Automatic Number Plate Recognition(ANPRS)

Submitted by:
Names Registration No
Muhammad Ehtisham Jamil 2019-UKT-006606
Muhammad Taha Khalil 2019-UKT-006607
Class:
BS SE (2019-23)

Supervised by:
Dr. Umair Khadim

Department of Software Engineering

Faculty of computing and engineering
University of Kotli Azad Jammu and Kashmir

i
 FINAL APPROVAL
It is certified that we have reviewed the project report prepared for “ANPRS” and
it is our judgment that this project is of sufficient standard to warrant its acceptance by
the University of Kotli Azad Jammu and Kashmir for BS Software Engineering as
a partial fulfilment. This project is submitted by Muhammad Ehtisham Jamil,
registration number 2019-UKT-006606, Muhammad Taha Khalil, registration
number 2019-UKT-006607.
Committee
Supervisor
Mr. Umair Khadim
Lecturer
Department of Software Engineering Sign: _______________________
Faculty of Computing & Engineering
University of Kotli AJK

External Examiner

Dr. Muhammad Munawar Iqbal

Assistant Professor Sign: ____________________
Department of Computer Science
University of Engineering and Technology (UET), Taxila,
Punjab Pakistan

Chairman
Mr. Umair Khadim
Lecturer
Department of Software Engineering Sign: _______________________
Faculty of Computing & Engineering
University of Kotli AJK

Dean
Prof. Dr. Ghulam Nabi
Faculty of Computing & Engineering Sign: ______________________
University of Kotli AJK

ii
 DECLARATION
We declare that this system, neither as a whole nor as a part has been copied
from any other source. It is further declared that we have completed our project entirely
on the basis of our personal effort made under the sincere guidance of our teachers. No
portion of the work presented in this report has been submitted in support of any
application for any other degree or qualification of this or any other university or
institute of learning. If any part of this project and write up is proved to be copied out
or there is any duplication of code, then will be responsible for the consequences.

Muhammad Ehtisham Jamil: ______________

Muhammad Taha Khalil: ______________

iii
 ABSTRACT
Automatic Number plate detection is an image processing technology that uses a license number
plate for vehicle identification. The objective is to design and implement an efficient vehicle
identification system that identifies the vehicle using the vehicle’s number plate. The system can
be implemented on the entrance of parking lots, toll booths, or any private premises like college,
etc. to keep the records of vehicles. It can be used to allow access to only permitted vehicles inside
the premises. The developed system first captures the image of the vehicle’s front, then detects the
number plate, then reads the number plate and then gets information of the vehicle. The vehicle
number plate is extracted using the image processing of the image. Optical character recognition
(OCR) is used for character recognition. The system is implemented using OpenCV and its
performance is tested on various images and show information for cloud. It is observed that the
developed system successfully detects and recognizes the vehicle number plate.

4
 ACKNOWLEDGEMENT
All the praise and glory to Allah, who has blessed us with the courage and knowledgeto
achieve our goal. We can never thank Him enough for His countless blessings upon us. Praise to
Prophet Mohammad (S.A.W), who is and will always be a source of guidance andknowledge
for humanity as a whole.
For us, a mile stone of this nature would never have been possible to achieve without the
support of galaxy of some truly loving and kind people in our life. No words can fully describe
our feelings of respect and gratitude for our affectionate parents, supporting sibling and friends,
whose love, encouragement and prayers invariably buoyed us up. Their concern, love and support
can never be paid back.
We owe a lot of sincere gratitude to our respected supervisor Dr. Umair Khadim, whose
true guidance, positive criticism and sincere encouragement made usto get to our destination. He
became a source of inspiration for us and kept us moving in the right direction towards our goal.

Muhammad Ehtisham Jamil

Muhammad Taha Khalil

5
 PREFACE
This report presents a description of the analysis, design, implementation, of the Automatic

Number Plate Recognition System ANPRS. These chapters include the steps involved in the study

to develop; a brief description of these chapters is given below:

Chapter 1: This chapter contains the introduction of the concerned organization and the project

Chapter 2: This chapter contains the description of the requirements specification.

Chapter 3: This chapter is about system design.

Chapter 4: This chapter is about project management.

Chapter 5: This chapter is about implementation.

6
Contents
FINAL APPROVAL ..................................................................................................................................... ii
DECLARATION .............................................................................................................................................. iii
ABSTRACT...................................................................................................................................................... 4
ACKNOWLEDGEMENT ................................................................................................................................... 5
PREFACE ........................................................................................................................................................ 6
Chapter 1 ..................................................................................................................................................... 12
1. Introduction ............................................................................................................................................ 12
1.1 Literature/background studies ......................................................................................................... 12
1.2 Objective ........................................................................................................................................... 13
1.3 Problem Description ......................................................................................................................... 13
1.4 Methodology..................................................................................................................................... 14
1.5 Project Scope .................................................................................................................................... 14
1.6 Feasibility Study ................................................................................................................................ 15
1.7 Solution Application Areas ................................................................................................................ 15
1.8 Tools/Technology .............................................................................................................................. 16
1.9 Expertise of the Team Members....................................................................................................... 16
1.10 Software Process Model ................................................................................................................. 17
1.11 Milestones....................................................................................................................................... 17
Chapter 2 ..................................................................................................................................................... 18
2 SYSTEM REQUIREMENT SPECIFICATION .................................................................................................. 18
2.1 Introduction ...................................................................................................................................... 18
2.1.1 Purpose ...................................................................................................................................... 18
2.1.2 Document Conventions ............................................................................................................. 18
2.1.3 Intended Audience and Reading Suggestions ............................................................................ 18
2.1.4 Product Scope ............................................................................................................................ 19
2.2 Overall Description............................................................................................................................ 19
2.2.1 Product Perspective ................................................................................................................... 19
2.2.2 Product Functions ...................................................................................................................... 19
2.2.3 Operating Environment ............................................................................................................. 20
2.2.4 Design and Implementation Constraints ................................................................................... 20
2.2.5 User Documentation .................................................................................................................. 20
2.2.6 Assumptions and Dependencies ................................................................................................ 20

