattern
classification. An SVM is a supervised learning technique first discussed by Vatnik.
SVM takes Statistical Learning Theory (SLT) as its theoretical foundation, and the structural risk
minimization as its optimal object to realize the best generalization. They are based on some simple
ideas and provide a clear intuition of what learning from examples is all about. More importantly,
they possess the feature of high performance in practical applications. From the 1960s to the
present, SVMs have become more and more important in the field of pattern recognition.

Literature Survey on SVM

2.3 PAPER 2:
Title:

ANISH LAZRUS,SIDDHARTHA CHOUBEY,SINHA G.R.,”AN EFFICIENT METHOD OF

VEHICLE NUMBER PLATE DETECTION AND RECOGNITION” Department of Computer
Science, International Journal of Machine Intelligence, Volume 3, Issue 3.

Context:

The images of various vehicles have been acquired manually and converted into grayscale images.
Then the Wiener2 filter is used to remove noise present in the plates. The segmentation of
grayscale image generated by finding edges using Sobel filter for smoothing image is used to

6
reduce the number of connected components and then Bilateral filter is used to calculate the
connected component. Finally, a single character is detected.

However, sets of blurry and skewed snapshots give worse recognition rates than a set of snapshots,
which has been captured clearly Due to rapidly increase in number of vehicles across the world’s
big cities, vehicle number plate recognition system has become one of the most important digital
image processing systems to be used. This system will solve so many problems for these city
facilities which are hard to be controlled by humans 24 hours.

Performance Matrix

Overall the vehicle license plate recognition software had been successfully designed and
developed to recognize the 38 different characters using correlation in two dimensions.

7
 Literature Survey on Vehicle Number Plate Recognition

2.4 PAPER 3:

Title:

Abhay Singh, Anand Kumar Gupta ,Anmol Singh, Anuj Gupta ,Sherish Johri, “VEHICLE
NUMBER PLATE DETECTION USING IMAGE PROCESSING”, Department of IT, Volume:
05 Issue: 03 | Mar-2018

Context:

In this technology we will be working on CCTV footage or input images given. The CCTV footage
must be clear to extract the Vehicle number from the image taken as Input. These input images are
converted to grayscale and characters are segmented and recognised using OCR. There are some
conditions for this software to work:

1) Vehicle plates should be white and according to the rules given by the government of India.

2) Image should be of appropriate brightness and contrast: In this, a software is designed which
detects the vehicle number plate number using MATLAB.
In this technique we will be performing several methods step by step to find the vehicle number.
Then using that vehicle number found we will be comparing that number from our database.

8
 Literature Survey on images extract from CCTV

2.5 PAPER 4:

Title:

Ganesh R. Jadhav, Kailash J. Karande, “Automatic Vehicle Number Plate Recognition for Vehicle
Parking Management System”, IISTE, Vol.5, No.11, 2014.

Context:

This paper discusses a method for the vehicle number plate recognition from the image using
mathematical morphological operations. The main objective is to use different morphological
operations in such a way that the number plate of vehicles can be identified accurately.
This is based on various operations such as image enhancement, morphological transformation,
edge detection and extraction of number plates from vehicle images. After this segmentation is
applied to recognize the characters present on the number plate using template matching. This
algorithm can recognize the number plate quickly and accurately from the vehicle's image.
The goal of the research is to investigate the possibility to create a comprehensive system for
Indian vehicle identification based on the license plate recognition. In that case no additional
hardware, such as e.g. transmitters, mounted on a vehicle, and responders will be required. The
system performs well on various types of vehicle license plate images.

9
The recognition errors of letters and numbers mainly occur in some of the characters with the very
similar main structures but some detailed differences, such as B and 8, O and 0, S and 5
You have to resize each character based on standardized size in this method, which becomes an
added step in pre-processing and increases time needed.

Literature Survey on Vehicle Parking Management System

2.6 PAPER 5:

Title:

Mutua Simon Mandi ,Bernard Shibwabo, Kaibiru Mutua Raphael, ”An Automatic Number Plate
Recognition System for Car Park Management”, International Journal of Computer Applications,
Volume 175 – No.7, October 2017

Context:

It proposes the adoption of a mobile based software solution that has ANPR capabilities to aid in
vehicle identification and vehicle registration. The software that was developed adopted an object-
oriented analysis and design methodology and implements Optical Character Recognition. (OCR)
using the mobile device camera to detect and capture the vehicle number plate.

10
The proposed system turned out to be efficient when it came to implementation of automatic
number plate recognition system for car park management, using Optical Character Reader (OCR)
on a mobile device.

Successful implementations of ANPR systems have resulted in faster and easier vehicle
identification. This has also resulted in faster and easier search and retrieval of vehicle information
mostly done by law enforcers in identifying vehicles that are uninsured, stolen, or driven by
someone without a license or prohibited from driving. It was recorded that the system required
1/5th of the original time that was needed by the manual system. Requires an efficient Local Area
Network Systems need to be integrated to be efficient.

Literature Survey on Car Parking System

11
3. SYSTEM ANALYSIS AND DESIGN

12
3.1 SYSTEM DESIGN:
This section elaborately describes the architecture of a Number plate recognition system and
an information extractor . The proposed system detects the vehicle number plate and extracts the
vehicle number plate in characters. In this module of vehicle number plate recognition, the input
image is preprocessed and the characters in the image are segmented. The characters that are
segmented are cropped and recognized. The recognized characters are then returned as a string.
The next module involves a web crawler which fetches the information of the vehicle. The
information fetched is converted to JSON format and stored in a database or displayed on a
dashboard for further processing.

Figure 3.1 System Architecture

The basic architecture of the system is demonstrated in Fig 5.1. The system has the following set
of modules:
● Number Plate Recognition System: The input image is captured by the system through a
camera feed or an image file. The image is pre-processed by converting the image to a
grayscale image and then bilateral filter is applied to smoothen the image further. The edges in
the image are detected using the canny edge detection algorithm. Once the canny edges

13
 are detected. Contours with 4 edges are ranked . The contour with the highest rank is
considered as the number plate region and it is cropped. Pytesseract is an OCR which
performs character recognition on this region of the image.
● Web Crawler: The web driver opens the website Vahan.nic.in and captures the captcha.
Once the captcha is captured, it is recognized and converted to a string. The string is then
solved as a mathematical equation and then it is sent back to the captcha input field. The
vehicle number plate is also sent the input field of the registration number.
● Application: The data of the vehicle extracted is converted to JSON format and stored
MySQL database and Firebase database. The data is then read by a Tkinter application and
displayed to the user.
The Following information can be collected:

1. Registering Authority

2. Registration No

3. Registration Date

4. Chassis No

5. Engine No

6. Owner Name

7. Vehicle Class

8. Fuel

9. Fitness/REGN Upto

10. MV Tax upto

11. Insurance Upto

12. Maker/Model

13. PUCC Upto

14. Emission norms

14
 15. RC Status

16. Finacc

Use Case diagram – User

shows the use case diagram of the User. The main function of the User is to upload orcapture
an image and then view the details and analyse the vehicle information that is extracted.

Data Flow Diagram of the Proposed System

15
3.2 Existing system:

3.2.1Online ANPR framework: In an online ALPR framework, the limitation and elucidation of tags
occur promptly from the approaching video outlines, enabling Real-time tracking through the surveil
ance camera.
Example: OpenALPR CloudWatch

3.2.2Offline ANPR framework: A logged off ALPR framework, interestingly, catches the shovel,
dumper number plate pictures and stores them in a concentrated information server for further
preparation, i.e. for translation of vehicle number plate
Example: OpenALPR Library
Looking at the works of other countries pushes and inspire us to try to solve the challenges that we
face in our country and also motivates us to use ANPR in all facets.

