SlideShare a Scribd company logo
H1010345X 1

Abstract — The unavailability of adequate technologies to
constantly monitor the roads has led to many road traffic
violations going unpunished such as traffic light violations and
disregard of speed limits. Security in private premises is also
continuously seeking improvement. This has prompted many
authorities in many countries to introduce surveillance through
use of Video Image Processors. One very useful form of video
surveillance is identification by means of license plate recognition
also known as Automatic Number Plate Recognition (ANPR) and
it can be implemented in highway tolling, vehicle tracking and
access control. This document presents a Matlab based ANPR
system using the technique of template matching for optical
character recognition of the characters that appear on vehicle
number plates. Matlab was used to carry out morphological
image processing of captured images through a USB interfaced
camera on a PC. A PIC microcontroller was also implemented
and communication was established between Matlab and the
microcontroller through serial port communication to enable
access to successfully recognised number plates and manually as
well through a GUI. The project was able to successfully capture
images and process them to isolate and extract characters
through the template matching technique and communication
was established between the PIC microcontroller circuit and
Matlab.
Index Terms — ANPR, Matlab, OCR, Template Matching.
I. INTRODUCTION
icense Plate Recognition System (LPRS) or more
commonly referred to as Automatic Number Plate
Recognition (ANPR) is a very useful tool in the field of
machine vision and automation. Generally, license plate
recognition consists of two separate parts. First, plates have to
be located within the image, (license plate detection), followed
by license plate character recognition, (determining the plate
number). Different techniques or algorithms are used for
various systems of this nature. Some systems use a
combination of edge detection and vertical pixel projection;
others may make use of Mean-Shift algorithm or the Hough
Transform algorithm to identify the number plate and for the
optical character recognition. Most similar technologies that
use these mentioned techniques typically make use of DSPs,
ASIC and FPGA.
II. RELATED WORK
A lot of research work has been done in the field of ANPR,
but most of them make use of neural networks for the
identification purpose and cater to specific dimensions, font,
lighting and other conditions (Sudip Roy Kharagpur, 2007).
Cemil Oz and Fikret Ercal from Sakarya University, Computer
Engineering Department, Turkey; presented an Artificial
Neural Network based computer vision system which analysed
the image of a car taken by camera, locate the license plate
and recognise the number. An ANN tries to do the recognition
of characters which make up the plate. Other techniques
similar to the ones used in this project have also been
undertaken. Er. Kavneet Kaur and Vijay Kumar Banga, E.C.E
Department, A.C.E.T, Amritsar, Punjab, India; presented an
ANPR system based on template matching and tested it on
different ambient illumination conditions.
III. ANPR AND TEMPLATE MATCHING
The acronym ANPR stands for automatic number plate
recognition. CCTV cameras equipped with ANPR software
are mostly employed for this. They take pictures of vehicles as
Automatic Number Plate Recognition
(XtraSurv)
Mungofa Tanaka Ronald
Electronic Engineering Department
Harare Institute of Technology
Harare, Zimbabwe
tanakamungofa@gmail.com
L
H1010345X 2
they travel on roads and motorways or as they request access
into restricted areas. Either artificial neural networks are
employed or various other image processing algorithms to
extract the characters off number plates for the desired use,
whether it is cross reference to a database or just keeping
record of vehicles passing a particular point. There are seven
primary algorithms that the software requires for identifying a
license plate (Steps 2, 3 and 4 shown in Figure 2.2.1):
1. Plate localization – responsible for finding and
isolating the plate on the picture.
2. Plate orientation and sizing – compensates for the
skew of the plate and adjusts the dimensions to the
required size.
3. Normalization – adjusts the brightness and contrast of
the image.
4. Character segmentation – finds the individual
characters on the plates.
5. Optical character recognition.
6. Syntactical/Geometrical analysis – check characters
and positions against country-specific rules.
7. The averaging of the recognised value over multiple
fields/images to produce a more reliable or confident
result. Especially since any single image may contain a
reflected light flare, be partially obscured or other
temporary effect.
The complexity of each of these subsections of the program
determines the accuracy of the system. During the third phase
(normalization), some systems use edge detection techniques
to increase the picture difference between the letters and the
plate backing. A median filter may also be used to reduce the
visual noise on the image.
The main technique used for this project was Optical
Character Recognition (OCR). Optical Character Recognition
is the conversion of printed image, handwritten or typewritten
document into machine - editable form (International Journal
of Emerging Trends in Electrical and Electronics, May-2013.).
It has wide application in capturing documents through
various representations like scanned images or ancient scripts
in various languages into high level semantic descriptions of
the documents. It therefore involves image processing and
character recognition. The Optical Character Recognition
system can be subdivided into five major categories some of
which include System Architecture, Optical Mark Reader or
Intelligent Character Recognition (ICR) which is used to
describe the process of interpreting image data, in particular
alphanumeric text which is commonly used in license plate
recognition.
IV. MORPHOLOGICAL IMAGE PROCESSING
License plate recognition has had some previous
work done which involves morphological image processing
which is implemented in this project. Morphological image
processing is a collection of non-linear operations related to
the shape or morphology of features in an image (Nick Efford,
2000). It is used mostly for identifying particular defined
features in images hence is suitable for applications like facial
recognition and number plate recognition. Morphological
operations rely only on the relative ordering of pixel values
and not on their numerical values, therefore are especially
suited to the processing of binary images. Morphological
operations can also be applied to greyscale images such that
their light transfer functions are unknown and therefore their
absolute pixel values are of no or minor interest.
Morphological techniques probe an image with a small shape
or template called a structuring element or structural element
(Figure 1). The structuring element is positioned at all possible
locations in the image and it is compared with the
corresponding neighbourhood of pixels. Some operations test
whether the element "fits" within the neighbourhood, while
others test whether it "hits" or intersects the neighbourhood.
The structuring element is a small binary image, i.e. a small
matrix of pixels, each with a value of zero or one. The matrix
dimensions specify the size of the structuring element while
the pattern of ones and zeros specifies the shape of the
structuring element. An origin of the structuring element is
usually one of its pixels, although generally the origin can be
outside the structuring element.
H1010345X 3
Figure 1. Probing of an image with structuring
element
V. SYSTEM OVERVIEW
This project was aimed at developing a system which is
able to capture images of vehicle number plates, identify the
number plate and extract, through optical character
recognition, the characters on the plate to display them in
digital form. The system that was developed uses the method
of template matching to identify characters off number plate
images via reference to a database of character templates.
The main constituents are an image capture device in the
form of a generic 8MP CMOS webcam which is triggered to
capture images by a Matlab program. Images are then sent to a
computer (Matlab) for image processing using algorithms
defined in Matlab. Consequent to the image processing, OCR
is carried out through the aforementioned template matching
and resulting characters are printed on a text file and
displayed. The Matlab side is also controlled by a customised
graphical user interface (GUI). Peripherals to the Matlab
ANPR system other than the image capture device include a
PIC microcontroller which receives a serially transmitted
signal through its UART port. The PIC microcontroller then