7
 2.3 External Interface Requirements ...................................................................................................... 21
2.3.1 User Interfaces ........................................................................................................................... 21
2.3.2 Hardware Interfaces .................................................................................................................. 21
2.3.3 Software Interfaces .................................................................................................................... 21
2.3.4 Communications Interfaces ....................................................................................................... 21
2.4 System Features ................................................................................................................................ 21
2.4.1 Functional Requirements ........................................................................................................... 22
2.4.2 Other Non-functional Requirements ......................................................................................... 23
Chapter 3 ..................................................................................................................................................... 24
3 SYSTEM DESIGN ....................................................................................................................................... 24
Introduction of Design Document .............................................................................................................. 24
3.1 Design Approach ............................................................................................................................... 24
3.1.1 Class Model ................................................................................................................................ 24
3.2 Object Modelling Technique (OMT).................................................................................................. 24
3.2.1 Interaction Model ...................................................................................................................... 25
3.3 Use Case Diagram ............................................................................................................................. 25
3.4 Entity Relationship Diagram (ERD) .................................................................................................... 28
3.5 Sequence Diagrams........................................................................................................................... 30
3.6 Class Diagram .................................................................................................................................... 31
3.7 Activity Diagram ................................................................................................................................ 33
3.8 Interface Design ................................................................................................................................ 35
3.9 Test Cases.......................................................................................................................................... 37
3.10 Login Test: ....................................................................................................................................... 37
3.11 Registration Test: ............................................................................................................................ 37
3.12 Capturing Image & Display vehicle information Test: .................................................................... 38
Chapter 4 ..................................................................................................................................................... 40
4 SOFTWARE PROJECT MANAGEMENT ...................................................................................................... 40
4.1 Project Management Techniques ..................................................................................................... 40
4.1.1 Work Breakdown Structure for ANPRS ...................................................................................... 40
4.1.2 Gantt Chart................................................................................................................................. 40
4.1.3 Critical Path Method: ................................................................................................................. 41
4.1.4 Activity on Node diagram .......................................................................................................... 41
4.1.5 Critical Path Method .................................................................................................................. 42

8
 4.1.6 Paths........................................................................................................................................... 42
4.1.7 Time Period:............................................................................................................................... 42
4.2 Total Cost: ......................................................................................................................................... 43
4.3 Productivity ....................................................................................................................................... 43
Chapter 5 ..................................................................................................................................................... 45
5 PROJECT IMPLEMENTATION .................................................................................................................... 45
5.1 PROGRAMMING LANGUAGE ............................................................................................................ 45
5.2 FRAMEWORK .................................................................................................................................... 45
5.3 SYSTEM REQUIREMENTS................................................................................................................... 45
5.3.1 Hardware Requirements ............................................................................................................ 45
5.3.2 Software Requirements ............................................................................................................. 46
5.4 Implementation ................................................................................................................................ 46
5.4.1 Read in Image, Grayscale and Blur: ........................................................................................... 47
5.4.2 Apply filters and find edges for Localization: ............................................................................. 48
5.4.3 Find Contours and Apply Masks:................................................................................................ 48
5.4.4 Grayscale Image of Number Plate: ............................................................................................ 49
5.5 Render Result: ................................................................................................................................... 49
5.6 Chapter summary.............................................................................................................................. 49
6 References ............................................................................................................................................... 50

9
 LIST OF FIGURES
Figure 1:Iterative Waterfall Process Model .............................................................................................. 17
Figure 2:Automatic Number Plate Recognition System ........................................................................... 26
Figure 3:ERD For Automatic Number Plate Recognition System ....................................................... 29
Figure 4:Sequence Diagram for Automatic Number Plate Recognition .............................................. 31
Figure 5:Class Diagram for Automatic number Plate recognition system .......................................... 32
Figure 6: Activity diagram for Login ...................................................................................................... 33
Figure 7: Activity Diagram for ANPRS .................................................................................................. 34
Figure 8: Interface for Login or Sin Up .................................................................................................. 35
Figure 9: Interface for Sin Up.................................................................................................................. 35
Figure 10: Interface for Login ................................................................................................................. 36
Figure 11: Interface for View Details ...................................................................................................... 36
Figure 12:Gantt Chart for ANPRS ......................................................................................................... 41
Figure 13: AON Network Diagram ......................................................................................................... 42
Figure 14: Critical Path Method.............................................................................................................. 42
Figure 15:Read in Image, Grayscale and Blur ....................................................................................... 47
Figure 16:Apply filters and find edges for Localization ........................................................................ 48
Figure 17:Find Contours and Apply Masks ........................................................................................... 48
Figure 18:Grayscale Image of Number Plate ............................................................................................. 49
Figure 19:Render Result .......................................................................................................................... 49

10
 LISTS OF TABLES
Table 1: Use Case for Login ........................................................................................................................ 27
Table 2:Use Case for Detection of Number Plate ................................................................................... 27
Table 3: Login Test Table ........................................................................................................................ 37
Table 4: Registration Test Table ............................................................................................................. 37
Table 5: Capturing Image & Display vehicle information Test Table ................................................. 38
Table 6: Work Breakdown Structure for ANPRS ................................................................................. 40
Table 7: Network Table ............................................................................................................................ 41
Table 8:Hardware Requirements ............................................................................................................ 45
Table 9:Software Requirements .............................................................................................................. 46

11
 Chapter 1

1. Introduction
This Project is about Automatic number plate recognition (ANPR) System. ANPR is a technology
that automatically reads vehicle registration marks (VRMs), allowing these details to be compared
against database records. An ANPR camera takes an image of a vehicle number plate; the image
is passed to a reader, which locates the VRM and reads the letters and characters so that they can
be identified using Optical Character Recognition (OCR) software. An image of the view of the
number plate and/or overview camera is then saved and checked against the database. ANPR data
comprises “read” data and “hit” data. A read is the capture of the VRM and image of the vehicle
as it passes through the camera view; read data is the term used to describe all the data collected
as vehicles pass through the ANPR reader. A hit is a match to a VRM held within the database
being searched. [1] It is can be applied at number of public places for fulfilling some of the
purposes like traffic safety enforcement, automatic toll text collection and checking the number
plate is Licensed or Fake number plate. ANPR is a technology tool which is used in providing
assistance put enforcement have off the law as well. ANPR algorithms are generally divided in
four steps: Vehicle image capture, Number plate detection, Character segmentation and Character
recognition. [2]

1.1 Literature/background studies

There are various techniques for plate detection and segmentation algorithm to implement vehicle
number plate detection. In [3] authors have used high resolution LPR cameras which are designed
to take photographs at high pixel resolution so that it won’t have too much noise. This also helps
the system in segmenting the characters easily. In authors have used pre-trained character
classifier. The vehicle image on which VNLD is to be applied is then sent to the Detect Plates ()
function to get a list of all the possible license plates that are present in the image. Then the cropped
license plates are passed to the Detect Chars () function which gives the predicted number for each
possible character. The character sequence is then returned in a string format and displayed as final
answer. In authors have used OpenCV, a library of programming functions for real time computer
vision. The library has more than five hundred optimized algorithms. OpenCV provides complex
and efficient adaptive thresholding algorithm. In authors have used OCR (Optical Character
Recognition) to detect the license plate number of the vehicles that are moving around. Once a

12
new vehicle is detected, the proposed system detects the region of the plate and applies an
algorithm to extract the image of the plate. In authors have used Image binarization process to
convert an image to black and white. In this method, certain threshold is chosen to classify certain
pixels as black and certain pixels as white. The main challenge is the assigning of the threshold
values for an image. In authors have used MATLAB toolbox function that delivers a function
called region props (). It measures a set of properties for each labelled region in the label matrix.
They have used bounding box to measure the properties of the image region. After labelling the
connecting components, the region will be removed from the input image. This is used for
segmentation of characters.