United States

Mobile ANPR use is widespread among US law enforcement agencies at the city, county, state and
federal level. According to a 2012 report by the Police Executive Research Forum, approximately 71%
of all US police departments use some form of ANPR. Mobile ANPR is becoming a significant
component of municipal predictive policing strategies and intelligence gathering, as well as for recovery
of stolen vehicles, identification of wanted felons, and revenue collection from individuals who are
delinquent on city or state taxes or fines, or monitoring for "Amber Alerts".

United Kingdom

The Home Office states the purpose of automatic number-plate recognition in the United Kingdom is
to help detect, deter and disrupt criminality including tackling organized crime groups and terrorists.
Vehicle movements are recorded by a network of nearly 8000 cameras capturing between 25 and 30
million ANPR ‘read’ records daily. These records are stored for up to two years in the National ANPR
Data Centre, which can be accessed, analyzed and used as evidence as part of investigations by UK
law enforcement agencies.

16
Saudi Arabia

Vehicle registration plates in Saudi Arabia use white background, but several vehicle types mayhave
a different background. United States diplomatic plates have the letters 'USD', which in Arabic reads
'DSU' when read from right to left in the direction of Arabic script. There are only17 Arabic letters
used on the registration plates.A Challenge for plates recognition in Saudi Arabia is the size of the
digits. Some plates use both Eastern Arabic numerals and the 'Western Arabic' equivalents. A
research with source code is available for APNR Arabic digits.

Turkey

The system has been used with two cameras per lane, one for plate recognition, one for speed
detection. Now the system has been widened to network all the registration number cameras
together, and enforcing average speed over preset distances. Some arteries have 70 km/h (43 mph)
limit, and some 50 km/h (31 mph), and photo evidence with date-time details are posted to
registration address if speed violation is detected. As of 2012, the fine for exceeding the speed limit
for more than 30% is approximately US$175.

Canada

The police service in Ontario uses automatic licence-plate recognition software[21] to nab
drivers behind the wheels of vehicles with Ontario number plates..

3.2.3Challenges in the existing system:

In the created nations the qualities of the vehicle number plate are entirely kept up. For instance, the
measure of the plate, shade of the plate, text style face/size/shade of every character, dispersingbetween
ensuing characters ,the quantity of lines in the vehicle number plate, script and so on are kept up
particularly. A portion of the pictures of the standard tags utilized as a part of created nations. In most
academic institutions and car parks, the ongoing car park entry registration process for visitors, staff
or students entering the institution involves a security guard having to confirm membership details by
checking for membership sticker on the windscreen of the vehicle or by checking the driver’s

17
identification card. This process of writing is tedious and time consuming and is prone to inaccurate
recordings, furthermore the backup and sharing of this vehicle information is difficult because the
data is hard copy.

A city like Bangalore has multiple apartment complexes and societies, most of them also verify by
checking for membership sticker on the windscreen of the vehicle. If a stranger or unknown vehicle
enters, they are required to register which is time consuming. Most complexes even consider it unsafe
as once a vehicle enters it is hard to track the movement of the members of the vehicle.
Security issues are the main drawback with many cars being stolen, especially when they are left at
parking lots even if for a few hours, it is hard to keep a record of all the vehicles entering/exitingat peak
usage times.
Thus keeping in mind these drawbacks of the traditional system we aim to get a step ahead and
address each of them individually when building our solution.

Automatic license plate recognition has two major technological requirements:

• The quality of the license plate recognition algorithms.

• The quality of the image acquisition (camera and the illumination conditions) The better
algorithms are:

• Higher is the recognition accuracy.

• Faster is the processing speed.

• Wider is the range of picture quality it can be used on.

1. Varying Indian Number Plate Formats

By and large, one LPR program can read plates from one specific nation just .This is on the grounds
that the geometrical structure of the plate and introduction, text styles, and grammar were imperative
parts of the LPR system. Without the earlier information of the plate geometry (character distribution,
character spacing, plate color, dimension ratios etc.), the algorithm may not even find the plate in the
captured image.
18
3.3 Proposed system:

Automatic Number Plate Recognition using an efficient OCR engine like Pytesseract along
with major and vast libraries of OpenCV for image processing. As we have seen so far ANPR
covers as a solution to most of the problems we have posed. We would like to dig a bit deeper
now and highlight the scope of the project and the extent to which we can push the boundaries.
The main issue that is usually recognized when it comes to number plate detection is the noise
that is addedto the image in the process of capturing the image or due to the environment around,
taking that into consideration we can say that using our system, we can implement it in all
environments, be it rain or even in the dark. Usually when any new system is proposed to possible
clients, their main concern is the addition of new features into their existing system. Keeping this
in mind we can say for sure that our system can be integrated to the pre-existing infrastructure of
most clients.

Using a web crawler, number plate recognized is parsed to the government website vahan.nic.in
along with the solved captcha and the vehicle details can be accessed for further Inference and
analysis. Also showcase the vulnerabilities in the security of the government websites and privacy
issues in government website. Also provide analytics and solution on the extracted data.

Advantages of the proposed system:

• To perform successful and efficient preprocessing on the raw RGB image

• To exploit the high performance and effectiveness of OpenCV and Pytesseract framework to
detect and recognize LP of vehicles,to improve our system reliability.
• To correctly determine the number plate based on Indian Number plate Standards
• To Successfully extract the information from Government vehicle information database
• To Show the security vulnerabilities on vahan.nic.in

Market Value of the ANPR System

According to the new market research report "Automatic Number Plate Recognition (ANPR)
System Market by Type (Fixed, Mobile, Portable), Component (ANPR Cameras, Software, Frame
Grabbers, Triggers), Application (Traffic Management, Law Enforcement, Electronic Toll
19
Collection, Parking Management), and Geography - Global Forecast to 2023", the automatic
number plate recognition (ANPR) system market in 2016 was valued at USD 1.78 Billion and is
expected to reach USD 3.57 Billion by 2023, at a CAGR of 9.74% between 2017 and 2023.
Factors that are driving this market include the infrastructure growth in emerging economies,
increasing allocation of funds by various governments on intelligent transport systems (ITS),
deployment of camera technologies in security and surveillance, and traffic enforcement
application, and the growing usage of video analytics technology for intelligent monitoring of
vehicles.
Europe was the largest market for ANPR systems in 2016. The large market in this region can be
attributed to the high adoption of intelligent transportation systems for traffic management, tolling
management, law/police enforcement, and other applications. The market in Europe has been
segmented into Germany, the UK, France and the Rest of Europe. Some major companies offering
ANPR systems in Europe include ARH Inc. (Hungary), Digital Recognition Systems Ltd. (UK),
NDI Recognition Systems Ltd. (UK), and Q-Free ASA (Norway).
The key players in the market include Kapsch TrafficCom AG (Austria), Conduent, Inc. (US),
QFree ASA (Norway), Siemens AG (Germany), Genetec Inc. (Canada) Neology, Inc. (US), Bosch
Security Systems GmbH (Germany), Tattile srl (Italy), TagMaster North America, Inc. (US), NDI
Recognition Systems Ltd. (UK), Euro Car Parks Limited (UK), Quercus Technologies, S.L.
(Spain) Vigilant Solutions, Inc. (US), Elsag North America, LLC (US), ARH Inc. (Hungary),
Digital Recognition System Ltd. (UK), Beltech BV (Netherlands), ANPR International Ltd. (UK),
HTS (New York), FF Group (Cyprus), and so on.