actuates the opening and closing of a motorised barrier
through an H-bridge motor driver.
Figure 2. System Block Diagram
The camera captures a full colour (Y’CbCr or R’G’B’)
image and streams it to the computer for processing with
Matlab. The Matlab code (algorithm) begins with image
conversion (pre-processing) which involves processes such as
those indicated in the block diagram; resizing the image,
converting from RGB to greyscale, eroding, dilating to
remove noise etc. Morphological processing then follows to
identify the plate region and segmentation allows isolation of
the individual characters. The template matching algorithm is
then applied resulting in the OCR. After all image processing
steps are carried out successfully, the realised alphanumeric
characters are the written to a text file which is opened to
display the characters. The serial port of the PIC
microcontroller then receives a signal from the computer to
actuate the opening of a motorised barrier in the event of
successful character extraction. The system is battery powered
with the computer using its rechargeable battery and the
peripheral control circuit also powered by a 12V rechargeable
battery. Regulators enable appropriate voltage levels to reach
every component in the system.
The project was aimed at developing an automatic number
plate recognition system. The system that was produced is
PC
H1010345X 4
controlled by a GUI from a PC for demonstrative purposes of
each crucial stage in the number plate extraction. An image of
an incoming vehicle is captured by the image capture device
(camera), the image tries to focus mostly on the number plate
of the vehicle. This image is then transmitted to the PC for
processing in Matlab. Morphological image processing and
OCR are carried out to output the characters that are on the
vehicles number plate. This is followed by a signal being
serially transmitted to the PIC microcontroller (control
circuitry) which allows entry by opening a motorised barrier.
This is only done after successful plate extraction.
Figure 3. System Flow Chart
VI. PERIPHERAL CONTROL CIRCUIT
The system was developed to incorporate an automated
barrier opening and closing circuit and this was achieved by
linking Matlab GUI to a PIC16f877 microcontroller. The
choice of microcontroller was due to its ability to connect to
the RS232 protocol through its UART port. Any
microcontroller with UART functionality could have been
implemented in the same way. This microcontroller circuitry
design will now be looked at in this section.
Communication was established between Matlab and the
UART of the PIC via the computer’s RS232 port. However,
since later Windows versions after XP do not come with an
available RS232 port, a USB-to-Serial chip had to be installed
to enable serial transmission. Serial data was passed through
to the PIC via a MAX232 for CMOS to TTL conversion. The
PIC microcontroller was loaded with a program developed in
MikroC which enabled output pins on the PIC to send high or
low signal levels to an H-bridge motor driver (L293D).
According to delays defined within the PIC, the signals sent to
the H-bridge motor driver would turn the motor of the barrier
clockwise to open it and then anti-clockwise to close it. The
PIC’s UART was then configured to wait for the next string
from Matlab to repeat this action.
VII. RESULTS
A. Optical Character Recognition
The system gave output of characters both from the test
images that were saved as well as those captured for
processing. A variety of images taken from different lighting
settings, varied distance of capture and randomized numbers
were used for testing. The type of camera implemented
appeared to be largely affected by light conditions hence
images captured under intense light were not processed well.
This is probably because CMOS image sensors are very
susceptible to noise. Dim to average lighting gave the most
accurate results. Distant images would often include several
other objects within the frame hence the inaccuracies.
Elevated angle of capture would skew the characters on the
number plate and therefore the shape of characters would be a
mismatch compared with templates.
B. Overall System Performance
The entire system, when run under optimal conditions which
were in favour of the hardware that was implemented,
produced accurate character recognition of captured images of
vehicle number plates. Failed extraction showed the defined
NO
YES
H1010345X 5
error message on a note pad and successful extraction
displayed the characters of the vehicle number plate on a
notepad together with the date of capture. An image without
any recognisable features (particularly a number plate or any
characters) returned a Matlab image processing error as there
were no characters to segment and match with templates.
Figure 4. Successful character recognition
C. Peripheral Circuit Performance
The PIC controlled circuit which was implemented to
control a motorised barrier behaved as desired. The
microcontroller program that was developed initiated
accurate motor triggers and delays through the H-bridge
driver with the barrier opening and closing as anticipated.
During testing using LEDs, Serial communication also
showed to have been executing appropriately with
successful interfacing of Matlab with the Microcontroller.
The H-bridge controlled motor ran clockwise for specified
duration of 2seconds and waited through a specified delay
of 4seconds and the rotated counter-clockwise for 2seconds
hence driving the barrier (gate) open and closed soon after
successful number plate extraction.
VIII. CONCLUSION
The ANPR system was successfully designed and
developed and both the hardware and software of the system
function with the purpose of meeting the objectives. Image
capture was successfully triggered by Matlab through calling
of the external camera. The images were also successfully
retrieved from storage for processing by the Matlab program.
Character extraction was also successfully done using the
template matching method of optical character recognition
with a 90% success rate under optimal conditions. The
interface of Matlab to a PIC microcontroller yielded a
successful communication link between the two and automatic
operation of a motorised barrier was realised.
IX. FUTURE RECOMMENDATIONS
This system was designed to be implemented on a PC and
due to other programs running concurrently on the computer,
processing speeds seemed to be relatively slow. A
recommended approach for such a system would be
implementation on a dedicated processor such as Field
Programmable Gate Array (FPGA) or Application Specific
Integrated Circuit (ASIC) for greater processing speeds. This
would entail designing the program to suit conversion to either
VERILOG or VHDL which are compatible with FPGAs and
ASICs.
REFERENCES
Nick Efford (2000). Digital Image Processing: A Practical
Introduction Using JavaTM. Pearson Education, Chapter 11
"Morphological image processing"
Oivind Due Trier, Anil K. Jain, and Orfinn Taxt (1996).
“Feature Extraction Methods for character Recognition – A
Survey”, Pattern Recognition, Vol. 29 No. 4, pp.641-662.
Sudip Roy (2007). Vehicle License Plate Extraction and
Recognition, Dept. of Computer Science and Engineering,
Indian Institue of Technology, Kharagpur.
Baby Sathya S and Rajesh Kumar T, (May-2013).
International Journal of Emerging Trends in Electrical and
Electronics (IJETEE – ISSN: 2320-9569) Vol. 3, Issue 3.
N. Bellas, S. M. Chai, M. Dwyer, and D. Linzmeier (2006).
FPGA implementation of a license plate recognition soc using
automatically generated streaming accelerators. In 20th
International Parallel and Distributed Processing Symposium
IPDPS), page 8.
V. Kamat and S. Ganesan, (1995). An efficient implementation
of the hough transform for detecting vehicle license plates
using DSP’s. In Proceedings of the Real-Time Technology
H1010345X 6
and Applications Symposium (RTAS), page 58. IEEE
Computer Society.
G. Shrikanth, Kaushik Subramanian (April 2008). Sri
Venkateswara College of Engineering, Sriperumbudur Anna
University: Chennai.
Jun-Wei Hseih, Shih-Hao Yu, and Yung-Sheng Chen (2002).
“Morphology-based license Plate Detection from Complex
Scenes”, IEEE.
Choudhary A. Rahman, Wael Badawy (2003). “A Real Time
Vehicle’s License Plate Recognition System”, Proceedings of
the IEEE Conference on Advanced Video and Signal Based
Surveillance (AVSS’03).
Shyang-Lih Chang, Li-Shien Chen, Yun-Chung Chung, and
Sei-Wan Chen (March 2004). “Automatic License Plate
Recognition”, IEEE Transactions on Intelligent Systems, Vol.
5, No. 1.
Clemens Arth, Florian Limberger, Horst Bischof Graz. Real-
Time License Plate Recognition on an Embedded DSP-
Platform, University of Technology Institute for Computer
Graphics and Vision Inffeldgasse 16/2, 8010 Graz, Austria.
Roberto Brunelli (September 2008). Template Matching
Techniques in Computer Vision. FBK - Fondazione Bruno
Kessler.