1.2 Objective
Number plate recognition provides immediate benefits for law enforcement, parking agencies,
security teams, government buildings and more. While NPR is used in many different cases, it’s
proven to be effective at deterring crime, analysing and collecting data, and providing agencies
with real-time solutions. We are designing this system specifically for the new proposed high
security number plates which have black boundary across the number plate and also have a uniform
font all across the country.

• Supports processing of single frames and video streams

• Compares detected plates against a watch list database and provides real-time alerts on
plate matches
• Provides detailed reports
• Handles different plate styles, e.g., regular/stacked
• Can be used for electronic toll collection (ETC)
• Can be connected to gate systems for automated parking access control
• Detect, recognize and search for license plates in real-time or archived footage
• Enables automated matching against a watch list with real-time alerting
• Allows vehicles to be tracked across multiple cameras or locations
• Records and logs all license plates at a scene for later forensic investigation

1.3 Problem Description

Traffic control and vehicle owner identification have become a major problem in every country.
Sometimes, it becomes difficult to identify vehicle owner who violates traffic rules and drives too
fast. Therefore, it is not possible to catch and punish those kinds of people because the traffic

13
personnel might not be able to retrieve the vehicle number from the moving vehicle because of the
speed of the vehicle. Therefore, there is a need to develop the system as one of the solutions to this
problem. Our Detect and Recognize Vehicle License Plate will detect the license plate from an
image and video. It can also detect in real-time using OpenCV and Python-tesseract. The user will
just need to upload an image or video from their device. [4]

1.4 Methodology
• License Plate Recognition Systems use the concept of optical character recognition to read
the characters on a vehicle license plate.
• In other words, LPR takes the image of a vehicle as the input and outputs the characters
written on its license plate.
• LPR systems can actually be developed without using machine learning. Other concepts
like template matching, feature extraction etc. can be used.
• With machine learning, we can improve the system accuracy by improving the training
process.
• We’re going to use machine learning for the character recognition aspect i.e., map a
character image to its actual character and differentiate between As, Bs etc.
• Thing we need to do is create a virtual environment.
• This makes it easy to manage our project dependencies and packages.
• You can use virulency package to create a virtual environment.

• Some key dependencies of the package are SciPy (for some complex scientific
calculations), NumPy (for n-dimensional arrays manipulations) and matplotlib (for plotting
graphs and displaying images). Another important package is Pillow, a python imaging
library.

1.5 Project Scope

The aim of the Number plate recognition is to automate the existing manual system with the help
of full-fledged computerized equipment and computer software, meeting their requirements, so
that their valuable data / information can be stored longer with easy access and handling of the
same. The required software and hardware are readily available and easy to use. [5] As it is not
possible to judge which approach is better, different papers, which are based on steps mentioned,
14
are surveyed and categorized based on the methodologies in each approach. For each approach
whenever available parameters like speed, accuracy, performance, image size and platform are
reported. Commercial product survey is beyond the scope of this paper as sometimes these
products claim more accuracy than actual for promotional purposes. The aim is to automate the
existing manual system with the help of computerized devices and full-fledged computer software
and to meet their requirements so that your valuable data / information can be stored over a longer
period of time, with easy access and manipulation. Basically, the project describes how good
performance and better services can be achieved for customers.

1.6 Feasibility Study

Detailed investigation has really helped in knowing the feasibility of various Software and
hardware components as well as the overall project model in terms of technical, operational and
economical respects. Thus, this project is feasible in all respect. i. Risks Involved: The system
might not be able to detect vehicle license plates if there’s a dim light environment while capturing.
ii. Resource Requirement: We need windows 10 operating system, Python latest version with some
basic development tools like OpenCV, TensorFlow, Pytesseract for the project. Pytesseract is a
Tesseract-OCR Engine to read images type and extract the details available in the image.
Compatible tools like Visual Studio Code, Jupyter Lab. The resources required by the system are
available easily in the market at reasonable cost. This procedure is to determine the benefits and
savings that are expected from a candidate system and compare with cost. Otherwise, further
justification or alterations in proposed system that have to be made if it is having a change of being
approved. This is an ongoing effort that improves in accuracy of each phase of the system lifecycle.
For my project I am not expecting any feasibility costs spent on this on this project because here I
am using open-source environments. [6]

1.7 Solution Application Areas

ANPR offers numerous advantages that are the basis for real-world applications. Most benefits
of ANPR come with automating manual tasks, highly efficient space management, governance,
and increasing the customer experience. The automated recognition of number plates allows
automated alerts and controls for facilities. Hence, ANPR is a key technology for smart cities or
toll stations.

15
 • Automation
• Accuracy
• Analytics
• Identification
• Cost Efficiency
• Low Footprint
• Scalability
• Security

1.8 Tools/Technology
We need windows 10 operating system, Python latest version with some basic development
tools like OpenCV, TensorFlow, Pytesseract for the project. Pytesseract is a Tesseract-OCR
Engine to read images type and extract the details available in the image. Compatible tools like
Visual Studio Code, Jupyter Lab, MySQL/ Microsoft SQL/ Firebase, Google Collab.

1.9 Expertise of the Team Members

All team members pre-equipped with the level of knowledge needed for the successful
completion of this project. We have studies the all-basic courses related to programming. Python
based web application development courses, Database System, Visual Programming, Software
Design and construction etc. And we are equally interested in this project.

16
1.10 Software Process Model
Software process model is an abstract representation of a software process, which is a set of
activities that leads to the production of a software product. Some of the genericprocess
models are waterfall model, evolutionary development and components-based software
engineering. For this project we will follow iterative waterfall process model,because of clear and
unchanging business requirements as shown in Error! Reference source not found..

