1

PROJECT REPORT ON

“LICENSE PLATE RECOGNITION SOFTWARE”

BY

ABHINANDAN SINGH - 08070121202 MAYANK KISHORE PATHIKRIT GUHA - 08070121224 - 08070121232

Under the Guidance of

Asst. Prof. MRUDANG SHUKLA
In partial fulfilment of
B.Tech ( E& TC )

DEGREE OF SYMBIOSIS INTERNATIONAL UNIVERSITY, YEAR 2011 - 2012 DEPARTMENT OF ELECTRONICS & TELECOMMUNICATION ENGINEERING SYMBIOSIS INSTITUTE OF TECHNOLOGY PUNE – 412 115.
1

2

CERTIFICATE

This is to certify that the project entitled LICENSE PLATE RECOGNITION SOFTWARE submitted by _ Abhinandan Singh _ , Roll No. _ 08070121202 _, is record of

bonafide work carried out by her/him , under my guidance, in partial fulfillment of the requirement for the award of Degree of Bachelor of Engineering ( Electronics & Telecommunication ) of Symbiosis International University.

Date :

Place :

Prof. Mrudang Shukla
Guide , Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115.

Prof. Dr. Narayan Pisharoty
Head, Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115.

2

3

CERTIFICATE

This is to certify that the project entitled LICENSE PLATE RECOGNITION SOFTWARE submitted by _ Mayank Kishore _ , Roll No. _ 08070121224 _, is record of

bonafide work carried out by her/him , under my guidance, in partial fulfillment of the requirement for the award of Degree of Bachelor of Engineering ( Electronics & Telecommunication ) of Symbiosis International University.

Date :

Place :

Prof. Mrudang Shukla
Guide , Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115.

Prof. Dr. Narayan Pisharoty
Head, Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115.

3

Roll No. Prof. Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115. Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115. Mrudang Shukla Guide .4 CERTIFICATE This is to certify that the project entitled LICENSE PLATE RECOGNITION SOFTWARE submitted by _ Pathikrit Guha _ . Date : Place : Prof. 4 . is record of bonafide work carried out by her/him . _ 08070121232 _. under my guidance. Narayan Pisharoty Head. in partial fulfillment of the requirement for the award of Degree of Bachelor of Engineering ( Electronics & Telecommunication ) of Symbiosis International University. Dr.

08070121232 Is approved for the degree of BACHELOR OF ENGINEERING – Electronics & Telecommunication Symbiosis International University.08070121224 Pathikrit Guha .5 The Project entitled “LICENSE PLATE RECOGNITION SOFTWARE” By Abhinandan Singh . Examiners: 1. Pune. ______________________________________ 2.08070121202 Mayank Kishore . _______________________________________ Date : Place: 5 .

We would have never succeeded in completing our task without the cooperation. enlightenment and cooperation. Mrudang Shukla. Symbiosis Institute of technology. encouragement. Department of Electronics & Telecommunication. Pune who has been a constant source pf inspiration for us throughout this work. ability and strength in us to complete this work. Above all we render our gratitude to the ALMIGHTY who bestowed selfconfidence. Head of the Department of Electronics & telecommunication. Narayan Pisharoty. With deep sense of gratitude we express our sincere thanks to our esteemed and worthy supervisor Mr. 6 .6 ACKNOWLEDGEMENT The real spirit of achieving a goal is through the way of excellence and austere discipline. Assistant Professor. We shall be failing in our duties if we do not express our deep sense of gratitude towards Dr. We are also thankful to all the staff members of the Department for their full cooperation and help. inspiration ad help provided to us by various personalities. Pune for his valuable guidance in carrying out this work under his effective supervision. Symbiosis Institute of Technology.

Imaging Hardware Chapter 7.1 Project Background 3. 8.4 Segmentation 8. Image Acquisition 9. 8.2 Image Processing 4.3 Objectives 3.5 Various Types of Vehicle License Plate 3.6 Commercial Products Chapter 4 Platform / Technology 4.4 Constraints 3.1 Algorithm for ANPR system 8.3 Comparison Between MATLAB and Artificial Intelligence Chapter 5. Introduction 3. Algorithm 8.2 Conversion of RGB Images to Binary Images 7 Page no.2 Input Image from file.5 Number identification 8. Development History Chapter 8.1 Problem Statement 2.1Image Cropping 9. 10 11 12 14 14 14 15 15 15 17 18 20 22 24 24 25 26 27 28 29 34 34 34 34 34 34 35 37 37 38 . Literature Survey Chapter 2. Components Chapter 6.3 Convert image into binary.6 Save to file in given format Chapter 9. Problem Definition 2.2 Features of project Chapter 3.7 Table of Contents Contents List of Figures Abstract Chapter 1.1 Introduction to matlab 4.2 How the Vehicle License Plate System works 3.

1 Feature Extraction from Digital Image 13.1 Extracting of Individual Digits 15.1 Imcomplement 10.3 Colour Image Processing Chapter 10.1 Threshold Selection 11.3 Adaptive thresholding Chapter 12 Image Noise 12.2 Database Chapter 14 Character Recognition 14.8 9.2 Algorithm to normalisation of characters 17.1 Normalization 14.1 Filtering 12. Image Enhancement 10.2 Template Matching Chapter 15 Analysis of Result 15.4 Identify and remove away the small connected objects Chapter 13 Image Segmentation 13.2 Medfilt2 Chapter 11 Thresholding 11.2 Vehicle Quantization and Equalization 15.2 Binary Area Open(Bwareaopen) 12.2 Global Thresholding 11.2 Discussion Chapter 19 Difficulties and Recommendations 8 40 42 42 42 43 43 44 44 45 45 45 45 46 48 48 49 50 50 50 52 52 53 53 55 57 57 58 58 61 61 63 65 .1 Experimental results 18.3 Checking and verification of the Static Chapter 16 List of Functions Used Chapter 17 Code 17.3 Algorithm to read characters Chapter 18 Result Analysis 18.3 Filtering of Digits 12.1 Algorithm to extract digits 17.