More Related Content

What's hot

Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
CSCJournals
 
Robot Machine Vision
Robot Machine VisionRobot Machine Vision
Robot Machine Vision
anand hd
 
Number Plate Recognition of Still Images in Vehicular Parking System
Number Plate Recognition of Still Images in Vehicular Parking SystemNumber Plate Recognition of Still Images in Vehicular Parking System
Number Plate Recognition of Still Images in Vehicular Parking System
IRJET Journal
 
A design of license plate recognition system using convolutional neural network
A design of license plate recognition system using convolutional neural networkA design of license plate recognition system using convolutional neural network
A design of license plate recognition system using convolutional neural network
IJECEIAES
 
A Survey on License Plate Recognition System
A Survey on License Plate Recognition SystemA Survey on License Plate Recognition System
A Survey on License Plate Recognition System
IJARIIE JOURNAL
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
IAEME Publication
 
Tracking number plate from vehicle using
Tracking number plate from vehicle usingTracking number plate from vehicle using
Tracking number plate from vehicle using
ijfcstjournal
 
Character recognition from number plate written in assamese language
Character recognition from number plate written in assamese languageCharacter recognition from number plate written in assamese language
Character recognition from number plate written in assamese language
Subhash Basistha
 
Final Thesis Presentation Licenseplaterecognitionincomplexscenes
Final Thesis Presentation LicenseplaterecognitionincomplexscenesFinal Thesis Presentation Licenseplaterecognitionincomplexscenes
Final Thesis Presentation Licenseplaterecognitionincomplexscenesdswazalwar
 
An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...
An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...
An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...
IJMTST Journal
 
A Novel Multiple License Plate Extraction Technique for Complex Background in...
A Novel Multiple License Plate Extraction Technique for Complex Background in...A Novel Multiple License Plate Extraction Technique for Complex Background in...
A Novel Multiple License Plate Extraction Technique for Complex Background in...
CSCJournals
 
Anpr based licence plate detection report
Anpr  based licence plate detection reportAnpr  based licence plate detection report
Anpr based licence plate detection reportsomchaturvedi
 
An Intelligent Control System Using an Efficient License Plate Location and R...
An Intelligent Control System Using an Efficient License Plate Location and R...An Intelligent Control System Using an Efficient License Plate Location and R...
An Intelligent Control System Using an Efficient License Plate Location and R...
CSCJournals
 
IRJET- iSecurity: The AI Surveillance, a Smart Tracking System
IRJET-  	  iSecurity: The AI Surveillance, a Smart Tracking SystemIRJET-  	  iSecurity: The AI Surveillance, a Smart Tracking System
IRJET- iSecurity: The AI Surveillance, a Smart Tracking System
IRJET Journal
 
Intelligent Parking Space Detection System Based on Image Segmentation
Intelligent Parking Space Detection System Based on Image SegmentationIntelligent Parking Space Detection System Based on Image Segmentation
Intelligent Parking Space Detection System Based on Image Segmentation
ijsrd.com
 
[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...
[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...
[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...
IJET - International Journal of Engineering and Techniques
 
Facial Expression Recognition Using SVM Classifier
Facial Expression Recognition Using SVM ClassifierFacial Expression Recognition Using SVM Classifier
Facial Expression Recognition Using SVM Classifier
ijeei-iaes
 
Neural Network based Vehicle Classification for Intelligent Traffic Control
Neural Network based Vehicle Classification for Intelligent Traffic ControlNeural Network based Vehicle Classification for Intelligent Traffic Control
Neural Network based Vehicle Classification for Intelligent Traffic Control
ijseajournal
 
IRJET- Traffic Sign Detection, Recognition and Notification System using ...
IRJET-  	  Traffic Sign Detection, Recognition and Notification System using ...IRJET-  	  Traffic Sign Detection, Recognition and Notification System using ...
IRJET- Traffic Sign Detection, Recognition and Notification System using ...
IRJET Journal
 
License plate recognition for toll payment application
License plate recognition for toll payment applicationLicense plate recognition for toll payment application
License plate recognition for toll payment application
eSAT Journals
 