Figure 1:Iterative Waterfall Process Model

1.11 Milestones

Q4 22 Q1 23 Q2 23
ID Task Name Start Finish Duration
Dec Jan Feb Mar Apr May Jun

1 Proposal 01/12/2022 05/12/2022 5d

2 Software Requirement Specification (SRS) 05/12/2022 13/12/2022 9d

3 Design 13/12/2022 24/12/2022 12d

4 Implementation 24/12/2022 16/06/2023 175d

5 Testing 16/06/2023 26/06/2023 11d

17
 Chapter 2
2 SYSTEM REQUIREMENT SPECIFICATION
2.1 Introduction
This document, Software Requirements Specification (SRS), describes the overall requirements of
the project. It states the scope of the project and details its functional and non-functional
requirements.

2.1.1 Purpose
This Project is about Automatic number plate recognition (ANPR) System. ANPR is a technology
that automatically reads vehicle registration marks (VRMs), These details to be compared against
database records. An ANPR camera takes an image of a vehicle number plate; the image is passed
to a reader, which locates the VRM and reads the letters and characters so that they can be
identified using Optical Character Recognition (OCR) software. Police forces use ANPR for law
enforcement purposes, to check if a vehicle is registered, or to identify vehicles related to traffic
violations.

2.1.2 Document Conventions

This document is going to be useful documentation for anyone who will be looking to learn about
the software. There will be a detailed description of the features and concepts used which makes
it scalable.

2.1.3 Intended Audience and Reading Suggestions

The audience of system will be: This document is intended for developers, project managers,
marketing staff, users, testers and Documentation writers.

Key Target Audience:

• Automatic number plate recognition (ANPR) system service provider companies.

• Market research and consulting firms.
• Government bodies such as regulating authorities and policy makers.
• Organizations, forums and alliances related to automatic number plate recognition
(ANPR) system.

18
2.1.4 Product Scope
The scope of the Number plate recognition is to automate the existing manual system with the help
of full-fledged computerized equipment and computer software, meeting their requirements, so
that their valuable data / information can be stored longer with easy access and handling of the
same. It can get the details of the vehicle number to reduce the malicious activity of vehicle
transportation. As it is not possible to judge which approach is better, different papers, which are
based on steps mentioned, are surveyed and categorized based on the methodologies in each
approach. For each approach whenever available parameters like speed, accuracy, performance,
image size and platform are reported.

2.2 Overall Description

2.2.1 Product Perspective
Existing System study reveals that there are some inconveniences of the past and current
framework. In some surveys the Number plate recognition system is a complete human interaction
with system (Man power). Here we can see that ANPR technology has the ability to detect and
recognize vehicles by their number-plates using recognition techniques. They used Deep-Learning
techniques which are widely utilized in CV field for better detection rates but it minimizes the
accuracy rate. Poor image resolution, usually because the plate is too far away but sometimes
resulting from the use of a black and white quality camera. Blurry images, particularly motion
blur. In this project, we propose an automatic and mechanized number plate recognition system
which can extract the license plate number of the vehicles passing through a given location using
image processing algorithms Using special cameras, the system takes pictures from each passing
vehicle and forwards the image to the computer for being processed by the ANPR software. Plate
recognition software uses different algorithms such as localization, orientation, segmentation and
finally optical character recognition (OCR).

2.2.2 Product Functions

The whole system can be divided into four main parts: Image Pre-processing, Number Plate
Localization, Character Segmentation and Character Recognition. Each main part contains some
important functions as shown below:

• Automatically reads vehicle registration marks

• Covert the Picture form of Number plate into Character System
• These details to be compared against database records
19
 • Provides real-time alerts on plate matches
• Provides detailed reports
• Allows vehicles to be tracked across multiple cameras or locations
• Records and logs all license plates at a scene for later forensic investigation

2.2.3 Operating Environment

This system is web-based system, user can use easily at desktop system, tablet or any mobile
browser. The system will be connected with internet. This web system has some requirements to
be accomplished. It needs hardware and software.

2.2.3.1 Hardware Requirements:

• Processor: i5 and above
• Min. 4GB RAM, 64-bit Operating System.
• Camera
• GPU (recommended)

2.2.3.2 Software Requirements:

• Python 3.9.5
• Different Python Packages
• OCR Technology
• MY SQL 8.0.31

• windows 10 or later

2.2.4 Design and Implementation Constraints

Research shows that plate recognition results are affected due to limitations in the distance, angle
of view, illumination conditions, and background complexity. Better recognition accuracy can be
achieved if these factors can be controlled.

2.2.5 User Documentation

User manual describing complete functioning and configuration of software is included.
Understand how to use the software and how to operate from the admin control and from the users.

2.2.6 Assumptions and Dependencies

• Result will show on the basis of captured images.
• The users have sufficient knowledge of computers, mobile or tablet.
• Backup power, internet bandwidth.
20
 • Internet availability

2.3 External Interface Requirements

External interface requirements specify hardware, software, or database elements with which a
system or component must interface.

2.3.1 User Interfaces

The features of user interface of our Web based Application are Admin Login, if in admin there
are new people then first register new account, user interface provide us capture option to capture
image of number plate of vehicle then process and give us number in the form of character then
fetch the detail of vehicle from database and show information and at last admin can logout.

2.3.2 Hardware Interfaces

Need a computer system to run the system with internet connection and Camera that used to
capture an image of vehicle number plate in run time, with TCP/IP ports, Power supply ports.

2.3.3 Software Interfaces

The software will interface with windows operating system and Web-Based Application. No
interaction with any other software or system.

For creating Model, we use:

• Dataset of Automatic number plate recognition.

• Python 3.8.1 or higher.
• MY SQL 8.0.31.
• Python packages.

• Jupyter, Goggle Collab, PyCharm or VS-Code IDE.

2.3.4 Communications Interfaces

There is an internet connection required to run this software, and power supply for the camera and
Computer System.

2.4 System Features

The functions listed below should be performed by system in order to call this

21
2.4.1 Functional Requirements

2.4.1.1 User Login

This process will verify the username and password. This process will verify the username and
password.

2.4.1.2 Creating New User

New user creation if they have not already an account, then registered to provide the required
details for create an account.

2.4.1.3 Capture
The image of the vehicle is captured using a high-resolution photographic camera. A better choice
is an Infrared (IR) camera. The camera may be rolled and pitched with respect to the license plates.