9 Chapter 20 Critical Review and Reflection Chapter 21 Conclusion and Future scope Annexure A: Project Planner and Progress Report References 67 68 71 72 9 .

............................................................................................37 9.....2 Captured image of vehicle2..........................41 9..................................39 9..............................................................1 Overview of the vehicle license plate system..............10 List Of Figures 3.1 Comparison of MATLAb with other softwares..................2 A car approaching a License Plate Recognition System................................5 Histogram of object and background which is close...........................................................................................................1 Segmented image.......................................................16 3.....................................................................2 Cropped image of the vehicle...............................5 Commercial and Private vehicle license plate........50 15............................................2 Block diagram of Image processing system..55 10 ..............38 9.....................................................4 Histogram of light object with dark background................53 15.................................1 Original image of the vehicle.............4 Morphologically open binary image......................................24 4...........48 13.................3 Characteristic function of binary image.....18 3.........20 4................................40 9.1 Binary image with noise...........25 8..................3 Indian car license plate....................53 15..........................17 3...3Morphologically open binary image.....2 Binary image after filtering...................................................................................39 9...7 Captured image of the vehicle........................54 15.........................................................................47 12............................................4 System Block Diagram...........................................................................36 9........................41 12....................................19 3....1 Captured image of vehicle1.......8 Binary image of the vehicle.37 9..............................6 RGB schematic block diagram......................................1 Automatic Number Plate Recognition System..................................................

 Character Segmentation/Recognition: Resample and threshold in order to isolate the license plate and vehicle license plate character. License Plate Recognition is an effective form of AVI systems. In segmentation part. This system also helps to conduct the graphic images of the vehicles which can be further stored in the database in text format reducing size of data to be stored. In this study. red light violation enforcement. . The proposed algorithm consists of three major parts: Extraction of plate region. And finally statistical based template matching is used for recognition of plate characters. This system helps in the functions like detection of the number plates of the vehicles.  Plate localization and extraction: To obtain the vehicle plate sub image. processing them and using processed data for further processes like storing. segmentation of characters and recognition of plate characters. border and customs checkpoints.  Implementing a file management system or database for storing the images of vehicle license plate. allowing vehicle to pass or to reject vehicle. numbers and characters Keywords     Character recognizer license plate recognition Segmentation Cropping 11     template matching Median Filter Connected Components Masking. The performance of the proposed algorithm has been tested on real images. The general algorithm involves the following steps:  Image Processing : The image captured is pre-processed and reduction in the contrast. filtering and some algorithms are used.11 ABSTRACT Automatic Vehicle Identification (AVI) has many applications in traffic systems (highway electronic toll collection. a smart and simple algorithm is presented for vehicle‘s license plate recognition system.). Based on the experimental results. etc. we noted that our algorithm shows superior performance in car license plate recognition. We used neural network for recognition of vehicle license late character. For extracting the plate region.  Evaluating the performance of the algorithm and compare the performance with other reported work. The neural network will be trained off-line with the characters and numbers. This system is based on the image processing system. edge detection algorithms and smearing algorithms are used.

The third approach was based on statistical properties of text. Today in the developed countries more than 90% of the job is done by automated system and this is due to the accuracy. contrast. number of edges. such as electronic toll collection and red-light violation 12 . this method could be used to detect the similar properties in a certain image and locate the position of number plate regions. The input image being first processed to enrich and enhance boundary line-information by using such algorithms as the gradient filter. This approach was commonly used in finding text in images. angles. etc. Eventually. reliability and versatile nature of the computer. symmetry. License plate identification/recognition (LPI/R) is one form of ITS technology that not only recognizes and counts vehicles. nuclear plants. The early approaches were based on characteristics of boundary lines. but distinguishes each as unique. couples of 2-parallel lines were considered as a plate-designate. text regions were discovered using statistical properties of text like the variance of gray level.The project is based on image processing technology using popular software MATLAB. work only in certain conditions or environment like indoor images etc. Due to these features. In this approach. color dependent. To add the further mile for this step we have presented a License plate recognition software . such as Hough transform.12 1 LITERATURE SURVEY It is almost known that the world is nowadays being more dependent in the computer than the human manpower. All of the systems discussed above have some kind of limitations for example they are plate size dependent. The problem of automatic VNP recognition is being studied since the 90‘s. etc. Another approach was based on the morphology of objects in an image. For some applications. edge densities in the region. The image thus processed was converted to its binary counterpart and then processed by certain algorithms. communication centers all of them are under the control of the computer because that‘s not the place where human hand can reach up. and resulting in an image formed of edges. and could well be used for discovering and designating candidate number plate areas as they include alphabets and numerals. Vehicle License Plate Recognition is an image processing system whereby it is used to recognize the vehicles by identifying the license plate. It is basically use for traffic and security purposes. In the developed western countries many big factories. to detect lines. This approach focuses on some salient properties of vehicle plate images such as their brightness.

13 enforcement. occupying lanes reserved for public transport. a vehicle's license plate is checked against a database of acceptable ones to determine whether a truck can bypass a weigh station or a car can enter a gated community or parking lot. such as entering restricted area without permission . 13 . In others. For implementing LPR system we have used digital image processing technique. License plate recognition (LPR) is a new tool for automatic vehicle and traffic monitoring by using digital image processing. like commercial vehicle operations or secure-access control. breaking speed limits . etc. The LPR system can be used to traffic control management for recognize vehicles that commit traffic violation. crossing red light. LPI/R records a license plates alphanumeric so the vehicle owner can be assessed the appropriate toll or fine.

with some configurable to store a photograph of the driver. high error rates. the system can automatically display the status of the car which it will compare between the car plate numbers recognized with the database. human is needed to observe and list the user car plate number manually. misidentification. So this project is developing to replace human to monitor the car and automatically capture the image. They are used by various police forces and as a method of electronic toll collection on pay-per-use roads and cataloging the movements of traffic or individuals.1 Problem statement: Automatic car license plate recognition (CLPR) system is implemented to help the human to automatically detect plate number without human supervision. Systems commonly use infrared lighting to allow the camera to take the picture at any time of the day. Previously.[ANPR technology tends to be region-specific. 14 .2 Features Automatic number plate recognition (ANPR) is a mass surveillance method that uses optical character recognition on images to read vehicle registration plates. They can use existing closed-circuit television or road-rule enforcement cameras. and increased government spending. owing to plate variation from place to place. or ones specifically designed for the task. Concerns about these systems have centered on privacy fears of government tracking citizens' movements. ANPR can be used to store the images captured by the cameras as well as the text from the license plate. 2.14 2 Problem Definition 2. Besides that.