What's hot (20)

Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
 
Robot Machine Vision
Robot Machine VisionRobot Machine Vision
Robot Machine Vision
 
Number Plate Recognition of Still Images in Vehicular Parking System
Number Plate Recognition of Still Images in Vehicular Parking SystemNumber Plate Recognition of Still Images in Vehicular Parking System
Number Plate Recognition of Still Images in Vehicular Parking System
 
A design of license plate recognition system using convolutional neural network
A design of license plate recognition system using convolutional neural networkA design of license plate recognition system using convolutional neural network
A design of license plate recognition system using convolutional neural network
 
A Survey on License Plate Recognition System
A Survey on License Plate Recognition SystemA Survey on License Plate Recognition System
A Survey on License Plate Recognition System
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
 
Tracking number plate from vehicle using
Tracking number plate from vehicle usingTracking number plate from vehicle using
Tracking number plate from vehicle using
 
Character recognition from number plate written in assamese language
Character recognition from number plate written in assamese languageCharacter recognition from number plate written in assamese language
Character recognition from number plate written in assamese language
 
Final Thesis Presentation Licenseplaterecognitionincomplexscenes
Final Thesis Presentation LicenseplaterecognitionincomplexscenesFinal Thesis Presentation Licenseplaterecognitionincomplexscenes
Final Thesis Presentation Licenseplaterecognitionincomplexscenes
 
An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...
An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...
An Efficient Model to Identify A Vehicle by Recognizing the Alphanumeric Char...
 
A Novel Multiple License Plate Extraction Technique for Complex Background in...
A Novel Multiple License Plate Extraction Technique for Complex Background in...A Novel Multiple License Plate Extraction Technique for Complex Background in...
A Novel Multiple License Plate Extraction Technique for Complex Background in...
 
Anpr based licence plate detection report
Anpr  based licence plate detection reportAnpr  based licence plate detection report
Anpr based licence plate detection report
 
An Intelligent Control System Using an Efficient License Plate Location and R...
An Intelligent Control System Using an Efficient License Plate Location and R...An Intelligent Control System Using an Efficient License Plate Location and R...
An Intelligent Control System Using an Efficient License Plate Location and R...
 
IRJET- iSecurity: The AI Surveillance, a Smart Tracking System
IRJET-  	  iSecurity: The AI Surveillance, a Smart Tracking SystemIRJET-  	  iSecurity: The AI Surveillance, a Smart Tracking System
IRJET- iSecurity: The AI Surveillance, a Smart Tracking System
 
Intelligent Parking Space Detection System Based on Image Segmentation
Intelligent Parking Space Detection System Based on Image SegmentationIntelligent Parking Space Detection System Based on Image Segmentation
Intelligent Parking Space Detection System Based on Image Segmentation
 
[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...
[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...
[IJET-V1I6P15] Authors : Sadhana Raut, Poonam Rohani,Sumera Shaikh, Tehesin S...
 
Facial Expression Recognition Using SVM Classifier
Facial Expression Recognition Using SVM ClassifierFacial Expression Recognition Using SVM Classifier
Facial Expression Recognition Using SVM Classifier
 
Neural Network based Vehicle Classification for Intelligent Traffic Control
Neural Network based Vehicle Classification for Intelligent Traffic ControlNeural Network based Vehicle Classification for Intelligent Traffic Control
Neural Network based Vehicle Classification for Intelligent Traffic Control
 
IRJET- Traffic Sign Detection, Recognition and Notification System using ...
IRJET-  	  Traffic Sign Detection, Recognition and Notification System using ...IRJET-  	  Traffic Sign Detection, Recognition and Notification System using ...
IRJET- Traffic Sign Detection, Recognition and Notification System using ...
 
License plate recognition for toll payment application
License plate recognition for toll payment applicationLicense plate recognition for toll payment application
License plate recognition for toll payment application
 

Viewers also liked

Automatic Vehicle Entry Exit Log - Senior Year Project
Automatic Vehicle Entry Exit Log - Senior Year ProjectAutomatic Vehicle Entry Exit Log - Senior Year Project
Automatic Vehicle Entry Exit Log - Senior Year Project
Ahmad Azhar
 
Iaetsd fpga implementation of various security based tollgate system using anpr
Iaetsd fpga implementation of various security based tollgate system using anprIaetsd fpga implementation of various security based tollgate system using anpr
Iaetsd fpga implementation of various security based tollgate system using anpr
Iaetsd Iaetsd
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image ProcessingSamir Sabry
 
A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...
A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...
A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...
Shinya Takamaeda-Y
 
A Smart Approach to Number Plate Recognition in Tollgate System using FPGA
A Smart Approach to Number Plate Recognition in Tollgate System using FPGAA Smart Approach to Number Plate Recognition in Tollgate System using FPGA
A Smart Approach to Number Plate Recognition in Tollgate System using FPGA
ijsrd.com
 
AUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDA
AUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDAAUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDA
AUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDAMuhammed Sahal c
 
Automatic vehicle license plate detection using VEDA
Automatic vehicle license plate detection using VEDAAutomatic vehicle license plate detection using VEDA
Automatic vehicle license plate detection using VEDA
Rojith Thomas
 
Matlab based vehicle number plate identification system using ocr
Matlab based vehicle number plate identification system using ocrMatlab based vehicle number plate identification system using ocr
Matlab based vehicle number plate identification system using ocr
Ghanshyam Dusane
 
Automatic license plate recognition system for indian vehicle identification ...
Automatic license plate recognition system for indian vehicle identification ...Automatic license plate recognition system for indian vehicle identification ...
Automatic license plate recognition system for indian vehicle identification ...
Kuntal Bhowmick
 
A four way autometic traffic control system with variable delay using hdl
A four way autometic traffic control system with variable delay using hdlA four way autometic traffic control system with variable delay using hdl
A four way autometic traffic control system with variable delay using hdl
eSAT Journals
 
AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...
AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...
AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...
Kuntal Bhowmick
 
License Plate Recognition System
License Plate Recognition System License Plate Recognition System
License Plate Recognition System
Hira Rizvi
 
Automatic no. plate recognition
Automatic no. plate recognitionAutomatic no. plate recognition
Automatic no. plate recognitionAnjali Mehra
 