This report categorizes the global ANPR system market on the basis of type, component,
application, and geography. The report describes the drivers, restraints, opportunities, and
challenges for the growth of this market.

20
3.4 Project Report Methodology:

The total report is composed in the following way:

Chapter 2: Literature Survey- The literature survey is an effective tool to research about the
current developments in the related field and their drawbacks, in order to incorporate a better
mechanism in the proposed system.
Chapter 3: Theoretical Background – This contains information about the underlying
technologies and algorithms that have been made use of in the architecture and design of the
proposed system.
Chapter 4: System Requirement Specification – This chapter deals with the various functional
and non functional requirements that are to be implemented in the proposed system. It also encloses
both hardware and software requirement specifications that are needed to run the software.
Chapter 5: System Design – This chapter deals with the architecture and design of the system.
Various diagrams have been included that describe the working of the system in a way that can be
understood better.
Chapter 6: Implementation – The algorithms that form the proposed system have been listed,
along with important modules of code.
Chapter 7: Results and testing – This chapter discusses the obtained results and the outcome of
the testing process.
Chapter 8: Conclusion and future work – This chapter concludes the discussion of the work
done so far. Future enhancements that can be made to the work are also discussed in this chapter.
References – This chapter lists the various websites and books that have been referred to, in the
making of this project and the project report.

21
3.5 SYSTEM REQUIREMENT SPECIFICATION

INTRODUCTION:
This chapter describes about the requirements. It specifies the hardware and software
requirements that are required in order to run the application properly. The Software Requirement
Specification (SRS) is explained in detail, which includes overview of dissertation as well as the
functional andnon-functional requirement of this dissertation.
A SRS document describes all data, functional and behavioral requirements of the software under
production or development. SRS is a fundamental document, which forms the foundation of the
software development process. It is the complete description of the behavior of a system to be
developed. Requirement Analysis discusses the conditions to be met for a new or altered product.
Requirement Analysis is critical to the success to a development project. Requirement must be
documented, measurable, testable, related to in identified business needs or opportunities, and
defined to a level of detail sufficient for system design.
The SRS functions as a blueprint for completing a project. The goal of preparing the SRS document
is to:

● Facilitate communication between the customer, analyst, system developers, maintainers.

● To form a foundation for the design phase.

● Support system testing facilities.

● Controlling the evolution of the system.

22
3.6 FUNCTIONAL REQUIREMENTS

Functional Requirement defines in detail how the system must respond to the various kinds of
input that is given to the system. It also talks about the expected system behavior under certain
conditions. In this system following are the functional requirements:

1. Mobility: The device identifying the License plate should be movable to capture the LPon the
go
2. Convenience: The system will make it efficient to access for vehicles and prevent
congestion at entry and exit points
3. User-Interface: The system shall provide an easy-to-use user-interface.

4. Transparency: Users should be able to possess a general knowledge and understanding of the
ALPR process.
5. Flexibility: The system shall be flexible in that it allows a variety of formats to ingrate the
scanning of characters to
6. Support for Disabled: The system shall cater to the needs of physically challengedvoters
(e.g. blind voters).
7. Accuracy: The system shall accurately convert the image to characters

8. Uniqueness: The system is trained to handle unique and varying types of number plates

9. Documentation and Assurance: The design, implementation, and testing procedures must
be well documented so that the confidence is ensured.
10. Cost-effectiveness: Should be affordable and efficient.

3.6.1 NON-FUNCTIONAL REQUIREMENTS

Non-functional requirements are the requirements which are not directly concerned with the
specific function delivered by the system. They specify the criteria that can be used to judge the
operation of a system rather than specific behaviours. They may relate to emergent system

23
properties. Non-functional requirements are requirements that are not specifically concerned
with the functionality of a system. They normally place restrictions on the product being developed
and the development process. Non-functional requirements may be regarded as parameters of
functionality in that they determine how quickly, how accurately, how reliably, how securely, etc.,
functions must operate. Some of the ALPR non-functional requirements are as follows:

• The system may issue a receipt to remove any papers printed and make it a green initiative

• The system must be working at 100% peak efficiency

• When checking the database for errors, a 100% scan of the data is required, rather than selecting
a sample set

• A process must be devised to support normal precinct business hours

• The system should provide documentation to inform users of system functionality and any change
to the system

• The system should provide friendly graphical Interface to ensure ease of use when end users
utilize system functionality

3.6.2 HARDWARE REQUIREMENTS:

· Processor : Intel I5 2.1 Ghz.

· Storage : 100 GB.

· RAM : 4 GB

24
3.7 SOFTWARE REQUIREMENTS:

• Platform: Windows/Linux/macOS
• Language used: Python

•Technologies used: PyTesseract, OpenCV, Selenium, Chrome Driver, Tkinter,

Pyrebase,MySQL connector

Pytesseract : Library to use the Tesseract-OCR. Tesseract is an optical character recognition

engine for various operating systems. Tesseract is considered to be one of the most accurate open-
source OCR engines available.

OpenCV : OpenCV stands for Open Source Computer Vision. It is an open source computer vision
and machine learning software library. The library has more than 2500 optimized algorithms,
which includes a comprehensive set of both classic and state-of-the-art computer vision and
machine learning algorithms. These algorithms can be used to detect and recognize faces, identify
objects, classify human actions in videos, track camera movements, track moving objects, extract
3D models of objects, produce 3D point clouds from stereo cameras, stitch images together to
produce a high resolution image of an entire scene, find similar images from an image database,
remove red eyes from images taken using flash, follow eye movements, recognize scenery and
establish markers to overlay it with augmented reality, etc.

Selenium : It is a free (open-source) automated testing framework used to validate web

applications across different browsers and platforms. You can use multiple programming
languages like Java, C#, Python etc to create Selenium Test Scripts. Testing done using the
Selenium tool is usually referred to as Selenium Testing. Selenium Software is not just a single
tool but a suite of software, each piece catering to different testing needs of an organization.

Pyrebase - is a Python interface to Firebase’s REST API. In layman’s terms, it allows you to use
Python to manipulate your Firebase database.

Chrome Driver - WebDriver is an open source tool for automated testing of web apps across
many browsers. It provides capabilities for navigating to web pages, user input, JavaScript
execution, and more. ChromeDriver is a standalone server that implements the W3C WebDriver
25
standard. ChromeDriver is available for Chrome on Android and Chrome on Desktop.

Tkinter - is the standard GUI library for Python. Python when combined with Tkinter provides a
fast and easy way to create GUI applications. Tkinter provides a powerful object-oriented interface
to the Tk GUI toolkit.

Creating a GUI application using Tkinter is an easy task. All you need to do is perform the
following steps −

● Import the Tkinter module.

● Create the GUI application main window.
● Add one or more of the above-mentioned widgets to the GUI application.
● Enter the main event loop to take action against each event triggered by the user.