In entrance gate. number plate is recognized again and paired with the first-one stored in the database and it is taken a count. access and border control. When a vehicle later exits the place through the gate. The cycle will start when the vehicle steps over the detector. For example. or by special intelligent equipment which is be able to recognize vehicles by their number plates in a real environment and reflect it into conceptual resources. various recognition techniques have been developed and number plate recognition systems are today used in various traffic and security applications. such as parking. or tracking of stolen cars. vehicles can be directed to different lanes for a better congestion control in busy urban communications during the rush hours. Vehicle License Plate Recognition is an image processing system whereby it is used to recognize the vehicles by identifying the license plate. When a vehicle enters an input gate. Because of this. 15 . there was also a need to transform information about vehicles between the reality and information systems. This can be achieved by a human agent. . In some countries. this technology is used in many companies to grant access only to vehicles of authorized personnel. 3. In traffic control. number plate is automatically recognized and stored in database and black-listed number is not given permission. It will activate a signal to the Vehicle License Plate System of the presence of the vehicle. Each vehicle can be registered in a central database and compared to a black list of stolen vehicles. number plates are used to identify the vehicles.2 How the Vehicle License Plate System works Firstly. ANPR systems installed on country borders automatically detect and monitor border crossings. Automatic Line Tracking Robot (ALR) is used in this project as a vehicle which contains circuitry for moving in a guided track.15 3 INTRODUCTION 3. the vehicle will stop at the car gantry. It also will have capacity to park in the given parking area.1 Project Background Massive integration of information technologies into all aspects of modern life caused demand for processing vehicles as conceptual resources in information systems because a standalone information system without any data has no sense. Automatic number plate recognition systems can be used in access control. It will have mechanism to detect the opened and closed door.

Fig 3. Below are the non-constant variables which will affect the accuracy of recognition:  Speed of the vehicle 16 . The system will read the information pixels of the vehicle and run the recognition process. the system will try to match the recognized vehicle plate number with the car plate database.1 Besides. If ―Access Granted‖. the characters will be recognized by using Neural Network. Next. Besides analyzing. Next. the Vehicle License Plate Recognition also provide an advantage by keeping the image of the vehicle in which it will be useful for crime fighting. Lastly.16 Secondly. the gantry will open and allowed the vehicle to pass through. we also need to look into other facts of variables that are not constant. locating the vehicle plate position and extract the characters from the vehicle plate. illumination (infra-red) will be activated and images of the front picture of the vehicle will be taken. the system will apply certain algorithm to analyses the vehicle image. Diagram is illustrate in Fig 1. There are difficulties for Vehicle License Plate Recognition in which it will affect the efficiency and accuracy of the system. Thirdly. It is essential and important to determine the facts which will able to influence the operations and recognition proficiency. the images will be enhance. Camera can also focus on the face of the driver and save it for security reason.

Thus. The system will be based on a Personal Computer such that it will generate report on the vehicle license plate it has captured. the system can also serve as a security purpose whereby it can spot on any wanted or stolen vehicles. In the past. Fig 3.17       Weather condition Type of Vehicle Distance between vehicle license plate and the camera Type of plate ( Rectangular.3 Objectives The overall objective of the project is to develop a system to recognize vehicle license plate from a car at a gate entrance of a parking lot. Once the vehicle license plate is captured. there has been similar project implemented but had poor accuracy. Besides.2 A car approaching a License Plate Recognition System 3. The software could lead to a cheaper and faster way of enhancing and determined the performance of the recognition system. we would need to improve or rewrite the algorithm to improve the accuracy. the characters will be recognized and displayed on the Graphical User Interface. I 17 . Bent type) Vehicle license plate orientation Type of vehicle fonts character.

18 will address a set of constraints and focus on the design of the algorithm to extract the vehicle license plate in order to improve the accuracy. The constraint is listed as below:           Image taken only when vehicle is stationary.3 18 . Captured image of vehicle at fixed angle. Fig 3. Thus. Captured images on location where light is proportional. Take only the front view image of the car. Deal with only Indian Car License Plate with Times new roman font. There is definitely a lot more room for further improvement on this project. it is not advisable to include all of the possible cases.4 Constraints Due to limited time that we possess and dealing with image vision software. However. 3. Thus. we managed to come up with the progress guideline as to what need to be included in this project. The vehicle license plate position should be captured centred. Try on zoom in image of the car and image consists of headlamp. in discussion with my tutor. The image should be taken with the height of 50cm to 70 cm above the ground level. due to the limited time frame given. it is not advisable for me to cover all aspects in this project. we have to set a list of constraints to make the project more systematic and manageable. Captured image of vehicle at fixed distance. There will be no motion capture image.