Fabrication of Automatic Guided Vehicle
Fabrication of Automatic Guided Vehicle Fabrication of Automatic Guided Vehicle
Fabrication of Automatic Guided Vehicle
Ajith Aravind
 
FPGA
FPGAFPGA
Automatic vehicle accident detection and messaging system using gsm and gps m...
Automatic vehicle accident detection and messaging system using gsm and gps m...Automatic vehicle accident detection and messaging system using gsm and gps m...
Automatic vehicle accident detection and messaging system using gsm and gps m...mahesh_rman
 
Basics of c++ Programming Language
Basics of c++ Programming LanguageBasics of c++ Programming Language
Basics of c++ Programming Language
Ahmad Idrees
 

Viewers also liked (18)

Automatic Vehicle Entry Exit Log - Senior Year Project
Automatic Vehicle Entry Exit Log - Senior Year ProjectAutomatic Vehicle Entry Exit Log - Senior Year Project
Automatic Vehicle Entry Exit Log - Senior Year Project
 
Iaetsd fpga implementation of various security based tollgate system using anpr
Iaetsd fpga implementation of various security based tollgate system using anprIaetsd fpga implementation of various security based tollgate system using anpr
Iaetsd fpga implementation of various security based tollgate system using anpr
 
Lpr2003
Lpr2003Lpr2003
Lpr2003
 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
 
A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...
A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...
A Framework for Efficient Rapid Prototyping by Virtually Enlarging FPGA Resou...
 
A Smart Approach to Number Plate Recognition in Tollgate System using FPGA
A Smart Approach to Number Plate Recognition in Tollgate System using FPGAA Smart Approach to Number Plate Recognition in Tollgate System using FPGA
A Smart Approach to Number Plate Recognition in Tollgate System using FPGA
 
AUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDA
AUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDAAUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDA
AUTOMATIC CAR LICENSE PLATE RECOGNITION USING VEDA
 
Automatic vehicle license plate detection using VEDA
Automatic vehicle license plate detection using VEDAAutomatic vehicle license plate detection using VEDA
Automatic vehicle license plate detection using VEDA
 
Matlab based vehicle number plate identification system using ocr
Matlab based vehicle number plate identification system using ocrMatlab based vehicle number plate identification system using ocr
Matlab based vehicle number plate identification system using ocr
 
Automatic license plate recognition system for indian vehicle identification ...
Automatic license plate recognition system for indian vehicle identification ...Automatic license plate recognition system for indian vehicle identification ...
Automatic license plate recognition system for indian vehicle identification ...
 
A four way autometic traffic control system with variable delay using hdl
A four way autometic traffic control system with variable delay using hdlA four way autometic traffic control system with variable delay using hdl
A four way autometic traffic control system with variable delay using hdl
 
AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...
AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...
AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION ...
 
License Plate Recognition System
License Plate Recognition System License Plate Recognition System
License Plate Recognition System
 
Automatic no. plate recognition
Automatic no. plate recognitionAutomatic no. plate recognition
Automatic no. plate recognition
 
Fabrication of Automatic Guided Vehicle
Fabrication of Automatic Guided Vehicle Fabrication of Automatic Guided Vehicle
Fabrication of Automatic Guided Vehicle
 
FPGA
FPGAFPGA
FPGA
 
Automatic vehicle accident detection and messaging system using gsm and gps m...
Automatic vehicle accident detection and messaging system using gsm and gps m...Automatic vehicle accident detection and messaging system using gsm and gps m...
Automatic vehicle accident detection and messaging system using gsm and gps m...
 
Basics of c++ Programming Language
Basics of c++ Programming LanguageBasics of c++ Programming Language
Basics of c++ Programming Language
 

Similar to journal nakk

Automatic License Plate Recognition Using Optical Character Recognition Based...
Automatic License Plate Recognition Using Optical Character Recognition Based...Automatic License Plate Recognition Using Optical Character Recognition Based...
Automatic License Plate Recognition Using Optical Character Recognition Based...
IJARIIE JOURNAL
 
IRJET- Automatic Number Plate Recognition System in Real Time
IRJET- Automatic Number Plate Recognition System in Real TimeIRJET- Automatic Number Plate Recognition System in Real Time
IRJET- Automatic Number Plate Recognition System in Real Time
IRJET Journal
 
IRJET- Vehicle Number Plate Recognition System
IRJET- Vehicle Number Plate Recognition SystemIRJET- Vehicle Number Plate Recognition System
IRJET- Vehicle Number Plate Recognition System
IRJET Journal
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
IAEME Publication
 
LICENSE PLATE RECOGNITION
LICENSE PLATE RECOGNITIONLICENSE PLATE RECOGNITION
LICENSE PLATE RECOGNITION
IRJET Journal
 
IRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLAB
IRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLABIRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLAB
IRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLAB
IRJET Journal
 
IRJET - Automatic License Plate Detection using Image Processing
IRJET - Automatic License Plate Detection using Image ProcessingIRJET - Automatic License Plate Detection using Image Processing
IRJET - Automatic License Plate Detection using Image Processing
IRJET Journal
 
IRJET- Recognition of Indian License Plate Number from Live Stream Videos
IRJET-  	  Recognition of Indian License Plate Number from Live Stream VideosIRJET-  	  Recognition of Indian License Plate Number from Live Stream Videos
IRJET- Recognition of Indian License Plate Number from Live Stream Videos
IRJET Journal
 
IRJET - License Plate Recognition
IRJET - License Plate RecognitionIRJET - License Plate Recognition
IRJET - License Plate Recognition
IRJET Journal
 
Paper id 25201447
Paper id 25201447Paper id 25201447
Paper id 25201447IJRAT
 
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
IRJET Journal
 
IRJET- Optical Character Recognition using Image Processing
IRJET-  	  Optical Character Recognition using Image ProcessingIRJET-  	  Optical Character Recognition using Image Processing
IRJET- Optical Character Recognition using Image Processing
IRJET Journal
 
Number plate recogition
Number plate recogitionNumber plate recogition
Number plate recogition
hetvi naik
 
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
Lori Moore
 
Automatic number plate recognition (anpr)
Automatic number plate recognition (anpr)Automatic number plate recognition (anpr)
Automatic number plate recognition (anpr)
AbhishekChoudhary464889
 