26
3.8 FEASIBILITY STUDY:
The feasibility of the project is analyzed in this phase and business proposal is put forth with a very
general plan for the project and some cost estimates. During system analysis the feasibility study of the
proposed system is to be carried out. This is to ensure that the proposed system is not a burden to the
company. For feasibility analysis, some understanding of the major requirements for the system is
essential.
Three key considerations involved in the feasibility analysis are
• Economical Feasibility
• Technical Feasibility
• Social Feasibility
3.8.1 Economical Feasibility:
This study is carried out to check the economic impact that the system will have on the organization.
The amount of fund that the company can pour into the research and development of the system is
limited. The expenditures must be justified. Thus the developed system as well within the budget and
this was achieved because most of the technologies used are freely available. Only the customized
products had to be purchased.
3.8.2 Technical Feasibility:
This study is carried out to check the technical feasibility, that is, the technical requirements of the
system. Any system developed must not have a high demand on the available technical resources. This
will lead to high demands on the available technical resources. This will lead to high demands being
placed on the client. The developed system must have a modest requirement, as only minimal or null
changes are required for implementing this system.
3.8.3 Social Feasibility:
The aspect of study is to check the level of acceptance of the system by the user. This includes the
process of training the user to use the system efficiently. The user must not feel threatened by the
system, instead must accept it as a necessity. The level of acceptance by the users solely depends on
the methods that are employed to educate the user about the system and to make him familiar with it.
His level of confidence must be raised so that he is also able to make some constructive criticism,
which is welcomed, as he is the final user of the system

27
3.9 INPUT DESIGN:
The input design is the link between the information system and the user. It comprises the
developing specification and procedures for data preparation and those steps are necessary to put
transaction data in to a usable form for processing can be achieved by inspecting the computer to read
data from a written or printed document or it can occur by having people keying the data directly into
the system. The design of input focuses on controlling the amount of input required, controlling the
errors, avoiding delay, avoiding extra steps and keeping the process simple. The input is designed in
such a way so that it provides security and ease of use with retaining the privacy. Input Design
considered the following things:
• What data should be given as input?
• How the data should be arranged or coded?
• The dialog to guide the operating personnel in providing input.
• Methods for preparing input validations and steps to follow when error occur.

Objectives
1.Input Design is the process of converting a user-oriented description of the input into a computer-
based system. This design is important to avoid errors in the data input process and show the correct
direction to the management for getting correct information from the computerized system.
2.It is achieved by creating user-friendly screens for the data entry to handle large volume of data. The
goal of designing input is to make data entry easier and to be free from errors. The data entry screen is
designed in such a way that all the data manipulates can be performed. It also provides record viewing
facilities.
3.When the data is entered it will check for its validity. Data can be entered with the help of screens.
Appropriate messages are provided as when needed so that the user will not be in maize of instant.
Thus, the objective of input design is to create an input layout that is easy to follow.

28
3.10 OUTPUT DESIGN:
A quality output is one, which meets the requirements of the end user and presents the
information clearly. In any system results of processing are communicated to the users and to other
system through outputs. In output design it is determined how the information is to be displaced for
immediate need and also the hard copy output. It is the most important and direct source information to
the user. Efficient and intelligent output design improves the system’s relationship to help user
decision-making.
1. Designing computer output should proceed in an organized, well thought out manner; the right
output must be developed while ensuring that each output element is designed so that people will find
the system can use easily and effectively. When analysis design computer output, they should Identify
the specific output that is needed to meet the requirements.
2.Select methods for presenting information.
3.Create document, report, or other formats that contain information produced by the system.

29
4. IMPLEMENTATION

30
IMPLEMENTATION:
This section contains the algorithms that are used by the system. The system makes use of these
algorithms in order to satisfy the various functional and non functional requirements of the proposed
scheme.
4.1 SOFTWARE ENVIRONMENT:
THEORITICAL BACKGROUNG:

4.1.1 Digital Image Processing

Signal processing is a discipline in electrical engineering and in mathematics that deals with
analysis and processing of analog and digital signals , and deals with storing , filtering , and other
operations on signals. These signals include transmission signals , sound or voice signals , image
signals , and other signals etc.

Out of all these signals , the field that deals with the type of signals for which the input is an
image and the output is also an image is done in image processing. As it name suggests, it deals
with the processing on images. The digital image processing deals with developing a digital system
that performs operations on an digital image.

Digital Image Processing

Since capturing an image from a camera is a physical process. The sunlight is used as a source of
energy. A sensor array is used for the acquisition of the image. So when the sunlight falls upon
the object, then the amount of light reflected by that object is sensed by the sensors, and a
continuous voltage signal is generated by the amount of sensed data. In order to create a digital
image , we need to convert this data into a digital form. This results in an two dimensional array
or matrix of numbers which are nothing but a digital image.
31
Steps in Digital Image Processing:
• Image Preprocessing: It is usually necessary to preprocess remote sensing data prior to its
analysis because image data recorded by sensors contain errors which degrade quality of the
image and cause the image to appear noise, blurred and distorted. The errors creep into during
data acquisition process. Most common types of errors are geometric and radiometric errors.
All these errors are corrected using suitable mathematical models at the time of preprocessing.
• Image Enhancement: Image enhancement is carried out to improve the appearance of certain
image features to assist in human interpretation and analysis. You should note that image
enhancement is different from image preprocessing step. Image enhancement step highlights
image features for interpreter whereas image preprocessing step reconstructs a relatively
better image from an originally imperfect/degraded image.
• Image Transformations: Image transformations are operations similar in concept to those for
image enhancement. However, unlike image enhancement operations which are normally
applied only to a single channel of data at a time, image transformations usually involve
algebraic operations of multi-layer images. Algebraic operations such as subtraction, addition,
multiplication, division, algorithms, exponentials and trigonometric functions are applied to
transform the original images into new images which display better or highlight certain
features in the image. We shall discuss about all the four digital image processing steps in the
next block, i.e. Block 4 of MGY-002. 71 Ground Truth Data Collection.
• Thematic Information :Extraction It includes all the processes used for extracting thematic
information from images. Image classification is one such process which categorizes pixels
in an image into some thematic classes such as land cover classes based on spectral
signatures. Image classification procedures are further categorized into supervised,
unsupervised and hybrid depending upon the level of human intervention in the process of
classification.

32
Advantages of Digital Image Processing:

1. Digital images can be processed by digital computers.

2. Important features such as edges can be extracted from images which can be used in
industry.
3. Images can be given more sharpness and better visual appearance.

4. Minor errors can be rectified.

5. Image sizes can be increased or decreased.

6. Images can be compressed and decompressed for faster image transfer over thenetwork.
7. Images can be automatically sorted depending on the contents they have.

8. unrecognizable features can be made prominent.

9. Images can be smoothened.

10. It allows robots to have vision.

11. It allows industries to remove defective products from the production line.

12. It allows weather forecasting.

13. It is used to analyze cells and their composition.

14. It is used to analyze medical images.

Problems associated with Digital Image Processing:

1. It is very costly depending on the system used, the number of detectors purchased.\
2. Time consuming
3. Lack of qualified professional

33
4.1.2 Optical Character Recognition

Optical character recognition or optical character reader (OCR) is

the electronic or mechanical conversion of images of typed, handwritten or printed text into
machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo
(for example the text on signs and billboards in a landscape photo).

Widely used as a form of data entry from printed paper data records – whether passport documents,
invoices, bank statements, computerized receipts, business cards, mail, printouts of static-data, or
any suitable documentation – it is a common method of digitizing printed texts so that they can be
electronically edited, searched, stored more compactly, displayed on-line, and used in machine
processes such as cognitive computing, machine translation, (extracted) text-to-speech, key data
and text mining. OCR is a field of research in pattern recognition, artificial
intelligence and computer vision.

Optical Character Recognition

34
Early versions needed to be trained with images of each character, and worked on one font at a
time. Advanced systems capable of producing a high degree of recognition accuracy for most fonts
are now common, and with support for a variety of digital image file format inputs. Some systems
are capable of reproducing formatted output that closely approximates the original page including
images, columns, and other non-textual components.

Techniques of OCR

• Pre-processing

OCR software often "pre-processes" images to improve the chances of successful

recognition. Techniques include:
• De-skew – If the document was not aligned properly when scanned, it may need to be tilted a
few degrees clockwise or counterclockwise in order to make lines oftext perfectly horizontal
or vertical.
• Despeckle – remove positive and negative spots, smoothing edges
• Line removal – Cleans up non-glyph boxes and lines
• Layout analysis or "zoning" – Identifies columns, paragraphs, captions, etc. asdistinct
blocks. Especially important in multi-column layouts and tables.