19 System block Diagram Fig 3.4 19 .

Instead they have the Emblem of India in gold embossed on a red plate.  Current Format The current format of the registration index consists of 3 parts    The first two letters indicate the state to which the vehicle is registered. The President of India and state governors travel in official cars without licence plates.. DL 2C 0001).g. The next two digit numbers are the sequential number of a district.  Format Vehicle owner who register the car as private vehicle have a white background and black text.5 20 . This scheme of numbering has some advantages:   the State or District of registration of a particular vehicle In the case of a police investigation of an accident or vehicle-related crime. Commercial vehicles such as taxis and trucks have a yellow background and black text (e. Fig 3. The third part is a 4 digit number unique to each plate.5 Various Types of Vehicle License Plate  What is Car license Plate Car license Plate is a rectangular metal plate which consists of a combination sequence of alphabet characters and numbers issued by the government for identification purpose of registered vehicle.g. the numbers were given to the RTO offices of registration as well. Due to heavy volume of vehicle registration. Vehicles belonging to foreign consulates have white lettering on a light blue background (e. witnesses usually remember the initial area code letters — it is then quite simple to narrow down suspect vehicles to a much smaller number by checking the database without having to know the full number. A letter(s) is prefixed when the 4 digit number runs out and then two letters and so on.20 3. 22 UN 14).

probably a country close to the letter A or B. a pollution under control (PUC) certificate and the driver's licence. The permanent registration certificate is one of the four important documents a vehicle plying on the road should always have. The numbers are registered by the Ministry of Defence in New Delhi. taxis and auto-rickshaws. Diplomatic plates Vehicle belonging to foreign missions bear the plates UN. it has to be presented to the RTO's office. this prevents the number being read wrongly in case the plate (and/or the vehicle bearing it) is upside down. A diplomatic plate numbered 13 CC xxxx would refer to country 13. The next two digits (or the two preceding the arrow) signify the year in which the Military procured the vehicle. For example. To register a vehicle.21 Military vehicles Military vehicles have a unique numbering system unlike any other licence numbers. there are a number of additional documents like a roadworthiness certificate and a transportation permit. The next is the base code. The first (or the third) character is always an arrow pointing upwards. Other numbering Other numbering includes the special numbers allotted to public transportation such as buses. CD or CC. which stand for United Nations. This mechanism is used for unique identification. The numbers are registered by the organization which run the services and are usually printed on the side of the vehicle. Diplomatic Corps or Consular Corps respectively. during which the owner must register the vehicle in the controlling RTO of the area in which the owner is residing to get a standard licence plate. the others being a valid insurance certificate. where a Motor Vehicle Inspector will verify the applicant's address and other details. 21 . The letter ending after the serial number indicates the class of the vehicle. the dealer of the vehicle issues a temporary licence sticker known colloquially as a TR (To Register) number. a vehicle bearing the number 77 CD xxxx in India refers to a vehicle owned by either the United States mission in India or by a person working with the mission. confirm that the engine and chassis numbers are identical to what is written in the application and issues a permanent registration certificate which is usually valid for 20 years. taxis and pick-up vans. This is valid for one month. followed by the serial number. trucks. For public utility vehicles like buses. Temporary numbers As soon as a vehicle is purchased.

captures and identifies a vehicle's license plate data and makes a read decision.2 Perceptics Perceptics [27] is the world leader in license plate reader technology. it automatically locates vehicle license plates and reads the numbers accurately each time every time.6. 22 . Using advanced image processing and artificial intelligent techniques such as AI best first breadth-wise search algorithm. 3. 3. easy installation and has accessories and features for most parking security surveillance needs. Current LPR system read Latin (A-Z) and Korean (Hangul) letter and Arabic number (09).6. • Works 24 hours a day. 3. VISPA provides for state-of-the-art video technology. uses video imaging for better recognition. The system's reliability and flexibility allow it to accommodate some of the most stringent needs in some of the worst conditions. • Automatic and within milliseconds. combined template and neural network recognizers. identification and improved security.1 IMPS (Integrated Multi-Pass System) An IMP [26] is a Singaporean commercially developed license plate recognition system. • Reads accurately at highway speeds. however. It is a high performing robust system that gives consistent results under all weather conditions. 7 days a week. Features of this LPR technology includes. fuzzy logic and an arsenal of image processing tools.6 Commercial Products The various products in the market today are described briefly below. • Reads accurately in most weather conditions. With milliseconds the LPR system locates.6.22 3. the LPR can be programmed to read any language or symbol in any alphanumeric combination or context on both retro and non-retro reflective plates.3 Vehicle Identification System for Parking Areas (VISPA) PPI's Vehicle Identification System for Parking Areas (VISPA) [28].

An image of the car and/or the driver (depending on the location of your camera) will be taken as soon as the car approaches the triggering device. Enhanced Version:. traffic surveillance. The image will be linked to the ticket. The VISPA controller with an integrated frame grabber card for 4. and transmits the ID string to the port or gate computer. • Compatible with standard hardware and software.23 Features are • Open architecture to most common video-systems. such as SeeGate .Tracks and reads Shipping container identification marking. the system read the camera images and extract the identification data from the images. as a stand-alone turn-key version. SeeCar License Plate Recognition:. Windows DLL or Linux library. The recognition result is then logged together with the images. or to a client process.Detects and reads Vehicle license plates for parking. or in form of different special-task systems. Available as complete systems. or SeeCrane . law enforcement and security applications. 23 . There product includes.6. the records include both the image plus the extracted result. The basic system version connects to 4 cameras and can be upgraded to 8 cameras. 8. access control. or 16 cameras automatically identifies the license plate from the video image and stores it in a database.a recognition system for the Tracks and Containers. • Can be customized according to specific user needs. The license plate can then be encoded on the ticket.4 Hi-Tech Solution Hi-Tech Solutions [29] is a system and software company that develops cutting edge optical character recognition (OCR) solutions by implementing the company's unique image processing software and hardware in a wide range of security and transportation applications. This is the main advantage of vision based recognition. Available as a complete system which is based on a background Windows application. There technology is based on computer vision. SeeContainer Identification System:. 3.License Plate Identification. VISPA is available in two forms Basic Version: .crane mounted Container recognition system.

predefined function and deviceindependent plotting. Graphical User interface and MATLAB compiler.1 INTRODUCTION TO MATLAB MATLAB is chosen as the main development for the license plate recognition application. The advantages of MATLAB can be classified as follows: Platform independence. MATLAB is also very efficient as it have built-in-function tools for neural network and image processing.24 4 Platform/Technology 4.1 MATLAB read images using the function ―imread‖. Comparison of MATLAB with other program is shown in the below diagram. Fig 4. The task is to construct the algorithm and recognizes can be done using MATLAB. Besides. 24 . The table below show images/graphs format that is supported by ―imread‖ with MATLAB.

xwd 4.2 Image Prcessing Image Processing generally involves extraction of useful information from an image. This useful information may be the dimensions of an engineering component. Traffic Control etc. or even a 3D view of an unborn baby. Quality Control.2 25 .tiff .tif. . . The main areas of application of Image Processing are Bio-Medical.gif . Face Detection. Engineering.25 Format Name TIFF JPEG GIF BMP PNG XWD Description Tagged image file format Joint photographs Expert Group.Jpeg . size of diagnosed tumour. Graphic Interchange Format Windows bitmap Portable network Graphics X Window Dump Extension . Block Diagram of Image Processing Steps Fig 4.png .bmp .Jpg .

