International Journal of Engineering Research & Technology (IJERT)

ISSN: 2278-0181
Vol. 4 Issue 02, February-2015

Vehicle Number Plate Recognition System for

Theft Detection

Kulkarni Suraj Deeliprao Prof. Pallavi S. Deshpande

Dept. of Electronics and Telecommunication Dept. of Electronics and Telecommunication
Smt.Kashibai Navale College of Engg.,Vadgaon(Bk) Smt.Kashibai Navale College of Engg.,Vadgaon(Bk)
Pune, India, Pune, India,

Abstract— Large number of vehicles around us in daily life vehicle registration plate is a plate which is made by either
creates disturbances such as heavy traffic, stealing of vehicles at metal or plastic and is usually will be attached to the front or
the places like toll plazas, parking areas, heavy traffic roads. back of a vehicle. Vehicle plate number contains of numbers
Management of vehicles transportation is tedious and time and alphabetical letter which can be used to represent an
consuming task if it is completely done manually and which
identity of respective vehicle as described in [2].
results in huge errors and faults. Therefore it is necessary to
develop automatic license plate recognition system to solve the
problems discussed above which will automatically recognize
number from front side image of vehicle. The detection number
plate goes through following steps: finding plate location in
image, segmenting and recognizing characters. Number of
license plate is displayed on graphical user interface and stored
in database with time and date for further use and alarm will
ring of stolen vehicle is detected. The system can be used for Fig. 1. Automatic Vehicle License Recognition System
purpose of security as well as automatic highway speed
detection, traffic violation cases, toll plazas, parking areas The first two letter of the vehicle serves as the state
location prefix and followed by two numerical digits which
Keywords—Automatic vehicle license recognition system, represents district from where vehicle belongs to. Number
Character segmentation, Character recognition, stolen vehicle,
plate format of Indian vehicle is LLNN LLNNNN where L is
Theft detection.
letter and N is the number. If vehicles are recognized
manually then will be more mistakes with less efficiency and
I. INTRODUCTION slow. If the described system will be implemented artificially
Vehicles are increasing in enormously as they are by using machines described in next chapter, it will be more
necessary to travel from one place to another place in little efficient and Less Costly.
time. We see number of vehicles around us in our daily life Paper is organized as follows. Section I is the introduction
and everyone needs it but with population increase, vehicles to the paper. Section II describes the literature survey of the
increased last decades in large quantity. But it created systems and methods implemented so far. Section III is the
disturbances to human life such as huge traffic, large sound, details of implementations where three different steps are of
crime cases such as stealing of vehicles, accidents, etc. and the system i.e. Number plate extraction, Character
therefore management of vehicle is very necessary. As a segmentation and Character recognition described in detail.
result, there is a lot of work going on to improve the Section IV describes the Experimental results obtained in
transportation of vehicles. Out of these, vehicle Plate MATLAB. Section V deals with conclusion and
acknowledgements of the project. Paper ends with references
Recognition System is the most attractive research issue and
this manuscripts discusses some practical aspect of
recognizing number written on vehicle number plate. A II. LITERATURE SURVEY
Vehicle Plate Recognition System is a tracking system that Huge work is done on Vehicle License plate Recognition
identifies the vehicle so that the car is tracked down through System in various industries; large numbers of papers are
the existing database. Normally the recognition system will published by various authors in IEEE journals, non IEEE
be installed at the gate of the residential area, factory journal and Dissertation reports. Some basic references which
entrances, parking space, toll gates, university entrance or are referred by authors are discussed in following section.
other high-secured building such as defense institute, nuclear 1. Christos Nikolaos E. Vassili Loumos ,Anagnostopoulos,
factories as given in [1]. Ioannis E. Anagnostopoulos, ,and Eleftherios Kayafas-
Above Fig.1 describes the more details of Vehicle Plate „A License Plate Recognition. Algorithm for Intelligent
Recognition system systematically. The presence of vehicle is Transportation System Applications‟ IEEE transaction
detected using IR sensor after camera will capture image of on Intelligent Transportation System, Vol. 8, No. 3, Sept
vehicle which will be used for further processing. Basically, 2006