2.4.1.4 Pre-process
Pre-processing is the set algorithms applied on the image to enhance the quality. For the present
system pre-processing involves two processes:

• Resize – The image size from the camera might be large and can drive the system slow. It
is to be resized to a feasible aspect ratio.
• Convert Colour Space – Images captured using IR or photographic cameras will be either
in raw format or encoded into some multimedia standards.

2.4.1.5 Number plate segmentation

The input is the image of the plate; we will have to be able to extract the unicharacter images. The
result of this step, being used as input to the recognition phase, is of great importance.
Segmentation is one of the most important processes for the automatic identification of license
plates, because any other step is based on it.

2.4.1.6 Character Recognition

Number Plate Recognition is to actually read the number plate information from the segmented
image. We will use the python packages to read characters from image.

2.4.1.7 Get Vehicle Information

Here we could get the information from the database.

2.4.1.8 Display Information of Vehicle

Here we could Display the information from database which is from the cloud.

22
2.4.1.9 Logout
This module allows user to exit from the system.

2.4.2 Other Non-functional Requirements

2.4.2.1 Usability
• The web-based system will allow the users to access the system from the internet.
• Since all users are familiar with the general usage of browsers, no specific training is
required.
• The system is user friendly and self-explanatory.
2.4.2.2 Reliability
The web-based system has to be very reliable due to the importance of data and damages
incorrect or incomplete data can do.
2.4.2.3 Performance
The web-based system has to be very reliable due to the importance of data and damages
incorrect or incomplete data can do.
2.4.2.4 Response Time
The information page should be able to be downloaded within a minute or less using a 56K
modem. The access time for a mobile device should be less than a minute.
2.4.2.5 Safety Requirements
Wrong password should not be entered. If any person forgets his password a facility provides to
him to recover his password using his register e-mail address.
2.4.2.6 Security Requirements
Data will be private and cannot be accessed from un-authorized users.
2.4.2.7 Feasibility study
Detailed investigation has really helped in knowing the feasibility of various Software and
hardware components as well as the overall project model in terms of technical, operational and
economical respects. Thus, this project is feasible in all respect.
i. Risks Involved: The system might not be able to detect vehicle license plates if there’s a dim
light environment while capturing.

23
 Chapter 3
3 SYSTEM DESIGN

Introduction of Design Document

Design is the first step in the development phase for any engineered product or system. The
designer’s goal is to produce a model or representation of a class that will later be built. Beginning,
once system requirement has been specified and analysed, system design is the first of the three
technical activities -design, code and test that is required to build and verify software. This
document details out the overall software design. The importance can be stated with a single word
“Quality”. Design is the place where quality is fostered in software development. Design provides
us with representations of software that can assess for quality. Design is the only way that we can
accurately translate a customer’s view into a finished software product or system. Software design
serves as a foundation for all the software engineering steps that follow. Without a strong design
we risk building an unstable system that will be difficult to test, one whose quality cannot be
assessed until the last stage. During design, progressive refinement of data structure, program
structure, and procedural details are developed reviewed and documented. System design can be
viewed from either technical or project management perspective. From the technical point of view,
design is comprised of four activities – architectural design, data structure design, interface design
and procedural design.

3.1 Design Approach

Design approach for this software is conventional, that is, database model used is relational and
on the other side Object modelling technique (OMT) is used.

3.1.1 Class Model

The class model shows static class objects in a system and the relationships between them. Two
particularly important relationships are generalization (inheritance) and aggregation each class
object on the diagram often shows the class name, its attributes, and operations. Here we capture
the real-world concept that are important to our application.

3.2 Object Modelling Technique (OMT)

OMT is object-oriented design approach, here we used two fundamental modelling techniques
which are class and interaction modelling.

24
3.2.1 Interaction Model
This model describes the interaction between the objects. Its diagrams are:

• Use Case Diagram

• Sequence Diagram
• Activity Diagram

3.3 Use Case Diagram

Use case illustrates a unit of the functionality provided by the system. The main purpose of the
use-case diagram is to help development teams visualize the functional 4 requirements of a system,
including the relationship of "actors" (human beings who will interact with the system) to essential
processes, as well as the relationships among different use cases. In this use case diagram, the
ANPR System is the main subject of the diagram and it has three use cases, "Capture Image",
"Process Image" and "Recognize Plate". These use cases represent the main functions of the ANPR
system. The system captures the image of a vehicle and its license plate, processes the image to
extract the license plate number and then recognizes the plate number and compares it with the
database to check for the vehicle details.

The use case of Automatic Number Plate Recognition System in Figure 2.

25
 Plate Recognition System

Login

Register

Capture Image
<< include >>
Character
Recognition

Check Vehcle
Details
<< include >>
Admin
Show Details

Log out

Figure 2:Automatic Number Plate Recognition System

The description of use case login is show in Table 1 that describe that user can login to the system
and will have access. The preconditions are that the user must have to login to the system.
Description, the user enters a username and password to log in to the system for authenticated
entry.

26
 Table 1: Use Case for Login

Use Case Login

Actor Admin

Pre-condition User must have a username and password

Post-condition User logged in

Description The user enters a username and password to log in to the system
for authenticated entry.

A use case is a written description of how system will perform tasks. It outlines, from a user point
of view, a system’s behaviour as it responds to a request. Preconditions are that identify number,
Images are captured and stored in a repository. Post conditions are that the license plate numbers
are recognized and displayed on the terminal. Descriptions, the user runs the web-based application
and detect the number plate of vehicle. The description of use case Detection of number plate is
shown in Table 2

Table 2:Use Case for Detection of Number Plate

Use Case Detect Number Plate

Actor Admin

27
 Pre-condition Identify number, Images are captured and stored in a
repository.

Post-condition The license plate numbers are recognized and displayed on

the terminal.

Description The user runs the web-based application and detects the
number plate of vehicle and show results.

3.4 Entity Relationship Diagram (ERD)

Entity Relationship Diagram, also known as ERD, ER Diagram or ER model, is a type of structural
diagram for use in database design. An ERD contains different symbols and connectors that
visualize two important information: The major entities within the system scope, and the inter-
relationships among these entities. And that's why it's called "Entity" "Relationship" diagram
(ERD). When we talk about entities in ERD, very often we are referring to business objects such
as people/roles (e.g., Student), tangible business objects (e.g., Product), intangible business objects
(e.g., Log), etc. "Relationship" is about how these entities relate to each other within the system.
In a typical ER design, you can find symbols such as rounded rectangles and connectors (with
different styles of their ends) that depict the entities, their attributes, and interrelationships. An ER
diagram can help businesses document existing databases and thereby troubleshoot logic or
deployment problems or spot inefficiencies and help improve processes when a business wants to
undertake business process re-engineering. ERDs can also be used to design and model new
databases and make sure that engineers can identify any logic or design flaws before they're
implemented in production.