Data can be represented in terms of matrices or vectors. 4. 2.  Disadvantage of Artificial Intelligence: 1.26 4. The system will perform faster when using “Matrix Approach”. Expensive. 2. We can changed and add individual rules. 3. MATLAB coding is shorter and simpler. 26 . 5. Good for solving complex problems where humans or programmer have expert knowledge in it. 3. Non-programmers can easily understand the rules of artificial intelligence. MATLAB possess power graphic visualization tools. . 2. 3. Not good in common sense reasoning. There are difficulty in getting expert knowledge and putting it in used in the system. 5. 4.  Advantage of MATLAB 1. Slow response. Algorithm used in MATLAB can be converted to use in hardware. Unpredictable.3 Comparison Between MATLAB and Artificial Intelligence  Advantage of Artificial Intelligence: 1.

the information captured of the plate alphanumeric. ANPR systems are generally deployed in one of two basic approaches: one allows for the entire process to be performed at the lane location in real-time. or stored at the lane for later retrieval. Often in such systems. lane identification. there is a requirement to forward images to the remote server. can easily be transmitted to some remote computer for further processing if necessary. and then optical character recognition (OCR) to extract the alphanumeric of the license plate. and any other information that is required is completed in somewhere around 250 milliseconds. now small data packets. normalize and enhance the image of the number plate. In the other arrangement. such as those found in the London congestion charge project. It first uses a series of image manipulation techniques to detect.27 5 COMPONENTS The software aspect of the system runs on standard home computer hardware and can be linked to other applications or databases. there are typically large numbers of PCs used in a server farm to handle high workloads. date-time. and this can require larger bandwidth transmission media. 27 . and the other transmits all the images from many lanes to a remote computer location and performs the OCR process there at some later point in time. This information. When done at the lane site.

This is only possible on dedicated ANPR cameras. To avoid blurring it is ideal to have the shutter speed of a dedicated camera set to 1/1000 of a second. headlight glare and harsh environmental conditions. or when the camera is at a lower level and the vehicle is at an angle approaching the camera. varying ambient lighting conditions. Manufacturers have developed tools to help eliminate errors from the physical installation of license plate capture cameras.28 6 IMAGING HARDWARE At the front end of any ANPR system is the imaging hardware which captures the image of the license plates. License plate capture is typically performed by specialized cameras designed specifically for the task. slower shutter speeds could result in an image which is too blurred to read using the OCR software. however. and so cameras used for other purposes must rely more heavily on the software capabilities. installers should carefully consider the positioning of the camera relative to the target capture area. This returns the light back to the source and thus improves the contrast of the image. To maximize the chances of effective license plate capture. Exceeding threshold angles of incidence between camera lens and license plate will greatly reduce the probability of obtaining usable images due to distortion. In some countries. when a full-colour image is required as well as use of the ANPR-retrieved details it is necessary to have one infrared-enabled camera and one normal (colour) camera working together. giving a high level of contrast with the reflective background in any lighting conditions. Factors which pose difficulty for license plate imaging cameras include speed of the vehicles being recorded. Many countries now use license plates that are retro reflective. Since the car is moving. License plate capture cameras can now produce usable images from vehicles travelling at 120 mph (190 km/h). In slow-moving traffic. A camera that makes use of active infrared imaging (with a normal colour filter over the lens and an infrared illuminator next to it) benefits greatly from this as the infrared waves are reflected back from the plate. the characters on the plate are not reflective. especially if the camera is much higher up than the vehicle. Shutter speeds of 1/500 of a second can cope with traffic moving up to 40 mph (64 km/h) and 1/250 of a second up to 5 mph (8 km/h). Most dedicated license plate capture cameras will incorporate infrared illumination in order to solve the problems of lighting and plate reflectivity. the shutter speed does not need to be so fast. 28 . Further.

there are 3. 2003). i. 2006). Instead. if it had been involved in another crime. partially destroying the façade of the Exchange‘s offices and extensively damaging the rest of the building (Baltic exchange.29 7 Development History The United Kingdom: In 1992. as well as a video image of the plate and a video of the vehicle occupants (Pughe. the heart of London‘s financial district (1993 Bishops gate bombing. 2006). the Irish Republican Army bombed the Baltic Exchange. In addition. When a plate is photographed by an ANPR camera. The United Kingdom is at the forefront in the use of plate recognition technology. 10 times the national average (PA Consulting Group. killed one person. or if it was uninsured (Pughe. In 2002 to 2003. The results of this initial study indicated that officer productivity increased primarily due to the officers not having to spend as much time waiting for hits after they typed in a plate. the patrol officer is provided with information regarding the vehicle. the United Kingdom evaluated the use of ANPR with nine police forces. 2008). 29 . 2006). and police forces were provided with computers that were able to store ANPR information in real time (Pughe. the time and date of the scan. a JPEG image of the plate is produced. The bombing was massive in size and destroyed several buildings with many others suffering shattered windows. 1993. a text file containing information on the car registration number. 2006). scanning up to 5 million plates a day (Pughe. NADC stores plate data and lists of suspect vehicles (Pughe. officers were able to spend more of their time investigating hits. ALPR technology was developed at Cambridge University in the United Kingdom in response to terrorism. 2006). such as whether the car was stolen. Almost a year later on April 24.e. and the GPS location of the camera is created. 1992. stationary (roadside) and mobile (mounted on police cars). As a part of its intelligence network. The central ANPR system. the databases. all 43 police forces in England and Wales were provided with vans equipped with automated number plate technology (ANPR1): ANPR cameras were mounted in vans. 2008). As of 2001. and injured 44 others. On April 10. This resulted in an increase in arrests to 100 per year. Approximately four seconds after a plate is read by the camera. the Irish Republican Army detonated a truck bomb at Bishops gate. is stored at the National ANPR1 This term is synonymous with ALPR and will be used interchangeably 3 Data Center (NADC) in London. The blast caused approximately £1 billion in damage.000 cameras across the United Kingdom. a British company operating a premier global marketplace for shipbrokers and charterers.