IJERTV4IS020692 www.ijert.org 773

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 4 Issue 02, February-2015

In this paper, a new algorithm for vehicle There are various methods to detect License Number
license plate identification is proposed, using Plate from total image and segment the characters from
segmentation technique and connected component number plate. Some methods are described in Table 1 with
analysis in conjunction with a character recognition. The their comparative advantages and disadvantage [4]. Number
algorithm was verified with different gray-level vehicle plate localization is important step in developing VLPR
images of different backgrounds and ambient system. If system fails to detect the location of License plate
illumination. The camera towards the plate, while the then VLPR system will not able to recognize the number
angle and the distance from the vehicle varied according plate.
to the experimental setup.
2. Choudhury A. Rahman, Wael Badawy,Ahmad Methods Pros Cons
Radmanesh „A Real Time Vehicle‟s License Plate Using Simplest, fast and Hardly be applied to
Recognition System „Proceedings of the IEEE Conference boundary Straight forward. complex images
on Advanced Video and Signal Based Surveillance,0- features since they are too
7695-1971.June 2010. sensitive to
A smart and simple algorithm is presented in this Unwanted edges.
paper for vehicle‟s license plate recognition system. Using global Straightforward, May generate
Depend on pattern comparison; this algorithm can be image independent of the broken objects.
applied for real time detection of license plates for features license plate
collecting data for surveying or for some application position.
specific purposes. The system has been designed using Using Be able to detect Computationally
C++ and the experimental results have been shown for texture even if the boundary complex when there
recognition of Alberta license plates. features is deformed. are many edges.
3. Banshidhar Majhi‟Heuristics for license plate localization
and hardware implementation of Automatic License Plate Segmentation process is used to find the individual
Recognition (ALPR) system‟Department of Computer characters on the number plate considering character
Science and Engg, National Institute of Technology properties. It is segmented by finding the characters inside the
Rourkela, 2012. image and bounded each character with the rectangle to
The project “Heuristics for license plate localization separate them. Table 2 describes methods of characters
and hardware implementation of Automatic License Plate segmentation [5].
Recognition (ALPR) system” deals with detection and
recognition of license plate from a captured front view of
any car. The work obeys all the steps in an ALPR system III. DETAILS OF IMPLEMENTATION
like pre-processing, segmentation, and license plate
A. After Plate Extraction Detection
localization, extraction of characters and finally
recognition of each character to form a string to match
with the registered License plate numbers. The crucial and initial step in ALPR system is to extract
the characters of number plate from the vehicle image. The
Automatic Vehicle License Plate Recognition System procedure for detecting is done in several stages. The number
plate extraction is started with the horizontal and vertical
consists of following 3 main processing steps as shown in
edge detection techniques that are based on the characteristics
Fig.2 License Plate Extraction from whole image, Character
of the edge displayed by the edges of the character on the
Segmentation form number plate and Character Recognition vehicle‟s number plate. The procedure used to for number
comparing with database images [3]. plate extraction out of total image is discussed as follows.
Methods Pros Cons 1. Read Photo of vehicle as Input Image (I) and Crop the
Image with Proper Dimensions(IC).
Using pixel Simple and May not to extract all 2. Use Morphological Operation like Closing with Proper
connectivity straightforward, the characters when Structuring Element.
there are joined or 3. Obtain Difference between I-Ic and Find all candidates
broken characters for Number Plates by Labelling Connected Component
Using Independent of Noise may increase. in it. Measure Properties in above Image like Area,
projection character positions Major Axial Length Area>70
profiles 4. Select Candidates who‟s Major Axis Length is greater
than and Remove Objects that will be never Number
Using basic Simple Limited by Any change may Plate using Closing and Dilation Process.
knowledge of the prior result in errors. 5. Select Largest connected Component as Number Plate
characters knowledge and Crop it and display it.

IJERTV4IS020692 www.ijert.org 774

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 4 Issue 02, February-2015

B. Character Segmentation code and some of the GUI‟s are discussed in this section.
Fig.3 indicates user interface for Front Page and reading
Segmentation process is used to find the individual image already stored or by camera which shows systematic
characters on the number plate. In this work, characters are flow of working of system.
segmented using the thresholding technique. It is segmented
by obtaining the characters inside the image and bounded
each character with the rectangle to separate. Process used to
for character segmentation is as follows.