IRJET- Number Plate Extraction from Vehicle Front View Image using Image ...
IRJET-  	  Number Plate Extraction from Vehicle Front View Image using Image ...IRJET-  	  Number Plate Extraction from Vehicle Front View Image using Image ...
IRJET- Number Plate Extraction from Vehicle Front View Image using Image ...
IRJET Journal
 
IRJET- Cheque Bounce Detection System using Image Processing
IRJET- Cheque Bounce Detection System using Image ProcessingIRJET- Cheque Bounce Detection System using Image Processing
IRJET- Cheque Bounce Detection System using Image Processing
IRJET Journal
 
Automatic Number Plate Recognition System (ANPR) A Survey.pdf
Automatic Number Plate Recognition System (ANPR)  A Survey.pdfAutomatic Number Plate Recognition System (ANPR)  A Survey.pdf
Automatic Number Plate Recognition System (ANPR) A Survey.pdf
Tina Gabel
 
Number plate recognition using ocr technique
Number plate recognition using ocr techniqueNumber plate recognition using ocr technique
Number plate recognition using ocr technique
eSAT Publishing House
 

Similar to journal nakk (20)

Automatic License Plate Recognition Using Optical Character Recognition Based...
Automatic License Plate Recognition Using Optical Character Recognition Based...Automatic License Plate Recognition Using Optical Character Recognition Based...
Automatic License Plate Recognition Using Optical Character Recognition Based...
 
IRJET- Automatic Number Plate Recognition System in Real Time
IRJET- Automatic Number Plate Recognition System in Real TimeIRJET- Automatic Number Plate Recognition System in Real Time
IRJET- Automatic Number Plate Recognition System in Real Time
 
IRJET- Vehicle Number Plate Recognition System
IRJET- Vehicle Number Plate Recognition SystemIRJET- Vehicle Number Plate Recognition System
IRJET- Vehicle Number Plate Recognition System
 
Visual pattern recognition in robotics
Visual pattern recognition in roboticsVisual pattern recognition in robotics
Visual pattern recognition in robotics
 
LICENSE PLATE RECOGNITION
LICENSE PLATE RECOGNITIONLICENSE PLATE RECOGNITION
LICENSE PLATE RECOGNITION
 
IRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLAB
IRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLABIRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLAB
IRJET- Designing of OCR Tool Box for Decoding Vehicle Number Plate using MATLAB
 
IRJET - Automatic License Plate Detection using Image Processing
IRJET - Automatic License Plate Detection using Image ProcessingIRJET - Automatic License Plate Detection using Image Processing
IRJET - Automatic License Plate Detection using Image Processing
 
IRJET- Recognition of Indian License Plate Number from Live Stream Videos
IRJET-  	  Recognition of Indian License Plate Number from Live Stream VideosIRJET-  	  Recognition of Indian License Plate Number from Live Stream Videos
IRJET- Recognition of Indian License Plate Number from Live Stream Videos
 
IRJET - License Plate Recognition
IRJET - License Plate RecognitionIRJET - License Plate Recognition
IRJET - License Plate Recognition
 
20120130402031
2012013040203120120130402031
20120130402031
 
Paper id 25201447
Paper id 25201447Paper id 25201447
Paper id 25201447
 
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
Automatic Number Plate Recognition System Through Smart Phone Using Image Pro...
 
IRJET- Optical Character Recognition using Image Processing
IRJET-  	  Optical Character Recognition using Image ProcessingIRJET-  	  Optical Character Recognition using Image Processing
IRJET- Optical Character Recognition using Image Processing
 
Number plate recogition
Number plate recogitionNumber plate recogition
Number plate recogition
 
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
AUTOMATIC NUMBER PLATE RECOGNITION SYSTEM THROUGH SMART PHONE USING IMAGE PRO...
 
Automatic number plate recognition (anpr)
Automatic number plate recognition (anpr)Automatic number plate recognition (anpr)
Automatic number plate recognition (anpr)
 
IRJET- Number Plate Extraction from Vehicle Front View Image using Image ...
IRJET-  	  Number Plate Extraction from Vehicle Front View Image using Image ...IRJET-  	  Number Plate Extraction from Vehicle Front View Image using Image ...
IRJET- Number Plate Extraction from Vehicle Front View Image using Image ...
 
IRJET- Cheque Bounce Detection System using Image Processing
IRJET- Cheque Bounce Detection System using Image ProcessingIRJET- Cheque Bounce Detection System using Image Processing
IRJET- Cheque Bounce Detection System using Image Processing
 
Automatic Number Plate Recognition System (ANPR) A Survey.pdf
Automatic Number Plate Recognition System (ANPR)  A Survey.pdfAutomatic Number Plate Recognition System (ANPR)  A Survey.pdf
Automatic Number Plate Recognition System (ANPR) A Survey.pdf
 
Number plate recognition using ocr technique
Number plate recognition using ocr techniqueNumber plate recognition using ocr technique
Number plate recognition using ocr technique
 