30 In total. and 8. workload concerns continued to exist. equivalent to approximately one stop per hour. 200 arrests per month (Metropolitan Police Service. seven instances of drug seizures (equivalent to approximately 3.300 pounds total).8% of arrests were made for theft or burglary offences. an average. ANPR technology continues to be used across the United Kingdom. the number of vehicles used in the commission of other criminal offences. On an annual basis. however. 2003). these units made. In effect. One-quarter of the arrests were for disqualified. over 1. three instances involving the recovery of other stolen goods (equivalent to approximately 23. For instance. and five instances of recovery of other stolen property (PA Consulting Group. 180. 2006).g. and fatal and serious injury road traffic accidents (Hampshire Constabulary. enforced an arrest). In total. a constable using ANPR technology could expect to encounter: the recovery of 11 stolen vehicles (equivalent to approximately 68. In effect. However. 2003). or prohibited drivers. A further 16. no date). ANPR was beneficial to police forces by providing better efficiency in the deployment of officers. In 2005 and 2006. 30 . This initial study also provided the Home Office with descriptions of the quantity of vehicles on the road violating insurance or other traffic regulations.000 pounds). the data also highlighted the limited ability of the intercept teams to respond to the volume of hits they received. Over this one year period.000 pounds total). the Hampshire Constabulary uses ANPR to prevent and detect terrorism. Currently. 2004). on average. and the number of vehicles owned or operated by persons of interest (PA Consulting Group. The results also indicated that the police could expect a substantial increase in the amount and value of goods they recovered. serious crime.2% for drug offences. There are deployment teams who are used to assist in targeting hot spots for vehicle and other crime. police were only able to respond to 13% of hits (PA Consulting Group. again suggesting a need for policy outlining a response priority scheme. volume crime.543 vehicles were stopped by intercept teams resulting in 13. 10. 2004). A second evaluation was conducted between June 2003 and June 2004 with 24 police forces (PA Consulting Group. The Metropolitan Police Service operates four ANPR units who work across London. The results of this study were similar to the first study. arrests were made in nearly 4-8% of the vehicle stops. uninsured.000 stolen vehicles were recovered over this period (PA Consulting. approximately one out of every 200 cars photographed by the ANPR cameras was stopped by an ANPR intercept team. In nearly two-thirds (61 per cent) of these stops. The results of this evaluation also demonstrated that the ANPR technology contributed to a substantial increase in arrests (Pughe. 2003). 2007). two seizures of weapons and/or firearms. the intercept team took some action (e.3% for theft of or from a vehicle.499 arrests.

primarily in the form of ―red light cameras‖ (Jenkins.m. This technology will also be used. These offenders have a photograph taken of their plate by the ALPR cameras and receive a ticket in the mail. 2007). The US has also used plate recognition technology at border crossings with Mexico and Canada to track auto theft (Canadian Press NewsWire. in several jurisdictions.m. Fines for traveling within the zone without paying the charge are £60 per infraction if paid before the deadline. More recently. A reduced fee of £9 is paid by vehicle owners who sign up for the automatic deduction scheme. Both front and back number plates are being captured. It is estimated that around 98% of vehicles moving within the zone are caught on camera. A recent study of ALPR technology in the state of Ohio emphasized 31 . In 2007. on vehicles going both in and out – this gives up to four chances to capture the number plates of a vehicle entering and exiting the zone. 2006). There are also a number of mobile camera units which may be deployed anywhere in the zone. There are currently 1. which use Automatic Number Plate Recognition (ANPR) technology. The London congestion charge is an example of a system that charges motorists entering a payment area. A second data centre provides a backup location for image data. to catch drivers who violate speed limits (Jenkins. and 6:00 p. leave or move around within the congestion charge zone between 7 a. doubling to £120 per infraction thereafter. The United States Over the past several years.500 cameras.. 2007). This list is then compared with a list of cars whose owners/operators have paid to enter the zone – those that have not paid are fined. the United States has also introduced plate recognition technology. 150 American cities utilized this technology to catch those who drove through red lights. Transport for London (TfL) uses ANPR systems and charges motorists a daily fee of £10 paid before 10pm if they enter. The registered owner of such a vehicle is looked up in a database provided by the DVLA. Monday to Friday. The video streams are transmitted to a data centre located in central London where the ANPR software deduces the registration plate of the vehicle. ALPR has been used to track potential terrorists.31 Charge zones – the London congestion charge The London congestion charge scheme uses 230 cameras and ANPR to help monitor vehicles in the charging zone.