• Text Recognition

Matrix matching involves comparing an image to a stored glyph on a pixel-by-pixel basis; it is

also known as "pattern matching", "pattern recognition", or "image correlation". This relies on
the input glyph being correctly isolated from the rest of the image, and on the stored glyph
being in a similar font and at the same scale. This technique works best with typewritten text
and does not work well when new fonts are encountered. This is the technique the early
physical photocell-based OCR implemented, rather directly.

35
• Post-processing

OCR accuracy can be increased if the output is constrained by a lexicon – a list of words that
are allowed to occur in a document.[15] This might be, for example, all the words in the English
language, or a more technical lexicon for a specific field. This technique can be problematic if
the document contains words not in the lexicon, like proper nouns. Tesseractuses its dictionary to
influence the character segmentation step, for improved accuracy. The output stream may be a
plain text stream or file of characters, but more sophisticated OCR systems can preserve the
original layout of the page and produce, for example, an annotated PDF that includes both the
original image of the page and a searchable textual representation.

Uses of OCR

• Data entry for business documents, e.g. check, passport, invoice, bank statement and
receipt
• Automatic number plate recognition
• In airports, for passport recognition and information extraction
• Automatic insurance documents key information extraction
• Traffic sign recognition
• Extracting business card information into a contact list
• More quickly make textual versions of printed documents, e.g. book scanning forProject
Gutenberg
• Make electronic images of printed documents searchable, e.g. Google Books
• Converting handwriting in real time to control a computer (pen computing)
• Defeating CAPTCHA anti-bot systems, though these are specifically designed to
prevent OCR. The purpose can also be to test the robustness of CAPTCHA anti-bot
systems.
• Assistive technology for blind and visually impaired users

36
• Writing the instructions for vehicles by identifying CAD images in a database that are
appropriate to the vehicle design as it changes in real time.
• Making scanned documents searchable by converting them to searchable PDFs.

4.1.3 Web Crawler

Web crawlers go by many names, including spiders, robots, and bots, and these descriptive
names sum up what they do — they crawl across the World Wide Web to index pages for
search engines. Search engines use web crawler programs as their helpers to browse the
Internet for pages before storing that page data to use in future searches. WebDriver is a remote-
control interface that enables introspection and control of user agents. It provides a platform- and
language-neutral wire protocol as a way for out-of-process programs to remotely instruct the
behavior of web browsers. To have the ability to write instruction sets that can be run
interchangeably in many browsers on different platforms is critical to deliver a consistent
experience to users.

Web Crawler

37
The different libraries for Web Crawlers are beautiful soup and selenium web driver
1. Beautiful Soup is a Python package for parsing HTML and XML documents. It creates a
parse tree for parsed pages that can be used to extract data from HTML, which is useful for
web scraping.
2. Selenium is an open-source tool that automates web browsers. It provides a single interface
that lets you write test scripts in programming languages like Ruby, Java, NodeJS, PHP, Perl,
Python, and C#, among others.
A browser-driver then executes these scripts on a browser-instance on your device.

WebDriver is an open source tool for automated testing of webapps across many browsers. It
provides capabilities for navigating to web pages, user input, JavaScript execution, and
more. ChromeDriver is a standalone server that implements the W3C WebDriver standard.
ChromeDriver is available for Chrome on Android and Chrome on Desktop (Mac, Linux,
Windows and ChromeOS).

4.1.4 Database

A database is a collection of information that is organized so that it can be easily accessed,

managed and updated. Computer databases typically contain aggregations of data records or files,
containing information about sales transactions or interactions with specific customers.
In a relational database, digital information about a specific customer is organized into rows,
columns and tables which are indexed to make it easier to find relevant information
through SQL or NoSQL queries. In contrast, a graph database uses nodes and edges to define
relationships between data entries and queries require a special semantic search syntax. As of this
writing, SPARQL is the only semantic query language that is approved by the World Wide Web
Consortium (W3C).
Typically, the database manager provides users with the ability to control read/write access,
specify report generation and analyze usage. Some databases offer ACID (atomicity, consistency,
isolation and durability) compliance to guarantee that data is consistent and that transactions are
complete.

38
Types of databases

Databases have evolved since their inception in the 1960s, beginning with hierarchical and
network databases, through the 1980s with object-oriented databases, and today with SQL and
NoSQL databases and cloud databases.

In one view, databases can be classified according to content type: bibliographic, full text, numeric
and images. In computing, databases are sometimes classified according to their organizational
approach. There are many different kinds of databases, ranging from the most prevalent approach,
the relational database, to a distributed database, cloud database, graph database or NoSQL
database.

Database

39
Relational database

A relational database, invented by E.F. Codd at IBM in 1970, is a tabular database in which data
is defined so that it can be reorganized and accessed in a number of different ways. Relational
databases are made up of a set of tables with data that fits into a predefined category. Each table
has at least one data category in a column, and each row has a certain data instance for the
categories which are defined in the columns. The Structured Query Language (SQL) is the
standarduser and application program interface for a relational database. Relational databases are
easy to extend, and a new data category can be added after the original database creation without
requiringthat you modify all the existing applications.

Distributed database

A distributed database is a database in which portions of the database are stored in multiple
physical locations, and in which processing is dispersed or replicated among different points in a
network. Distributed databases can be homogeneous or heterogeneous. All the physical locations
in a homogeneous distributed database system have the same underlying hardware and run the
same operating systems and database applications. The hardware, operating systems or database
applications in a heterogeneous distributed database may be different at each of the locations.

Cloud database

A cloud database is a database that has been optimized or built for a virtualized environment, either
in a hybrid cloud, public cloud or private cloud. Cloud databases provide benefits such as the
ability to pay for storage capacity and bandwidth on a per-use basis, and they provide scalability
on demand, along with high availability. A cloud database also gives enterprises the opportunity
tosupport business applications in a software-as-a-service deployment.

40
NoSQL database

NoSQL databases are useful for large sets of distributed data.NoSQL databases are effective for
big data performance issues that relational databases aren't built to solve. They are most effective
when an organization must analyze large chunks of unstructured data or data that's stored across
multiple virtual servers in the cloud.

Object-oriented database

Items created using object-oriented programming languages are often stored in relational
databases, but object-oriented databases are well-suited for those items.An object-oriented
database is organized around objects rather than actions, and data rather than logic. For example,
a multimedia record in a relational database can be a definable data object, as opposed to an
alphanumeric value.

Graph database

A graph-oriented database, or graph database, is a type of NoSQL database that uses graph
theory to store, map and query relationships. Graph databases are basically collections of nodes
and edges, where each node represents an entity, and each edge represents a connection between
nodes.Graph databases are growing in popularity for analyzing interconnections. For example,
companies might use a graph database to mine data about customers from social media.Graph
databases often employ SPARQL, a declarative programming language and protocol for graph
database analytics. SPARQL has the capability to perform all the analytics that SQL can perform,
plus it can be used for semantic analysis, the examination of relationships. This makes it useful for
performing analytics on data sets that have both structured and unstructured data. SPARQL allows
users to perform analytics on information stored in a relational database, as well as friend-of-a-
friend (FOAF) relationships, PageRank and shortest path.

41
Firebase database
The Firebase Realtime Database is a cloud-hosted database. When you build cross-platform

apps with our iOS, Android, and JavaScript SDKs, all of your clients share one Realtime
Database instance and automatically receive updates with the newest data.