1. Take Extracted Image Plate as Input and Use

Thresholding to Binarize Image.
2. Measure Properties of Individual Patterns like Area,
Angle, Length of Major Axis, etc.
3. Considering Largest Area as Character and detect other
Characters according to it and Turn Characters
according to Angles. Fig. 3.Graphical user interface for (a) Front Page (b) reading image already
4. Use Morphological Operations to Regain Shape of stored or by camera.
Characters and Remove Noise from it.
Every recognized number plate is compared with database
5. Crop Individual Characters and Display them as Separate of stolen vehicle if math founds then that vehicle is declared
Images in Standard size for Further Recognition as stolen vehicle. The data base of such vehicle maintained
Process. for security purpose so that stolen vehicle will be detected
easily. After detecting stolen vehicle system will generate
C. Character Recognition alarm and it will close door so that vehicle will not pass from
that place. After message will be send to the traffic police for
It is employed for the purpose of conversion of images of detecting theft.
text into characters. The objective of Optical Character
Recognition is to classify optical pattern corresponding to
alphanumeric or other characters. The process of character
recognition involves several steps like feature extraction and
classification. Before recognition algorithm, the characters
are normalized.
Normalization is to refine the characters into a block Fig. 4.Displaying message for stolen vehicle.
containing no extra white spaces (pixels) in all the four sides
of characters. Then each character is fit to equal size. Fitting
IV. EXPERIMENTAL RESULTS
technique is necessary for template matching. For comparing
the characters with the database, input images must be same- We have taken number photos of cars from camera of 8
sized with the database characters Template matching is a Megapixel and done survey to know what be the exact
proper algorithm for recognition of characters. The character position of number plate in total image. Out of them few
image is matched with the ones in the database and the best images are as shown in Fig.5.We considered all types of
similarity is calculated. To measure the similarity and find the number plate like titled and corrupted.
best match, a correlation function is used.
1. Load database of letters, numbers as templates (0-9, A-Z)
and Take segmented characters image as input from
previous step.
2. Check segmented characters and template characters
similarity and Compare it with all the loaded templates
using correlation function
3. Output of above function will be correlation coefficients
and Find maximum value correlation coefficient for
corresponding template.
4. Give unique identity to all the templates for easy process Fig. 5.Various Photo Images taken for Survey
and corresponding template is detected as recognized
character It is concluded that average size of number plate in total
5. Repeat all above steps for other characters and display image is 17×6.We can also conclude that size of number plate
recognized character to GUI as number plate. varies between 14 to 27 ×4 to 9 percent of total image as
shown in fig 10.
D. Creating GUI”s for user friendly and Theft detection
For proper user friendly environments various graphical
user interfaces are created so that user can process step by
step. Various buttons are provided for interfacing with main

IJERTV4IS020692 www.ijert.org 775

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 4 Issue 02, February-2015

A. Number Plate Extraction

Fig. 10.Two different character are considered as one after segmentation

Fig. 6. Number Plate Extraction and Captured Number Plate

Fig.6 shows extraction of number plate from total

front side image of vehicle taken by webcamera, and it also
indicate captured number plate as seprate image. Fig.7 (a)
and Fig.7 (b) are some errors obtained during number plate
extraction process.Fig.7 (a) shows extracted number plate
contains additional area other than number plate. Sometime
results shows corrupted number plate as shown in fig.7 (b).
Fig. 11.Single character is segmented into two characters

Fig. 7(a). Extracted number plate contains additional area Fig.7 (b) .When
plate is corrupted

B. Character Segmentation

Fig. 12.1.Number plate and its recognized characters are shown in GUI

Fig. 8.Captured Number Plate and Segmented Characters from Number Plate

Segmentation of character can be easily understood

from Fig.no.8.In few cases characters are not considered for
segmentation as shown in Fig.9 because of their size
comparatively very less from other characters. Two different
characters are considered as one after segmentation because Fig. 12.2.Number Plate and Recognized Character
they are connected to each other as described in Fig.10.Some
cases shows Single character is segmented into two Character recognized in segmentation step goes
characters because character is having very high size which is through recognition process by comparing with templates
shown in Fig.11. characters.Fig.12.1 to Fig.12.3 shows recognizes number
from concerned image with details like date, amount. In some
cases characters are not properly recognized due to some
problems like improper size of segmented character and
templates, damaged characters and it is shown in Fig 13