whether in the form of additional police on the roads utilizing this technology or the hiring of additional staff to assist in confirming hits. are prohibited from driving. criminal justice. One way to offset these resource increases may be to. wherever possible. Still. Over the four month period.000 (McClellan. and/or conducting further searches of licence plates. Using information obtained through 32 . using $61. ALPR was introduced in British Columbia as part of a pilot study in 2006. no date). 2007). did not provide information on unlicenced. updating the databases. for instance. must be weighed against the costs recovered through the use of this system. 2004). ALPR has the potential to allow Canadian police forces to engage in proactive policing. The United Kingdom established a central data warehouse in London containing information from insurance. the state highway patrol apprehended 23 criminal suspects and recovered 24 stolen vehicles valued at US $220. It is important to note that the ALPR technology used in this study was only linked to databases on stolen vehicles and wanted persons and. Nearly one-third (30 per cent) of the tolls are tracked through licence plate recognition technology allowing for faster movement of traffic as the need to stop and physically pay the toll is eliminated (Commission for Integrated Transport. installing. The cost of warehousing this data. The Highway 407 Express Toll Route was introduced in 1997. use civilian volunteers. Schuurman (2007) recently produced an analysis of the use of this technology in parking lots in Surrey. or prohibited drivers. The state of Ohio studied the effectiveness of ALPR technology over a four month period in 2004. uninsured. ALPR technology has been used in Toronto for toll-collection purposes. police can use ALPR technology linked to criminal justice and insurance databases to identify those drivers who. the technology also offers police a potentially useful tool for identifying and recovering stolen vehicles. including reductions in criminal activity. beginning in August 2004. or are driving uninsured vehicles. therefore. Canada ALPR technology in Canada has only recently been implemented for use with traffic and other criminal violations. and maintaining ALPR technology.000 in federal funding. have outstanding warrants. British Columbia.32 the recovery of two stolen trailers demonstrating the technology‘s potential utility for homeland security (McClellan. recovery of stolen goods. It allows drivers to use the express route for a toll fee that is recorded electronically. As previously discussed. and other agencies that is linked with the ALPR technology in police cruisers. Additional staffing costs may also be incurred. 2004). there are several issues that must be considered prior to the widespread use of ALPR technology in Canada. and increases in positive public perceptions of the police (Schuurman. These results were 50% higher than results during the same time period one year previous. By driving through traffic corridors in cities across Canada. in addition to the cost of buying.

lists of vehicles of interest2 were populated on a daily basis and uploaded to the patrol car‘s onboard computer. The remaining hits were for unlicenced (i. uninsured) vehicles (23. research must be conducted to determine the extent to which such technology is useful to Canadian police forces. The current study intends to provide some initial data regarding the use of ALPR technology in British Columbia. Given that there is limited information available to date on the use of ALPR technology. on average. there were. especially to locate and recover stolen vehicles. The Hot Lists were for unlicenced vehicles.8 per cent). 33 . Such research can be used to inform deployment strategies. 2007).876 licence plates were scanned. In fact. and stolen vehicles. Scanned plate images were compared to the CPIC and MVB databases. Of these. Schuurman‘s (2007) results indicated that 1. for example.33 the Canadian Police Information Centre (CPIC) and the Motor Vehicle Branch (MVB). prohibited drivers (4. Schuurman (2007) concluded that the deployment of ALPR technology exclusively to parking lots would not be the most efficient use of the system. one unmarked patrol vehicle drove through 31 Surrey parking lots scanning the licence plates of parked cars over the period of one week. in determining whether it is more beneficial to have police equipped with ALPR technology drive their usual patrol routes or travel exclusively within known ―hot spots‖ (Schuurman. It was concluded that using the technology in a stationary format along major intersections or installing it in mobile units that patrolled the jurisdiction‘s main roads would likely be more effective for identifying stolen vehicles. 2007). Canada. and over two-thirds (69. Over the course of this study.7 per cent) of the scans accurately captured the car‘s licence plate. uninsured drivers.6% of scanned plates resulted in a ‗hit‘.8 per cent) of hits were for unlicenced drivers.e. prohibited drivers. Nearly three-quarters (72 per cent) of the hits occurred between 3pm and 7pm.9 per cent). four hits every hour (Schuurman.4 per cent). nearly all (97. To collect the data for this initial study. 21. and stolen cars (1.

34

8 Algorithm
8.1 Algorithm for ANPR system 1. Input image from webcam. 2. Convert image into binary. 3. Detect number plate area. 4. Segmentation. 5. Number identification. 6. Save to file in given format. 8.2 Input Image from file. 1. Capture image from webcam. 2. Store the captured image into a image file for further processing. 8.3 Convert image into binary. 1. Identify the intensity of the image. If image intensity = high Reduce intensity Else if intensity = low Increase intensity Else No change. 2. Convert image into grayscale. 3. Calculate appropriate threshold value for the image. 4. Convert the image into binary image using the calculated threshold. 8.4 Segmentation 1. Crop the image. 2. Filter the noise level present in the image. 3. Clip the plate area in such a way that only numbers of plate area extracted. 4. Separate each character from the plate. 8.5 Number identification 1. Create the template file from the stored template images. 2. Resize image obtained from segmentation to the size of template.
34

35

3. Compare each character with the templates. 4. Store the best matched character. 8.6 Save to file in given format 1. Open a text file in write mode. 2. Store the character obtained from the number identification process to text file in given format. 3. Close the file.

35

36

Overview of the Vehicle license plate System

Fig 8.1
36

2 : Cropped Figure 37 . The figure below shows the copping of image: Fig 9. webcam etc can be used to capture the acquired images. Electronic devices such as optical (digital/video) camera.1: Original Image Fig 9. 9. The images will be stored as colour JPEG format on the camera. Next. vehicle images will be taken with a Panasonic FX 30 digital camera. For this project. As the license plate surrounding is of no importance. we might proceed in using the Matlab function to convert the vehicle JPEG image into gray scale format.1 Image Cropping Image cropping is a recognition process whereby it will extract the smallest rectangle which will contains the edge of the license plate and license plate itself.37 9 Image Acquisition The initial phase of image processing for Vehicle License Plate Recognition is to obtain images of vehicles. this cropping process will highly increase the speed of image processing.

2. Each pixel in the image has a brightness value which is known as grey level. then by converting the grayscale image to binary image by thresholding. We will obtain white object with black background or vice versa. The conversion is done by using the toolbox in MATLAB (im2bw).38 9. The pixel of grey level above the threshold will be set to 1 (equal to 255. Binary images is the simplest process and has apply to many other application. The application is as:  Text interpreting  Identify the object orientations Next.3 38 .2 Conversion of RGB Images to Binary Images In order facilitate the next process smoothly and reducing the processing time. It is useful as the information we need can be obtained from the silhouette of the object. white) and the rest will be set to 0 (black). The image is made up of a matrix squares which is called Pixel.1 What is Binary Images It is an image which quantatised into two values representing 0 and 1 or in pixel values of 0 and 255 representing the colour black and white. Binary Images are obtained by converting the input image into grayscale format. The characteristic function for the image object is classify below: Fig 9. the image obtain is being converted to Binary Image. 9.