• Document an existing database structure

• Debug, troubleshoot, and analyse
• Design a new database
• Gather design requirements
• Business process re-engineering (BPR)

When documenting a system or process, looking at the system in multiple ways increases the
understanding of that system. ERD diagrams are commonly used in conjunction with a data flow

28
diagram to display the contents of a data store. They help us to visualize how data is connected in
a general way, and are particularly useful for constructing a relational database. An ER diagram
has three main components: entities, relationships, and attributes connected by lines. The
"Camera" entity represents the physical cameras that are used to capture images of vehicles and
their license plate numbers. It has attributes such as the camera's location and the date and time
when it captured an image. The "Image" entity represents the images captured by the ANPR
cameras. It has attributes such as the image's resolution and file format, as well as a reference to
the camera that captured it. The "Recognition" entity represents the process of recognizing the
license plate number from an image. It has attributes such as the recognized license plate number,
the date and time when recognition took place, and the confidence level of the recognition.

Admin Camera image

PK id PK camera_id PK image_id
intract captuer
name location image

email date_time

password FK camera_id

associate

Vehicle_Detail Recognition
PK id
PK rec_id
number
number
model
date_time
vehicle_color associate

registartion_date

owner_name

owner_contact

owner_address

Figure 3:ERD For Automatic Number Plate Recognition System

29
The "Vehicle" entity represents a vehicle that is detected by the ANPR system. It has attributes
such as the vehicle's license plate number, make and model, and colour. The "Owner" entity
represents the owner of the vehicle. It has attributes such as the owner's name, address, and contact
information.

The relationships between these entities are:

• A camera captures one or more images.

• An image is captured by one camera.
• An image is associated with one recognition.
• A recognition is associated with one vehicle.
• A vehicle is owned by one owner.
• A vehicle is of one type of vehicle.

3.5 Sequence Diagrams

Sequence diagrams show a detailed flow for a specific use case or even just part of a specific use
case. They are almost self-explanatory; they show the calls between the different objects in their
sequence and can show, at a detailed level, different calls to different objects. A sequence diagram
has two dimensions: The vertical dimension shows the sequence of messages/calls in the time
order that they occur; the horizontal dimension shows the object instances to which the messages
are sent.

A sequence diagram simply depicts interaction between objects in a sequential order i.e., the order
in which these interactions take place. We can also use the terms event diagrams or event scenarios
to refer to a sequence diagram. Sequence diagrams describe how and in what order the objects in
a system function. These diagrams are widely used by businessmen and software developers to
document and understand requirements for new and existing systems.

30
 Plate Character vehicle
Admin Camera
Capture_image Frame
localization recognition details

request for
image capture

capture failed

Re capture
convert into
frame
detect n umber
plate extract
num into
character
request f or
vehicle details

Show vehicle details

Figure 4:Sequence Diagram for Automatic Number Plate Recognition

In this sequence diagram, the ANPR System object initiates the process by calling the capture
Image () method on the Camera object. The Camera object captures an image of a vehicle and its
license plate and returns it to the ANPR System object. The ANPR System object then passes the
image to the Image Processing object's process Image () method, which processes the image, such
as by converting it to grayscale, applying filters, or performing OCR to extract the license plate
number. The processed image is then passed to the License Plate objects recognize () method
which analyses the processed image to detect and recognize the license plate number. The ANPR
System object then passes the extracted license plate number to the Vehicle Database object's
check () method to check the details of the vehicle.

3.6 Class Diagram

After the identification of classes their attributes and the relationships among them our class
diagram is given below Figure 8. In software engineering, a class diagram in the Unified Modelling
Language (UML) is a type of static structure diagram that describes the structure of a system by
showing the system's classes, their attributes, operations (or methods), and the relationships among
objects.

31
 Admin
Capture_Image Pre_Processing
-ID_No:Int
-Email_Id:String 1 1
-Image_Name -Frames
-User_Name:String
-Password:String Operations 0...1
-cv2.Gaussian_Blur( )
+ LogIn( ) cv2.Image_Capture -cv2.cv1Color( )
+ Register( ) -cv2.Sobel( )
+ LogOut( ) -cv2.Threshold( )

Character_Recognition
0...1
-Segmented_Characters
+ Compare_Images
MSC( )

Vehicle_Detail
-Owner_Name:String
-Vehicle_Reg_Date:Date
0...1 -Vehicle_Type:String
-Vehicle_Number:String
-Vehicle_Model:Stdering
-Address:String
-Contact_Number:String
+ Request_For_Vehicle_Detail( )
+ Show_Vehicle_Detail( )

Figure 5:Class Diagram for Automatic number Plate recognition system

An automatic number plate recognition (ANPR) system typically includes the following classes:

Camera: responsible for capturing images of vehicles and their license plates.

Image Processing: responsible for processing the captured images, such as by converting them
to grayscale, applying filters, or performing optical character recognition (OCR) to extract the
license plate number.

Database/Vehicle Detail: responsible for storing information about vehicles and their license
plates, such as registration details and owner information.

32
3.7 Activity Diagram
Activity diagrams show the procedural flow of control between two or more class objects while
processing an activity. Activity diagrams can be used to model higher-level business processes at
the business unit level or to model low-level internal class actions. In my experience, activity
diagrams are best used to model higher-level processes, such as how the company is currently
doing business, or how it would like to do business. This is because activity diagrams are "less
technical" in appearance than sequence diagram, and business minded peoples tend to understand
the quickly.

Login

Register

No
Authentication Valid User No

Verify Credentials Yes

Success

Yes Home

Figure 6: Activity diagram for Login

33
 Capture image

Process Image

Recognize number

Check vehicle
Details

yes no

Show vehicle Details not

Details found

Figure 7: Activity Diagram for ANPRS

In this activity diagram, the process starts with the "Start ANPR system" activity. From there, the
next step is "Capture image" where the camera captures the image of the vehicle and its license
plate. Then the "Process image" activity takes place where the captured image is processed, such
as by converting it to grayscale, applying filters, or performing OCR to extract the license plate
number. Next, the "Recognize plate" activity takes place where the processed image is analysed
to detect and recognize the license plate number. Finally, the "Check details" activity takes place,

34
where the extracted license plate number is passed to the database to check for details of the
vehicle like make, model, year, colour, etc.