journal nakk

  • 1. H1010345X 1  Abstract — The unavailability of adequate technologies to constantly monitor the roads has led to many road traffic violations going unpunished such as traffic light violations and disregard of speed limits. Security in private premises is also continuously seeking improvement. This has prompted many authorities in many countries to introduce surveillance through use of Video Image Processors. One very useful form of video surveillance is identification by means of license plate recognition also known as Automatic Number Plate Recognition (ANPR) and it can be implemented in highway tolling, vehicle tracking and access control. This document presents a Matlab based ANPR system using the technique of template matching for optical character recognition of the characters that appear on vehicle number plates. Matlab was used to carry out morphological image processing of captured images through a USB interfaced camera on a PC. A PIC microcontroller was also implemented and communication was established between Matlab and the microcontroller through serial port communication to enable access to successfully recognised number plates and manually as well through a GUI. The project was able to successfully capture images and process them to isolate and extract characters through the template matching technique and communication was established between the PIC microcontroller circuit and Matlab. Index Terms — ANPR, Matlab, OCR, Template Matching. I. INTRODUCTION icense Plate Recognition System (LPRS) or more commonly referred to as Automatic Number Plate Recognition (ANPR) is a very useful tool in the field of machine vision and automation. Generally, license plate recognition consists of two separate parts. First, plates have to be located within the image, (license plate detection), followed by license plate character recognition, (determining the plate number). Different techniques or algorithms are used for various systems of this nature. Some systems use a combination of edge detection and vertical pixel projection; others may make use of Mean-Shift algorithm or the Hough Transform algorithm to identify the number plate and for the optical character recognition. Most similar technologies that use these mentioned techniques typically make use of DSPs, ASIC and FPGA. II. RELATED WORK A lot of research work has been done in the field of ANPR, but most of them make use of neural networks for the identification purpose and cater to specific dimensions, font, lighting and other conditions (Sudip Roy Kharagpur, 2007). Cemil Oz and Fikret Ercal from Sakarya University, Computer Engineering Department, Turkey; presented an Artificial Neural Network based computer vision system which analysed the image of a car taken by camera, locate the license plate and recognise the number. An ANN tries to do the recognition of characters which make up the plate. Other techniques similar to the ones used in this project have also been undertaken. Er. Kavneet Kaur and Vijay Kumar Banga, E.C.E Department, A.C.E.T, Amritsar, Punjab, India; presented an ANPR system based on template matching and tested it on different ambient illumination conditions. III. ANPR AND TEMPLATE MATCHING The acronym ANPR stands for automatic number plate recognition. CCTV cameras equipped with ANPR software are mostly employed for this. They take pictures of vehicles as Automatic Number Plate Recognition (XtraSurv) Mungofa Tanaka Ronald Electronic Engineering Department Harare Institute of Technology Harare, Zimbabwe tanakamungofa@gmail.com L
  • 2. H1010345X 2 they travel on roads and motorways or as they request access into restricted areas. Either artificial neural networks are employed or various other image processing algorithms to extract the characters off number plates for the desired use, whether it is cross reference to a database or just keeping record of vehicles passing a particular point. There are seven primary algorithms that the software requires for identifying a license plate (Steps 2, 3 and 4 shown in Figure 2.2.1): 1. Plate localization – responsible for finding and isolating the plate on the picture. 2. Plate orientation and sizing – compensates for the skew of the plate and adjusts the dimensions to the required size. 3. Normalization – adjusts the brightness and contrast of the image. 4. Character segmentation – finds the individual characters on the plates. 5. Optical character recognition. 6. Syntactical/Geometrical analysis – check characters and positions against country-specific rules. 7. The averaging of the recognised value over multiple fields/images to produce a more reliable or confident result. Especially since any single image may contain a reflected light flare, be partially obscured or other temporary effect. The complexity of each of these subsections of the program determines the accuracy of the system. During the third phase (normalization), some systems use edge detection techniques to increase the picture difference between the letters and the plate backing. A median filter may also be used to reduce the visual noise on the image. The main technique used for this project was Optical Character Recognition (OCR). Optical Character Recognition is the conversion of printed image, handwritten or typewritten document into machine - editable form (International Journal of Emerging Trends in Electrical and Electronics, May-2013.). It has wide application in capturing documents through various representations like scanned images or ancient scripts in various languages into high level semantic descriptions of the documents. It therefore involves image processing and character recognition. The Optical Character Recognition system can be subdivided into five major categories some of which include System Architecture, Optical Mark Reader or Intelligent Character Recognition (ICR) which is used to describe the process of interpreting image data, in particular alphanumeric text which is commonly used in license plate recognition. IV. MORPHOLOGICAL IMAGE PROCESSING License plate recognition has had some previous work done which involves morphological image processing which is implemented in this project. Morphological image processing is a collection of non-linear operations related to the shape or morphology of features in an image (Nick Efford, 2000). It is used mostly for identifying particular defined features in images hence is suitable for applications like facial recognition and number plate recognition. Morphological operations rely only on the relative ordering of pixel values and not on their numerical values, therefore are especially suited to the processing of binary images. Morphological operations can also be applied to greyscale images such that their light transfer functions are unknown and therefore their absolute pixel values are of no or minor interest. Morphological techniques probe an image with a small shape or template called a structuring element or structural element (Figure 1). The structuring element is positioned at all possible locations in the image and it is compared with the corresponding neighbourhood of pixels. Some operations test whether the element "fits" within the neighbourhood, while others test whether it "hits" or intersects the neighbourhood. The structuring element is a small binary image, i.e. a small matrix of pixels, each with a value of zero or one. The matrix dimensions specify the size of the structuring element while the pattern of ones and zeros specifies the shape of the structuring element. An origin of the structuring element is usually one of its pixels, although generally the origin can be outside the structuring element.