Firebase is based on a data structure used by the NoSQL database is vastly different from those
used in a relational database. Some operations are faster in NoSQL than relational
databasesFirebase RealTime Database with Operations in Android with Examples. Firebase
Realtime Database is a Cloud hosted database, i.e. it runs on a cloud and access to the user is
provided as a service. It stores data in JSON (Javascript Object Notation) format, a format to
store or transport data.

One of the main problems with it, is limited querying capabilities. Realtime database provides
no way to filter capabilities, because the whole DB is a huge JSON file, which makes it difficult
to make complex queries.

MySQL database
SQL is a domain-specific language used in programming and designed for managing data held in
a relational database management system, or for stream processing in a relational data stream
management system

SQL is used to communicate with a database. According to ANSI (American National

Standards Institute), it is the standard language for relational database management systems.
SQL statements are used to perform tasks such as update data on a database, or retrieve data
from a database.

42
4.1.5 Graphical User Interface
The graphical user interface, developed in the late 1970s by the Xerox Palo Alto research
laboratory and deployed commercially in Apple’s Macintosh and Microsoft’s Windows operating
systems, was designed as a response to the problem of inefficient usability in early, text-based
command-line interfaces for the average user.

Graphical user interfaces would become the standard of user-centered design in software
application programming, providing users the capability to intuitively operate computers and other
electronic devices through the direct manipulation of graphical icons such as buttons, scroll bars,
windows, tabs, menus, cursors, and the mouse pointing device. Many modern graphical user
interfaces feature touchscreen and voice-command interaction capabilities.

Graphical user interface design principles conform to the model–view–controller software pattern,
which separates internal representations of information from the manner in which information is
presented to the user, resulting in a platform where users are shown which functions are possible
rather than requiring the input of command codes. Users interact with information by manipulating
visual widgets, which are designed to respond in accordance with the type of data they hold and
support the actions necessary to complete the user’s task.

Graphical User Interface

43
The appearance, or “skin,” of an operating system or application software may be redesigned at
will due to the nature of graphical user interfaces being independent from application functions.
Applications typically implement their own unique graphical user interface display elements in
addition to graphical user interface elements already present on the existing operating system. A
typical graphical user interface also includes standard formats for representing graphics and text,
making it possible to share data between applications running under common graphical user
interface design purpose.

Graphical user interface testing refers to the systematic process of generating test cases in order to
evaluate the functionality of the system and its design elements. Graphical user interface testing
tools, which are either manual or automated and typically implemented by third-party operators,
are available under a variety of licenses and are supported by a variety of platforms. Popular
examples include: Tricentis Tosca, Squish GUI Tester, Unified Functional Testing (UFT),
Maveryx, Appium, and eggPlant Functional.

Tkinter

Tkinter is the standard GUI library for Python. Python when combined with Tkinter provides a
fast and easy way to create GUI applications. Tkinter provides a powerful object-oriented
interface to the Tk GUI toolkit.

Creating a GUI application using Tkinter is an easy task. All you need to do is perform the
following steps −

• Import the Tkinter module.

• Create the GUI application main window.

• Add one or more of the above-mentioned widgets to the GUI application.

• Enter the main event loop to take action against each event triggered by the user.

44
The foundational element of a Tkinter GUI is the window. Windows are the containers in which
all other GUI elements live. These other GUI elements, such as text boxes, labels, and buttons, are
known as widgets. Widgets are contained inside of windows.

PyQt

PyQt is one of the most popular Python bindings for the Qt cross-platform C++ framework. PyQt
developed by Riverbank Computing Limited. Qt itself is developed as part of the Qt Project. PyQt
provides bindings for Qt 4 and Qt 5. PyQt is distributed under a choice of licences: GPL version 3
or a commercial license.

PyQt is available in two editions: PyQt4 which will build against Qt 4.x and 5.x and PyQt5 which
will only build against 5.x. Both editions can be built for Python 2 and 3. PyQt contains over 620
classes that cover graphical user interfaces, XML handling, network communication, SQL
databases, Web browsing and other technologies available in Qt.

4.1.6 OpenCV

OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine
learning software library. OpenCV was built to provide a common infrastructure for computer
vision applications and to accelerate the use of machine perception in the commercial products.
Being a BSD-licensed product, OpenCV makes it easy for businesses to utilize and modify the
code. The library has more than 2500 optimized algorithms, which includes a comprehensive set
of both classic and state-of-the-art computer vision and machine learning algorithms. These
algorithms can be used to detect and recognize faces, identify objects, classify human actions in
videos, trackcamera movements, track moving objects, extract 3D models of objects, produce 3D
point clouds from stereo cameras, stitch images together to produce a high resolution image of an
entire scene, find similar images from an image database, remove red eyes from images taken
using flash, follow eye movements, recognize scenery and establish markers to overlay it with
augmented

45
reality, etc. OpenCV has more than 47 thousand people of user community and estimated number
of downloads exceeding 18 million. The library is used extensively in companies, research groups
and by governmental bodies.

Along with well-established companies like Google, Yahoo, Microsoft, Intel, IBM, Sony, Honda,
Toyota that employ the library, there are many startups such as Applied Minds, VideoSurf, and
Zeitera, that make extensive use of OpenCV. OpenCV’s deployed uses span the range from
stitching streetview images together, detecting intrusions in surveillance video in Israel,
monitoring mine equipment in China, helping robots navigate and pick up objects at Willow
Garage, detection of swimming pool drowning accidents in Europe, running interactive art in Spain
and New York, checking runways for debris in Turkey, inspecting labels on products in factories
around the world on to rapid face detection in Japan.

It has C++, Python, Java and MATLAB interfaces and supports Windows, Linux, Android and
Mac OS. OpenCV leans mostly towards real-time vision applications and takes advantage of
MMX and SSE instructions when available. A full-featured CUDAand OpenCL interfaces are
being actively developed right now. There are over 500 algorithms and about 10 times as many
functions that compose or support those algorithms. OpenCV is written natively in C++ and has a
templated interface that works seamlessly with STL containers.

4.1.7 Tesseract Engine

An open-source OCR engine that has gained popularity among OCR developers. Even though it
can be painful to implement and modify sometimes, there weren’t too many free and powerful
OCR alternatives on the market for the longest time. Tesseract began as a Ph.D. research project
in HP Labs, Bristol. It gained popularity and was developed by HP between 1984 and 1994. In
2005 HP released Tesseract as an open-source software. Since 2006 it is developed by Google.
Tesseract is an open source text recognition (OCR) Engine, available under the Apache 2.0 license.
It can be used directly, or (for programmers) using an API to extract printed text from images. It
supports a wide variety of languages. Tesseract doesn't have a built-in GUI, but there are several
available from the 3rdParty page. Tesseract is compatible with many programming languages and

46
frameworks through wrappers that can be found here. It can be used with the existing layout
analysis to recognize text within a large document, or it can be used in conjunction with an external
text detector to recognize text from an image of a single text line.

Tesseract Architecture

LSTMs are great at learning sequences but slow down a lot when the number of states is too
large. There are empirical results that suggest it is better to ask an LSTM to learn a long sequence
than a short sequence of many classes. Tesseract developed from OCRopus model in Python
which wasa fork of a LSMT in C++, called CLSTM. CLSTM is an implementation of the LSTM
recurrent neural network model in C++, using the Eigen library for numerical computations.

Legacy Tesseract 3.x was dependent on the multi-stage process where we can differentiate steps:

• Word finding
• Line finding

Character classification Word finding was done by organizing text lines into blobs, and the lines
and regions are analyzed for fixed pitch or proportional text. Text lines are broken into words
differently according to the kind of character spacing. Recognition then proceeds as a two-pass
process. In the first pass, an attempt is made to recognize each word in turn. Each word that is

47
satisfactory is passed to an adaptive classifier as training data. The adaptive classifier then gets a
chance to more accurately recognize text lower down the page.

