Department of Electronics and Telecommunication Engineering

M.Sc. Proposal:-Automated Vehicle License

Plate Detection System Using Image Processing
Algorithms
Supervisors: Md. Taslim Arefin, Associate Professor and Head
Saidur Rahman
ID:-183-31-255
Department of Electronics and Telecommunication Engineering
Daffodil International University Dhaka, Bangladesh

Abstract:-
At present, the traffic engineering and automation have developed, and the vehicle license
plate recognition technology need get a corresponding improvement. In case of identifying a
car license picture, the principle of automatic license plate recognition is illustrated in this
paper, and the processing is described in detail, which includes the preprocessing, the edge
extraction, the license plate location, the character segmentation, the character recognition.
Matlab edits the program implementing recognition. The example result shows that the
recognition method is feasible, and it can be put into practice.
Keywords— Image Compression, artificial intelligence, logic programming, constraint
programming, machine learning, bioinformatics

Aims:-
Vehicle identification plays important role in Intelligent Transportation System. Its number
plate identifies vehicle uniquely. It is used for applications like identification of authorized
vehicles, providing controlled access to restricted areas, and law enforcement.
Objects:-
The objectives of this project is to develop fast and accurate automated vehicle license plate
detection system for real time application. To achieve this goal the thesis has the following
objectives:
(i) To develop a novel technique for License Plate Detection (LPD) for an AVNPR
system, which should full-fill the requirement of a real-time system and efficient in
general sense.
(ii) To design and simulate the proposed LPD system
(iii) To verify the functionality and effectiveness of the technique in different scenarios
using benchmark images of license plate.

Automated Vehicle License Plate Detection System Using Image Processing Algorithms 1 of 5
 Department of Electronics and Telecommunication Engineering

Introduction:-
Amidst the hassles of the bustling ‘smart’ life that we live in, the development of a smart
transportation managing system, which provides the data of vehicle numbers that can be used
in follow up, analyses and monitoring, is quite necessary. Vehicle tracking, recognition and
management are major issues to be tackled in modern traffic control systems. Automatic
License Plate Recognition (ALPR) systems have their use in several in several applications of
traffic and security, such as parking management, toll fee collection, access and border control,
tracking of stolen cars etc. ALPR system involves capturing the image from a digital camera,
pre-processing of the image to remove noise, make the image suitable for character
segmentation, and thereby character recognition. The output of this system is the license plate
of the vehicle and the system can be tuned to accommodate the end user's requirement. One
such user requirement that is focused in this paper is the automation of parking security and
management at malls, colleges, offices, etc. The system that is developed can be used to
automatically detect a vehicle coming into a parking lot and/or toll booth. An image of the
vehicle is captured and the license plate is extracted. Once the characters are recognized, the
user is allowed to manage the system using a GUI. The GUI provides the timestamp of the
vehicle entering the premises, thereby allowing the user to monitor all the vehicles passing
through the premises.
Research methodology:
Vehicle license plate recognition has been an active research for the past few years. This thesis
try to automate the process of license plate recognition, improve the optimization of the neural
network, to achieve prediction accuracy greater than 95% and reduce running time to about 1
second. For localizing the LP, several techniques have been addressed. Horizontal edge
detection addressed in and double edge detection in are two such edge detection algorithms.
The techniques in make use of morphological operations along with other technique, however
specifically used only morphological processing.
Morphological Processing:
Morphology is defined as a particular shape or structure and when employed in image
processing, it is a collection of nonlinear operations related to the shape in an image.
Morphological techniques are applied on an image with a small template known as a
structuring element. This structuring element is centered on all the pixels of the image and
mathematical operations are carried with its corresponding neighborhood of pixels. A
structural element of diamond was used to dilate the image. This process enhances the bright
regions surrounded by dark regions and reverse is true for dark regions surrounded by bright
regions. Further, a disk was used to erode the image. A morphological algorithm was employed
on the database by applying canny edge detection, and henceforth being able to localize the
plate. However, it was found that this algorithm executed with a relatively lower percentage
of 83%. It was found that this algorithm did not work effectively on white cars having white
background number plates since the license plates did not appear to have a definite edge. The
edge of the number plate blends with the colour of the car, thereby not giving a distinct edge
when canny edge detection is applied. The algorithm failed for different illuminating

Automated Vehicle License Plate Detection System Using Image Processing Algorithms 2 of 5
 Department of Electronics and Telecommunication Engineering

environments. Therefore, this algorithm was discarded and edge projection technique was
employed, which improved the efficiency of the algorithm significantly.
Edge Processing:
Edges are boundaries that indicate sudden changes of discontinuities. In a license plate there
is a transition from relatively dark to light regions, i.e. characters and white spaces, and these
transitions are considered to be edges. Edge processing is the technique where histograms of
the edges processed are plotted. These edges are processed in both horizontal and vertical
directions in order to provide a probable region of the license plate.