  • 3. H1010345X 3 Figure 1. Probing of an image with structuring element V. SYSTEM OVERVIEW This project was aimed at developing a system which is able to capture images of vehicle number plates, identify the number plate and extract, through optical character recognition, the characters on the plate to display them in digital form. The system that was developed uses the method of template matching to identify characters off number plate images via reference to a database of character templates. The main constituents are an image capture device in the form of a generic 8MP CMOS webcam which is triggered to capture images by a Matlab program. Images are then sent to a computer (Matlab) for image processing using algorithms defined in Matlab. Consequent to the image processing, OCR is carried out through the aforementioned template matching and resulting characters are printed on a text file and displayed. The Matlab side is also controlled by a customised graphical user interface (GUI). Peripherals to the Matlab ANPR system other than the image capture device include a PIC microcontroller which receives a serially transmitted signal through its UART port. The PIC microcontroller then actuates the opening and closing of a motorised barrier through an H-bridge motor driver. Figure 2. System Block Diagram The camera captures a full colour (Y’CbCr or R’G’B’) image and streams it to the computer for processing with Matlab. The Matlab code (algorithm) begins with image conversion (pre-processing) which involves processes such as those indicated in the block diagram; resizing the image, converting from RGB to greyscale, eroding, dilating to remove noise etc. Morphological processing then follows to identify the plate region and segmentation allows isolation of the individual characters. The template matching algorithm is then applied resulting in the OCR. After all image processing steps are carried out successfully, the realised alphanumeric characters are the written to a text file which is opened to display the characters. The serial port of the PIC microcontroller then receives a signal from the computer to actuate the opening of a motorised barrier in the event of successful character extraction. The system is battery powered with the computer using its rechargeable battery and the peripheral control circuit also powered by a 12V rechargeable battery. Regulators enable appropriate voltage levels to reach every component in the system. The project was aimed at developing an automatic number plate recognition system. The system that was produced is PC
  • 4. H1010345X 4 controlled by a GUI from a PC for demonstrative purposes of each crucial stage in the number plate extraction. An image of an incoming vehicle is captured by the image capture device (camera), the image tries to focus mostly on the number plate of the vehicle. This image is then transmitted to the PC for processing in Matlab. Morphological image processing and OCR are carried out to output the characters that are on the vehicles number plate. This is followed by a signal being serially transmitted to the PIC microcontroller (control circuitry) which allows entry by opening a motorised barrier. This is only done after successful plate extraction. Figure 3. System Flow Chart VI. PERIPHERAL CONTROL CIRCUIT The system was developed to incorporate an automated barrier opening and closing circuit and this was achieved by linking Matlab GUI to a PIC16f877 microcontroller. The choice of microcontroller was due to its ability to connect to the RS232 protocol through its UART port. Any microcontroller with UART functionality could have been implemented in the same way. This microcontroller circuitry design will now be looked at in this section. Communication was established between Matlab and the UART of the PIC via the computer’s RS232 port. However, since later Windows versions after XP do not come with an available RS232 port, a USB-to-Serial chip had to be installed to enable serial transmission. Serial data was passed through to the PIC via a MAX232 for CMOS to TTL conversion. The PIC microcontroller was loaded with a program developed in MikroC which enabled output pins on the PIC to send high or low signal levels to an H-bridge motor driver (L293D). According to delays defined within the PIC, the signals sent to the H-bridge motor driver would turn the motor of the barrier clockwise to open it and then anti-clockwise to close it. The PIC’s UART was then configured to wait for the next string from Matlab to repeat this action. VII. RESULTS A. Optical Character Recognition The system gave output of characters both from the test images that were saved as well as those captured for processing. A variety of images taken from different lighting settings, varied distance of capture and randomized numbers were used for testing. The type of camera implemented appeared to be largely affected by light conditions hence images captured under intense light were not processed well. This is probably because CMOS image sensors are very susceptible to noise. Dim to average lighting gave the most accurate results. Distant images would often include several other objects within the frame hence the inaccuracies. Elevated angle of capture would skew the characters on the number plate and therefore the shape of characters would be a mismatch compared with templates. B. Overall System Performance The entire system, when run under optimal conditions which were in favour of the hardware that was implemented, produced accurate character recognition of captured images of vehicle number plates. Failed extraction showed the defined NO YES
  • 5. H1010345X 5 error message on a note pad and successful extraction displayed the characters of the vehicle number plate on a notepad together with the date of capture. An image without any recognisable features (particularly a number plate or any characters) returned a Matlab image processing error as there were no characters to segment and match with templates. Figure 4. Successful character recognition C. Peripheral Circuit Performance The PIC controlled circuit which was implemented to control a motorised barrier behaved as desired. The microcontroller program that was developed initiated accurate motor triggers and delays through the H-bridge driver with the barrier opening and closing as anticipated. During testing using LEDs, Serial communication also showed to have been executing appropriately with successful interfacing of Matlab with the Microcontroller. The H-bridge controlled motor ran clockwise for specified duration of 2seconds and waited through a specified delay of 4seconds and the rotated counter-clockwise for 2seconds hence driving the barrier (gate) open and closed soon after successful number plate extraction. VIII. CONCLUSION The ANPR system was successfully designed and developed and both the hardware and software of the system function with the purpose of meeting the objectives. Image capture was successfully triggered by Matlab through calling of the external camera. The images were also successfully retrieved from storage for processing by the Matlab program. Character extraction was also successfully done using the template matching method of optical character recognition with a 90% success rate under optimal conditions. The interface of Matlab to a PIC microcontroller yielded a successful communication link between the two and automatic operation of a motorised barrier was realised. IX. FUTURE RECOMMENDATIONS This system was designed to be implemented on a PC and due to other programs running concurrently on the computer, processing speeds seemed to be relatively slow. A recommended approach for such a system would be implementation on a dedicated processor such as Field Programmable Gate Array (FPGA) or Application Specific Integrated Circuit (ASIC) for greater processing speeds. This would entail designing the program to suit conversion to either VERILOG or VHDL which are compatible with FPGAs and ASICs. REFERENCES Nick Efford (2000). Digital Image Processing: A Practical Introduction Using JavaTM. Pearson Education, Chapter 11 "Morphological image processing" Oivind Due Trier, Anil K. Jain, and Orfinn Taxt (1996). “Feature Extraction Methods for character Recognition – A Survey”, Pattern Recognition, Vol. 29 No. 4, pp.641-662. Sudip Roy (2007). Vehicle License Plate Extraction and Recognition, Dept. of Computer Science and Engineering, Indian Institue of Technology, Kharagpur. Baby Sathya S and Rajesh Kumar T, (May-2013). International Journal of Emerging Trends in Electrical and Electronics (IJETEE – ISSN: 2320-9569) Vol. 3, Issue 3. N. Bellas, S. M. Chai, M. Dwyer, and D. Linzmeier (2006). FPGA implementation of a license plate recognition soc using automatically generated streaming accelerators. In 20th International Parallel and Distributed Processing Symposium IPDPS), page 8. V. Kamat and S. Ganesan, (1995). An efficient implementation of the hough transform for detecting vehicle license plates using DSP’s. In Proceedings of the Real-Time Technology
  • 6. H1010345X 6 and Applications Symposium (RTAS), page 58. IEEE Computer Society. G. Shrikanth, Kaushik Subramanian (April 2008). Sri Venkateswara College of Engineering, Sriperumbudur Anna University: Chennai. Jun-Wei Hseih, Shih-Hao Yu, and Yung-Sheng Chen (2002). “Morphology-based license Plate Detection from Complex Scenes”, IEEE. Choudhary A. Rahman, Wael Badawy (2003). “A Real Time Vehicle’s License Plate Recognition System”, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS’03). Shyang-Lih Chang, Li-Shien Chen, Yun-Chung Chung, and Sei-Wan Chen (March 2004). “Automatic License Plate Recognition”, IEEE Transactions on Intelligent Systems, Vol. 5, No. 1. Clemens Arth, Florian Limberger, Horst Bischof Graz. Real- Time License Plate Recognition on an Embedded DSP- Platform, University of Technology Institute for Computer Graphics and Vision Inffeldgasse 16/2, 8010 Graz, Austria. Roberto Brunelli (September 2008). Template Matching Techniques in Computer Vision. FBK - Fondazione Bruno Kessler.