Modernization of the Tesseract tool was an effort on code cleaning and adding a
new LSTM model. The input image is processed in boxes (rectangle) line by line
feeding into the LSTM model and giving output. In the image below we can
visualize how it work

48
4.2 SAMPLE CODE:

4.2.1 Algorithm to Recognize the Number Plates

The sequence of processes associated with Number plate recognition is given below. The file
upload process is initiated by the data owner entity.
Input: Uploading the image file from camera

Output: Vehicle number plate in characters

1) Read the original image or Capture the image
2) Resize the image
3) Convert it to grayscale.
4) Apply Bilateral Filter. What is a bilateral filter ? A bilateral filter is a non-linear, edge
preserving, and noise-reducing smoothing filter for images. It replaces the intensity of each pixel
with a weighted average of intensity values from nearby pixels.
5) Identify and store the Canny edges. What are Canny edges ? The Canny edge detector is an
edge detection operator that uses a multi-stage algorithm to detect a wide range of edges in images.
6) Find the contours in from the edges detected and sort the top 30 contours.
7) Get the perimeter of each contour and select those with 4 corners.

8) Mask all other parts of the image and show the final image.
9) Read the text using Tesseract OCR
10) Standardize the text to Indian vehicle number plate format
11) Stop On upload of the image file to the system, the number plate recognition system performs
itsfunctions to provide the output.

49
Algorithm to Extract Vehicle Information from Vahan.nic.in
The sequence of processes associated with extracting the vehicle information from vahan.nic.in .
The information is extracted from the website
Input: Vehicle Number plate characters

Output: Vehicle information

1. Initialize the Selenium web driver

2. Open the (vahan.nic.in) url in the web driver

3. Find the Captcha Element

4. Captcha Element is then converted to string

5. Captcha is solved based on the written rules

6. Captcha Solution is determined

7. The Vehicle Number and Captcha Solution are sent to their input field using Keys function

8. The Search button is pressed using the click function in Selenium

9. The Vehicle details are then extracted as text

10. The text is converted into JSON data and stored in a database

50
4.2.2 MAIN PROGRAM:

# Code to capture the image of the vehicle number plate

from skimage.io import imread

from skimage.filters import threshold_otsu
import matplotlib.pyplot as plt
import imutils
import cv2
from skimage import measure
from skimage.measure import regionprops
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import os
import shutil
filename = 'plate.mp4'
if os.path.exists('output'):
shutil.rmtree('output')
os.makedirs('output')
cap = cv2.VideoCapture(filename)
# cap = cv2.VideoCapture(0)
count = 0
while cap.isOpened():
ret,frame = cap.read()
if ret == True:
cv2.imshow('window-name',frame)
cv2.imwrite("./output/frame%d.jpg" % count, frame)
count = count + 1
if cv2.waitKey(10) & 0xFF == ord('q'):
break

51
 else:
break
cap.release()
cv2.destroyAllWindows()
# car image -> grayscale image -> binary image
car_image = imread("./output/frame%d.jpg"%(count-1), as_gray=True)
car_image = imutils.rotate(car_image, 270)
# car_image = imread("car.png", as_gray=True)
# it should be a 2 dimensional array
print(car_image.shape)
# the next line is not compulsory however, a grey scale pixel
# in skimage ranges between 0 & 1. multiplying it with 255
# will make it range between 0 & 255 (something we can relate better with
gray_car_image = car_image * 255
fig, (ax1, ax2) = plt.subplots(1, 2)
ax1.imshow(gray_car_image, cmap="gray")
threshold_value = threshold_otsu(gray_car_image)
binary_car_image = gray_car_image > threshold_value
#print(binary_car_image)
ax2.imshow(binary_car_image, cmap="gray")
# ax2.imshow(gray_car_image, cmap="gray")
plt.show()
# CCA (finding connected regions) of binary image
# this gets all the connected regions and groups them together
label_image = measure.label(binary_car_image)
# print(label_image.shape[0]) #width of car img
# getting the maximum width, height and minimum width and height that a license plate can be
plate_dimensions = (0.03*label_image.shape[0], 0.08*label_image.shape[0],
0.15*label_image.shape[1], 0.3*label_image.shape[1])
plate_dimensions2 = (0.08*label_image.shape[0], 0.2*label_image.shape[0],
0.15*label_image.shape[1], 0.4*label_image.shape[1])
52
min_height, max_height, min_width, max_width = plate_dimensions
plate_objects_cordinates = []
plate_like_objects = []
fig, (ax1) = plt.subplots(1)
ax1.imshow(gray_car_image, cmap="gray")
flag =0
# regionprops creates a list of properties of all the labelled regions
for region in regionprops(label_image):
# print(region)
if region.area < 50:
#if the region is so small then it's likely not a license plate
continue
# the bounding box coordinates
min_row, min_col, max_row, max_col = region.bbox
# print(min_row)
# print(min_col)
# print(max_row)
# print(max_col)
region_height = max_row - min_row
region_width = max_col - min_col
# print(region_height)
# print(region_width)
# ensuring that the region identified satisfies the condition of a typical license plate
if region_height >= min_height and region_height <= max_height and region_width >= min_width
and region_width <= max_width and region_width > region_height:
flag = 1
plate_like_objects.append(binary_car_image[min_row:max_row,
min_col:max_col])
plate_objects_cordinates.append((min_row, min_col,
max_row, max_col))
rectBorder = patches.Rectangle((min_col, min_row), max_col - min_col, max_row - min_row,
53
edgecolor="red",
linewidth=2, fill=False)
ax1.add_patch(rectBorder)
# let's draw a red rectangle over those regions
if(flag == 1):
# print(plate_like_objects[0])
plt.show()

if(flag==0):
min_height, max_height, min_width, max_width = plate_dimensions2
plate_objects_cordinates = []
plate_like_objects = []
fig, (ax1) = plt.subplots(1)
ax1.imshow(gray_car_image, cmap="gray")
# regionprops creates a list of properties of all the labelled regions
for region in regionprops(label_image):
if region.area < 50:
#if the region is so small then it's likely not a license plate
continue
# the bounding box coordinates
min_row, min_col, max_row, max_col = region.bbox
# print(min_row)
# print(min_col)
# print(max_row)
# print(max_col)
region_height = max_row - min_row
region_width = max_col - min_col
# print(region_height)
# print(region_width)

54
# ensuring that the region identified satisfies the condition of a typical license plate
if region_height >= min_height and region_height <= max_height and region_width >= min_width
and region_width <= max_width and region_width > region_height:
# print("hello")
plate_like_objects.append(binary_car_image[min_row:max_row,
min_col:max_col])
plate_objects_cordinates.append((min_row, min_col,
max_row, max_col))
rectBorder = patches.Rectangle((min_col, min_row), max_col - min_col, max_row - min_row,
edgecolor="red",
linewidth=2, fill=False)
ax1.add_patch(rectBorder)
# let's draw a red rectangle over those regions
# print(plate_like_objects[0])
plt.show()