Fig. 9.Some characters are not considered for segmentation

IJERTV4IS020692 www.ijert.org 776

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
Vol. 4 Issue 02, February-2015

Parameter Input Images Output Image Efficiency

Number plate 50 45 90%
Extraction
Character 45 40 90%
Segmentation
Character 40 30 75%
Recognition

ACKNOWLEDGMENT
Authors thanks to Prof.R.H.Jagdale, Prof.S.K.Jagtap,
Fig. 12.3.Recognized Number plate Prof. P. G. Chilveri,Prof.H.S.Thakkar, Mr. M. S. Navale
imparted valuable basic knowledge of Image processing and
embedded system MATLAB. We are indebted to PG HOD
Dr. S. K. Shah for her constant inspiration and assistance
throughout the course. Our heartfelt gratitude to our respected
Principal, Dr. A. V. Deshpande for his encouragement to our
project

REFERENCES

[1] As Shan Du,Mahmoud Ibrahim,Mohamed Shehata,Wael Badawy-

‟Automatic License Plate Recognition (ALPR) :A State-of-the-
Art‟ IEEE Transactions on Circuits and Systems For video
technology,Vol.23,No.2,pg no.311-325,Feb 2013.
[2] Kandula Venkata Reddy, D. Rajeswara Rao, K. Rajesh-‟ Hand
Fig. 13.Partially Recognized Number plate Written Character Detection by Using Fuzzy Logic Techniques
‟International Journal of Emerging Technology and Advanced
V. CONCLUSION Engineering Website: Volume 3, Issue 3, March 2013.pg 256-260
[3] Xiaojun Chi; Junyu Dong; Aihua Liu; Huiyu Zhou;” A Simple
The proposed system of Automatic Vehicle License Plate Method for Chinese License Plate Recognition Based on Support
Recognition can be implemented using above discussed Vector Machine” ,Conference on Communications and Systems
method which involves fundamental Image processing steps Proceedings International Volume 3, 25-28 June 2006
Page(s):2141 – 2145
using MATLAB. We can detect and recognize license
[4] Gecim, H. S.; Alkar, A. Z.”Efficient Embedded Neural-Network-
number from a captured front view image of any vehicle from Based License Plate Recognition System” Vehicular Technology,
camera. It contains main three processes: plate extraction, Vol.no.57, Issue 5, Sept. 2008 Page:2675 – 2683.
character detection and character recognition. Every process [5] Ying Zhang; Yingtao Xu; Gejian Ding” License plate character
has its own different efficiencies as per procedure used and recognition algorithm based on filled function method training bp
neural network”; Control and Decision Conference,
its complexity as shown in Table no.2. Further we can detect 2008.,Chinese 2-4 July 2008 Page(s):3886 – 389.
stolen by comparing it with database of stolen vehicles and [6] „Digital Image Processing‟-Rafael C.Gonzalez & Richard
ring an alarm which increases security of system. It can be E.Woods, Pearson Publications, 3‟rd ed..
used in many security purposes like speed detection, [7] „Digital Image Processing using MATLAB‟-Rafael
C.Gonzalez,Richard E.Woods,Steven L.Eddins,2‟nd edition, Mc
detection of traffic violation, toll collection, parking system Graw Hill Publications.
as well as can be installed at secure areas like at the gate of [8] www.mathwork.in
the residential area, factory gates, parking space, toll plazas, [9] Suraj Kulkarni,Pallavi Deshpande‟Vehicle License Plate
university entrance or other high-secured building such as Recognition using FPGA‟,ePGCON-
2014‟,Nashik,Maharashrta,pp 26-28.
defense institutes, nuclear factories.

IJERTV4IS020692 www.ijert.org 777

(This work is licensed under a Creative Commons Attribution 4.0 International License.)