3.8 Interface Design

Figure 8: Interface for Login or Sin Up

Figure 9: Interface for Sin Up

35
 Figure 10: Interface for Login

Figure 11: Interface for View Details

36
3.9 Test Cases
Test cases for Login test is shown in Table 3 which indicate the Login of admin or user. Test cases
for Registration Test is shown in Table 4 which register the new user and then login to system.
Test cases for Capturing Image & Display vehicle information Test is shown in Table 5 which
indicate that it captures image convert into character map it with database if match then display
vehicle detail otherwise show message number plate is fake and not recognized.

3.10 Login Test:

Table 3: Login Test Table

Test-Case ID: TC-01

Test-Case Name: Login (Admin & Client)
Pass/Fail Criteria: The test passes if the user enters a correct
username or password that is contained in the
database.

Input Data: Numeric and alphabet key code

Test Procedure: Expected Outcomes:
Step1: An error message is shown informing the user
Type an incorrect username about the error.
or password
Step 2: System indicate success; records successful
Type a correct username and password access in the database; user is redirected to the
homepage

Comments: The login page has a link that directs users that
are not already registered to the registration
page.

3.11 Registration Test:

Table 4: Registration Test Table

Test-Case ID: TC-02

Test-Case Name: Registration
Pass/Fail Criteria: The test passes if the user provide personal
information like username, email, password,
verify password all this information is to be
inputted into their respective fields in a form

Input Data: Numeric and alphabet key code

Test Procedure: Expected Outcomes:

37
 Step1 An error message is displayed.
Empty fields in the form

Step 2 System indicate success; records successful

Fill in all the fields access in the database If the password and verify
password are the same, the system checks the
email is already registered correct, then a new
user is created.

Step 3 System failure. records unsuccessful

Type different passwords in the fields of attempt in the database; an error message
password and verify password is displayed

Step 4 System indicate success; records successful

Type same passwords in the access in the database the password and verify
fields of password and verify password are the same, then the system checks
password the email is already registered correct, then a
new user is created.

3.12 Capturing Image & Display vehicle information Test:

Table 5: Capturing Image & Display vehicle information Test Table

Test-Case ID: TC-3

Test-Case Name: Capturing image
Pass/Fail Criteria: The test passes if admin click on capturing
image part. In this interface the following
functionalities are implemented for the fetching
image
Input Data: users click on admin part.
Test Procedure: Expected Outcomes:
Step 1 Frame The image of the vehicle is captured using a
high-resolution photographic camera. A better
choice is an Infrared (IR) camera. The camera
may be rolled and pitched with respect to the
license plates.
Step 2 Pre-processing is the set algorithms applied on
Pre-processing the image to enhance the quality. For the
present system pre-processing involves two
processes: Resize and Convert colour space.

38
Step 3 The input is the image of the plate, we will have
Plate Segmentation to be able to extract the unicharacter images.
The result of this step, being used as input to the
recognition phase, is of great importance.
Segmentation is one of the most important
processes for the automatic identification of
license plates, because any other step is based
on it.
Step 4 Number Plate Recognition is to actually read the
Character Recognition number plate information from the segmented
image.
Step 5 Here we could get the information from the
Get vehicle Information cloud and store it on database.
Step 6 Here we could Display the information from
Display Vehicle information database which is from the cloud.

39
 Chapter 4

4 SOFTWARE PROJECT MANAGEMENT

4.1 Project Management Techniques
Project management is the process of leading the work of a team to achieve all project goals within
the given constraints. This information is usually described in project documentation, created at
the beginning of the development process. The primary constraints are scope, time, and budget.
These two techniques we are using in our system.

• Gantt Chart
• Critical Path Method

4.1.1 Work Breakdown Structure for ANPRS

Work Breakdown structure for ANPRS is shown in Table 6. We have Different levels and level
IDS we can perform activities on each id. All this is for dividing work to complete in the sequence
and have details of each activity to be performed.

Table 6: Work Breakdown Structure for ANPRS

Level Activity
1 Idea
2 Research Work
3 SRS
4 Design Documentation
5 Progress Presentation
6 Implementation & Testing

4.1.2 Gantt Chart

A Gantt chart is a graphical depiction of a project schedule. It is a type of bar chart that shows the
start and finish dates of several elements of a project that include resources, milestones, tasks and
dependencies.

Gantt chart for ANPRS is shown in Figure 12.

40
 Q4 22 Q1 23 Q2 23
ID Task Name Start Finish Duration
Dec Jan Feb Mar Apr May Jun

1 Proposal 01/12/2022 05/12/2022 5d

2 Software Requirement Specification (SRS) 05/12/2022 13/12/2022 9d

3 Design 13/12/2022 24/12/2022 12d

4 Implementation 24/12/2022 16/06/2023 175d

5 Testing 16/06/2023 26/06/2023 11d

Figure 12:Gantt Chart for ANPRS

4.1.3 Critical Path Method:
The critical path method (CPM) is a technique where you identify tasks that are necessary for
project completion and determine scheduling flexibilities. A critical path in project management
is the longest sequence of activities that must be finished on time in order for the entire project to
be complete. The critical path method (CPM) is a technique that's used by project managers to
create a project schedule and estimate the total duration of a project. Critical Path Method for
ANPRS have activity, description, immediate predecessor and activity of the project as shown in
7.

Table 7: Network Table

Activity Description Immediate Activity Time,

Predecessor Weeks
A Generation of Idea - 3 Weeks
B Research and related work-study A 5 Weeks
C Making SRS B 4 Weeks
D Design Phase documentation C 5 Weeks
E Presentation of the Design phase B, C 2 Week
F Implementation and Testing E 2 weeks
4.1.4 Activity on Node diagram
We can see how we can draw activity on node, that how the activity is drawn on node from start
to the point ‘F’ as shown in Figure 13.

41
 Figure 13: AON Network Diagram
4.1.5 Critical Path Method
The Critical path method is that who is the largest of path in the project. The critical path method
for our project is given below Figure 14.

Figure 14: Critical Path Method

4.1.6 Paths
Two paths we can obtain in critical path method is given below,
A B C D E F = 35 Weeks

A B C E F = 30 Weeks

So ABCDEF is a critical path for this project.

4.1.7 Time Period:

This project will take 30 weeks to complete on normal.