55
5. SYSTEM TESTING AND SCREENSHOTS

56
5.1 SYSTEM TESTING:
The purpose of testing is to discover errors. Testing is the process of trying to discover every
conceivable fault or weakness in a work product. It provides a way to check the functionality of
components, sub-assemblies, assemblies and/or a finished product It is the process of exercising
software with the intent of ensuring that the Software system meets its requirements and user
expectations and does not fail in an unacceptable manner. There are various types of tests. Each test
type addresses a specific testing requirement.
Types of Tests:
5.1.1 Unit Testing:
Unit testing involves the design of test cases that validate that the internal program logic is
functioning properly, and that program inputs produce valid outputs. All decision branches and internal
code flow should be validated. It is the testing of individual software units of the application .it is done
after the completion of an individual unit before integration. This is a structural testing, that relies on
knowledge of its construction and is invasive. Unit tests perform basic tests at component level and test
a specific business process, application, and/or system configuration. Unit tests ensure that each unique
path of a business process performs accurately to the documented specifications and contains clearly
defined inputs and expected results.
5.1.2 Integration Testing:
Integration tests are designed to test integrated software components to determine if they actually
run as one program. Testing is event driven and is more concerned with the basic outcome of screens
or fields. Integration tests demonstrate that although the components were individually satisfaction, as
shown by successfully unit testing, the combination of components is correct and consistent.
Integration testing is specifically aimed at exposing the problems that arise from the combination of
components.
5.1.3 Functional Test:
Functional tests provide systematic demonstrations that functions tested are available as specified
by the business and technical requirements, system documentation, and user manuals.

Functional testing is centred on the following items:

Valid Input : identified classes of valid input must be accepted.
57
Invalid Input : identified classes of invalid input must be rejected.
Functions : identified functions must be exercised.
Output : identified classes of application outputs must be exercised.
Systems/Procedures: interfacing systems or procedures must be invoked.
Organization and preparation of functional tests is focused on requirements, key functions, or
special test cases. In addition, systematic coverage pertaining to identify Business process flows; data
fields, predefined processes, and successive processes must be considered for testing. Before functional
testing is complete, additional tests are identified and the effective value of current tests is determined.
5.1.4 System Test:
System testing ensures that the entire integrated software system meets requirements. It tests a
configuration to ensure known and predictable results. An example of system testing is the
configuration-oriented system integration test. System testing is based on process descriptions and
flows, emphasizing pre-driven process links and integration points.
5.1.5 White Box Testing:
White Box Testing is a testing in which in which the software tester has knowledge of the inner
workings, structure and language of the software, or at least its purpose. It is purpose. It is used to test
areas that cannot be reached from a black box level.
5.1.6 Black Box Testing:
Black Box Testing is testing the software without any knowledge of the inner workings,
structure or language of the module being tested. Black box tests, as most other kinds of tests, must be
written from a definitive source document, such as specification or requirements document, such as
specification or requirements document. It is a testing in which the software under test is treated, as a
black box .you cannot “see” into it. The test provides inputs and responds to outputs without
considering how the software works.

5.1.7 Unit Testing:

Unit testing is usually conducted as part of a combined code and unit test phase of the software
lifecycle, although it is not uncommon for coding and unit testing to be conducted as two distinct
phases.
Test strategy and approach Field testing will be performed manually and functional tests will be
written in detail.
58
Test objectives
• All field entries must work properly.
• Pages must be activated from the identified link.
• The entry screen, messages and responses must not be delayed.
Features to be tested
• Verify that the entries are of the correct format
• No duplicate entries should be allowed
• All links should take the user to the correct page.
5.1.8 Integration Testing:
Software integration testing is the incremental integration testing of two or more integrated
software components on a single platform to produce failures caused by interface defects.
The task of the integration test is to check that components or software applications, e.g.
components in a software system or – one step up – software applications at the company level –
interact without error.
Test Results: All the test cases mentioned above passed successfully. No defects encountered.
5.1.9 Acceptance Testing:
User Acceptance Testing is a critical phase of any project and requires significant participation
by the end user. It also ensures that the system meets the functional requirements.
Test Results: All the test cases mentioned above passed successfully. No defects encountered.

5.1.10 TESTING:
Testing is the process of checking whether the actual results obtained meet the expected results and to
ensure that the software system is free from any kind of defects. It involves execution of a software
component or system component to evaluate one or more properties of interest. Software testing also
helps to identify errors, gaps or missing requirements in contrary to the actual requirements. It can be
either done manually or using automated tools.
Testing is an important phase in the development life cycle of the product. Testing performs a very
critical role for quality assurance and ensuring the reliability of the software. Each test has a different
purpose, all work to verify that all the system elements have been properly integrated and perform
allocated functions. The testing process is actually carried out to make sure that the product exactly
does the same thing that it is supposed to do. Testing is the final verification and validation activity
within the development environment.
59
5.2 SCREENSHOTS
5.2.1 Input as video or image wisely:

60
5.2.2 Having input divide as a no. of Frames for reliable photo:

61
5.2.3 Output taken from input in a form of certain resolution with
(i) Black and white photo
(ii) Highlighted number plate photo

62
6.CONCLUSION AND FUTURE SCOPE

63
CONCLUSION AND FUTURE SCOPE:

Through this project it is possible to recognize Vehicle registration numbers through digital image
processing. From this system we have effortlessly obtained the various results such as
• Whether the vehicle which is registered is blacklisted or not.

• This also enables one single user to effectively monitor the traffic, and can easily locate the
traffic violated vehicle.
• The data can be easily stored and transferred which makes the system more efficient.
The system has been designed using a modular approach which allows easy upgrading and/or
substituting of various sub-modules thus making it potentially suitable for a large range of vision
applications. The performances of the system makes it a valid choice among its competitors especially
in those situations when the cost of the application has to be maintained at reasonable levels.
Furthermore, the modular architecture makes it extremely flexible and versatile.
The earlier methodologies which have been implemented have not been as accurate and efficient as the
designed Recognition system , this is because of the implementation of digital Image Processing which
gives an accuracy of 90% under normal conditions

This Project is based on automatic vehicle license plate recognition, in which it is observed that the
existing techniques don't pay much attention towards improving the system's efficiency in terms of its
power consumption. As the objective in our proposed design is to reduce power consumption of the
system, with the successful implementation of the same it will play a very important role in traffic
management and security systems such as automobile theft prevention, parking lot management etc.
implementations of the software algorithm have shown promising results. The system can be made more
robust if high precision cameras can be used to increase overall accuracy if this system is implemented
in real time applications. Also a sensor can be designed to allow the camera to capture the image only
when required to save power.

64
7. REFERENCES

65
REFERENCES:

[1] ANISH LAZRUS,SIDDHARTHA CHOUBEY,SINHA G.R.,”AN EFFICIENT METHOD OF

VEHICLE NUMBER PLATE DETECTION AND RECOGNITION” Department of Computer
Science, International Journal of Machine Intelligence, Volume 3, Issue 3.
[2] Amninder Kaur, Sonika Jindal ,Richa Jindal “License Plate Recognition Using Support Vector
Machine (SVM)” Dept. Of Computer Science, International Journal of Advanced Research in
Computer Science and Software Engineering, Volume 2, Issue 7.
[3] Abhay Singh, Anand Kumar Gupta ,Anmol Singh, Anuj Gupta ,Sherish Johri, “VEHICLE NUMBER
PLATE DETECTION USING IMAGE PROCESSING”, Department of IT, Volume: 05 Issue: 03 |
Mar-2018
[4] Ganesh R. Jadhav, Kailash J. Karande, “Automatic Vehicle Number Plate Recognition for Vehicle
Parking Management System”, IISTE, Vol.5, No.11, 2014.
[5] Mutua Simon Mandi ,Bernard Shibwabo, Kaibiru Mutua Raphael, ”An Automatic Number Plate
Recognition System for Car Park Management”, International Journal of Computer Applications,
Volume 175 – No.7, October 2017
[6] https://en.wikipedia.org/wiki/Automatic_number-plate_recognition

66