Character Extraction:-
The extracted characters from the license plate are the input layer units of the neural network.
Most Indian license plates contain an ‘IND’ hologram as per the High Security Registration
Plates. To segment the characters, the image is converted to binary by applying a global
threshold obtained from Otsu’s method . These irrelevant features are removed by area opening
and border clearing.
Neural Network:-
Amongst the several techniques of training the neural network, this paper has been
implemented based on supervised learning. In order to predict the characters, the training set
has an input vector ‘X’ and a corresponding desired output value ‘Y’. This network makes use
of three layers i.e. an input, hidden and output layer. Feed- forward backpropagation algorithm
has been used to train the network. The training set was created from the license plate database
that was used for plate localization. Also, a variety of fonts that are inbuilt in Microsoft Word
have been incorporated into the training set. The database consisted of 1391 characters. The
neural network was trained using 70% of these characters and remaining 30% of these
characters were used for cross-validation. The dataset was created by extracting the characters
from the license plate and resizing them into a 55 by 30 binary image. At first, the network had
a single hidden layer having 25 units. The input layer consisted of 1650 units while the output
layer had 36 units.
My research proposal
In this thesis, an LPD method is presented to overcome the issues raised in the literature,
which include complex environment, rotation, lighting, low contrast, and blurriness. The
proposed method also has high degree of freedom about license plate size and orientation.
Here we have declared the steps for the proposed technique for license plate detection using
FRIT. Shows the workflow for the proposed method.

Automated Vehicle License Plate Detection System Using Image Processing Algorithms 3 of 5
 Department of Electronics and Telecommunication Engineering

Fig:-Work Flow of the Proposed Technique

Conclusions
Automatic vehicle number plate recognition (AVNPR) is plays an important role in intelligent
transportation system and it has huge number of practical applications such as automatic toll
collections, parking fee payment, detection of vehicle crossing speed limits and thereby
reducing road accidents etc. LPD is one of the most crucial components of total solution of
AVNPR. Literatures have been extensively reviewed and found the challenges in this area due
to the varying size, shape and position (rotation) of the plate, varying illumination condition,
varying color, type and noises in the image. Again the image may be blurred which is a
common scenario for motion compensated pictures. Obstacles such as shadows, dirt and dust
may make the system too difficult to detect the license plate. This thesis presents FRIT based
effective LPD system that can overcome all of these limitations. Experimental results over a
number of benchmark images presented in this thesis shows that it can process the
computational work for license plate detection in real time. Detection accuracy of the research
work is also compared with that of others researches where it is shown that our work
outperforms all the existing techniques. A field test has also been conducted to prove the proper
functionality of the proposed technique and test the performance, which shows that our work
is also effective in this case.

Automated Vehicle License Plate Detection System Using Image Processing Algorithms 4 of 5
 Department of Electronics and Telecommunication Engineering

Time Schedule:-

GANTT CHART OF THESIS

Start Time Complete Incomplete

SELECTING THESIS TITLE 10-Jan-20 20

THEORY CONCEPTS 20-Jan-20 10

0

PROPOSAL SUBMISSION 2-Feb-20 13

0

PREVIOUS WORK ANALYSIS 9-Feb-20 07

INSTRUCTIONAL DESIGN 12-Feb-20 20

0

LITERATURE REVIEW 19-Feb 25

0

RESEARCH METHODOLOGY 23-Feb

RESEARCH WORK PLAN PREPARE 27-Feb

PREPARE MATLAB CODE 2-Mar 03

DATA COLLECTION 6-Mar

DATA ANALYSIS 10-Mar

THESIS ALL PRACTRICAL CALCULATION 14-Mar 15

0

COMPARISON SIMULATION AND PRACTICAL… 18-Mar 15

0

PROGRESS REPORT SUBMISSION 22-Mar

FINAL IMPLEMENTATION 26-Mar 20

0

REVIEW 30-Mar 10
0

TESTING 3-Apr 10
0

BOOK WRITING 7-Apr 10

0

THESIS BOOK SUBMISSION TO EXTERNAL 11-Apr 18

0

RECEIVE FEEDBACK FROM SUPERVISOR 15-Apr 17

0

POSTER AND SUMMARY 19-Apr 07

DEFENCE PRESENTATION READY 23-Apr 04

FINAL DEFENCE 27-Apr 10

0

Automated Vehicle License Plate Detection System Using Image Processing Algorithms 5 of 5