42
4.2 Total Cost:
To estimate the effort and cost required to develop the Automatic Number Plate Recognition
(ANPR) system, we can use the Function Points calculated earlier and the following industry
standard assumptions: It takes about 20 person-hours to develop one Function Point (FP) of
software The average cost of one person-hour is $50 Based on these assumptions, we can estimate
the effort and cost required to develop the ANPR system as follows: Effort = Function Points x 20
person-hours per FP = 106 x 20 = 2,120 person-hours Cost = Effort x Cost per person-hour = 2,120
x $50 = $106,000 Therefore, we estimate that the development of the ANPR system would require
approximately 2,120 person-hours of effort and would cost approximately $106,000. To calculate
the cost per Function Point, we can divide the total cost by the total number of Function Points as
follows:

Cost per FP = Total cost / Total Function Points = $106,000 / 106 = $1,000 per FP Therefore, the
estimated cost per Function Point for the ANPR system is $1,000. Note that the actual effort, cost,
and cost per Function Point may vary depending on various factors such as the complexity of the
software, the development tools and environment used, the skills and experience of the developers,
and so on. These estimates are based on industry standard assumptions and are meant to provide a
rough estimate of the effort and cost required to develop the ANPR system.

4.3 Productivity
To calculate productivity for the Automatic Number Plate Recognition (ANPR) system, we need
to first calculate the size of the software in lines of code (LOC) and then divide it by the effort
required to develop the software. The formula for productivity is as follows:

Productivity = Size of the software (in LOC) / Effort (in person-hours)

To estimate the size of the software, we can use the Function Points calculated earlier and convert
them to LOC using a conversion factor. The conversion factor can vary depending on the
programming language, development methodology, and other factors. For the purpose of this
calculation, we will use a conversion factor of 50.

Size of the software (in LOC) = Function Points x Conversion factor = 106 x 50 = 5,300

43
Assuming that the ANPR system was developed by a team of 5 developers working for 3 months,
the total effort required would be 5 x 3 x 160 = 2,400 person-hours. Here, we assume that each
developer works for 8 hours a day and 5 days a week, which gives us 160 hours per month.
Therefore, the productivity of the ANPR system can be calculated as follows:

Productivity = Size of the software (in LOC) / Effort (in person-hours) = 5,300 / 2,400 = 2.21 LOC
per person-hour.

This means that on average, each developer was able to produce 2.21 lines of code per hour during
the development of the ANPR system. Note that this is just an estimate and the actual productivity
may vary depending on various factors such as the skills and experience of the developers, the
complexity of the software, the development tools and environment used, and so on.

44
 Chapter 5
5 PROJECT IMPLEMENTATION
5.1 PROGRAMMING LANGUAGE
We use Python as a programming language in android studio to do all the necessary tasks and
operations that are required to achieve the proposed solution of our project. We are using VS Code
latest version to develop application. By using this language, we are doing interact with modules
and implement other different modules.

5.2 FRAMEWORK
Python is an elegant and type-safe language that enables developers to build a variety of secure
and robust applications that run on the Python Framework. You can use Python to create windows
client applications, XML web services, distributed components, client server applications,
database applications, and much more Python provides an advanced code editor, convenient user
interface designers, integrated debugger and many other tools to make it easier to develop
application based on the Python Language.

5.3 SYSTEM REQUIREMENTS

5.3.1 Hardware Requirements

This phase of the software development process deals with a brief study of different hardware used
in the computerized system. There is a list of hardware materials used during the making and also
during the use of the proposed system. As the new system to be made into a computerized
functional system, requirement of a computer is must. All the hardware needed here are generally
the basic configuration of a typical office computer. A list of the hardware requirement used in the
system given below:

Table 8:Hardware Requirements

Laptop For designing and developing applications, we need a laptop having
at least 8 gigabytes of RAM, 520 gigabytes HDD and high frequency
processor (minimum core i5).

45
5.3.2 Software Requirements
Along with the hardware, used in the system it requires software to make a system as well as to
run a system with the computer hardware. Collection of different types of hardware into a specific
type can form a computer but it cannot execute different process on its own. For efficient and
proper working of any system software must be installed. This software’s may be in the form of
operating system or application software. To make the system one also needs to use software. The
software’s used in the proposed system are the latest versions of them and can give up-to-date and
perfect result of every process in the system. This software comprises operating system and
application software used in the system.

Table 9:Software Requirements

Language Python

Platform VS Code, Google Collab

Libraries OpenCV, NumPy, Pandas, Matplotlib, Easyocr, Imutils

5.4 Implementation
This section of document provides a general overview of coding of our Automatic number Plate
Recognition System, the codes for some important functions are outlined here.

46
5.4.1 Read in Image, Grayscale and Blur:

Figure 15:Read in Image, Grayscale and Blur

47
 5.4.2 Apply filters and find edges for Localization:

Figure 16:Apply filters and find edges for Localization

5.4.3 Find Contours and Apply Masks:

Figure 17:Find Contours and Apply Masks

48
5.4.4 Grayscale Image of Number Plate:

Figure 18:Grayscale Image of Number Plate

5.5 Render Result:

Figure 19:Render Result

5.6 Chapter summary

This chapter basically captures the design architecture of the project, the languages and other
different tools used to develop this project. It describes the functionality of the framework which
we are using in this project. Framework allows writing cross-platform software to control devices
to create all kinds of creative coding. Also, it describes the hardware and software requirements of
the project along with their working.

49
 6 References

[1] “ALERTSYSTEM, "alertsystem.co.uk," AlertSystems Ltd, [Online]. Available:

https://www.alertsystems.co.uk/security-solutions/anpr-automatic-number-plate-
recognition/how-anpr-
works/#:~:text=An%20ANPR%20camera%20takes%20an,Character%20Recognition%20(O
CR)%20so”.

[2] “C. I. Patel, "Automatic Number Plate Recognition system (ANPR)," Internation journal of
Computer Application (0975-8887), vol. 69, no. 9, May 2013, p. 33, 2013.”.

[3] “M. K. R. B.Santoshmanojkumar, "University Campus Number Plate logging System,"

International Journal of Innovative Technology and Exploring Engineering, vol. 8, no. 07
May-2019., p. 5.”.

[4] “L. Yao, Y. Zhao, J. Fan, M. Liu, j. jiang and Y. Wan, "Research and Application of License
Plate Recognition Technology Based on Deep Learning," Journal of Physics Conference
Series 1237(2):022155, p. 6, June 2019.”.

“Y.-H. P. Chih-Hai Fana, "Vehicle License Plate Recognition System Design," Chung Hua
[5] Journal of Science and Engineering, vol. 7, no. 2009, p. 53.”.

[6] “S. Kasaei and S. Kasaei, "https://www.internationaljournalssrg.org," IJCSE-V2I12P102, vol.

] 2, no. 2015, p. 8.”.

50