5 : Histogram of object and background which is close 39 .39 Below will illustrate different type of histogram images Fig 9. Frequency Fig 9.4: Histogram of light object with dark background.

there is difficulty in choosing the threshold as the histogram is no more bimodal This root cause is due to the variations of light or colours in the images. Fig 9. The colour space is normally graphically shown as RGB colour cube. The cube vertex consists of the primary colour (Red. Magenta and Yellow). Green and Blue) and the secondary colour (Cyan. 9.40 In this circumstance.3 Colour Image Processing RGB Colour Space The RGB image is made of colour pixels of an M x N x 3 array.The schematic of the RGB cube that illustrate both the primary and secondary colour at each vertex is shown below.6 40 .

41 Fig 9.7 : Original Image Fig 9.8 : Binary mage 41 .

black will becomes white and white will be come black . Therefore. zeros will become ones or ones will become zeros. For the complement of the true color image.1 IMCOMPLEMENT Imcomplement will compute the complement image(IM). color image processing and image segmentation as well. the value of each pixel will be subtracted by the maximum pixel value which is supported by the class. 10. the light areas will become darker and the darker area will become lighter. The pixel value obtained by the differences will be used in the output image. IM can intensity. 42 . reducing noise. binary or true color image.2 MEDFILT2 Median filtering is a nonlinear operation often used in image processing to reduce "salt and pepper" noise. contrast manipulation.42 10 IMAGE ENHANCEMENT The aim of this process is to increase and improve the visibility of the image. For the complement binary image. Image Enhancement techniques consists process of sharpening the edges image. 10. A median filter is more effective than convolution when the goal is to simultaneously reduce noise and preserve edges.

43 . however.y) =1 for image object. Fast and cheap. One of the simplest process will be the Gray-level thresholding. and is robust against image noise. often making the selection of an accurate threshold difficult. does not require much specific knowledge of the image. Several different methods for choosing a threshold exist. F (x. A more sophisticated approach might be to create a histogram of the image pixel intensities and use the valley point as the threshold.y)>=T. the rationale being that if the object pixels are brighter than the background. Thresholding is one of the oldest segmentation method.y) < T. which is known as automatic thresholding . One method that is relatively simple. this may be computationally expensive. this will generally not be the case.1 Threshold Selection The key parameter in the thresholding process is the choice of the threshold value (or values. It also transform the input image(K) into an output binary image (F) which is being segmented. the mean or median will work well as the threshold. Representing F (x. is the following iterative method: 1. they should also be brighter than the average. The regions of the images are classified by the reflectivity and absorption of light on its surface. or a thresholding algorithm can compute a value automatically. It is still greatly used in applying on the applications in the market due to certain reason. The histogram approach assumes that there is some average values for both the background and object pixels.y) = 1 if K (x.43 11 Thresholding Image thresholding enjoys the central position of any application in the process of image segmentation.y) = 0 for background of the object and T = threshold. as mentioned earlier). = 0 if K (x. However. users can manually choose a threshold value. 11. and image histograms may not have clearly defined valley points. The value of threshold (T) is being selected and compare with the pixel of the image. An initial threshold (T) is chosen. this can be done randomly or according to any other method desired. In such cases a unimodal threshold selection algorithm may be more appropriate. A simple method would be to choose the mean or median value. In a noiseless image with uniform background and object values. F (x. but that the actual pixel values have some variation around these average values.

2 Global Thresholding This is a method whereby the histogram of the image is being partitioned using a single threshold value.n):f(m. which has been proven to converge at a local minimum— meaning that a different initial threshold may give a different final result.e. The threshold defines the value of the gray level in which the baseline boundary is in between the foreground pixels and the background. the threshold will try to reduce the error of taking the background pixels as object pixel and vice versa.n)>T} (object pixels) 2. For other cases. 44 . The value of the gray level varies from the darkest (0) to the brightest (255). 11. G2= {f(m.44 2. until convergence has been reached). The image is segmented into object and background pixels as described above. This is a common reason why global thresholding fail. By using the adaptive thresholding. nth row) 3. creating two sets: 1. T‘ = (m1+m2)/2 5. The average of each set is computed. A new threshold is created that is the average of m1and m2 1.. m2= average value of G2 4.n):f(m. m1= average value of G1 2. in which the modes are overlapping. If the histogram is bimodal. 1. G1= {f(m. This iterative algorithm is a special one-dimensional case of the k-means clustering algorithm. now using the new threshold computed in step four. f(m.n) is the value of the pixel located in the mth column. keep repeating until the new threshold matches the one before it (i. the value of the threshold will be taken in the middle of the bimodal.3 Adaptive Thresholding The vehicle number plate can be partially illustrated.n) T} (background pixels) (note. Image is form up of square matrixes called pixels and each pixels in the image have a brightness level known as gray level. its can solve the disadvantages of the global thresholding as it computes the value of the threshold for every pixel separately using the neighborhood. We can use the graythresh toolbox function to calculate the threshold value by using Otsu‘s method. The threshold value which is selected is use to reduce the intraclass variance between the white and black pixels. Go back to step two. 11.

12. we need longer time for the image sensor for collection of weak signal. 12. blurring with liner/non liner filter is able to achieve noise reduction. softening is often applied to the low pass filter and it will affect the image to become blurring. We will be enlarging the signal from the received light photons when we are using the digital camera with a higher ISO setting. We can apply convention techniques such as softening and sharpening. Blurring is used in the preprocessing step which involved in removing and cleaning up of small patches and details from the image prior to object extraction.1 Filtering In this pre-processing stage.3 FILTERING OF DIGITS Now. In this circumstance. In order to reduce the background noise. The syntax is as bellowed: BW2 = bwareaopen(BW. filtering process is used for blurring and for noise reduction and thus resulting a more sharpen image. bridging of gaps in curves and lines. it will reproduce another binary image. It has been cropped to a rectangular shape in which it enhances the algorithm to be more uniformed in the further stages. Thus. the electrical noise from the background will be higher than the signal.P). Next. From the amplification of the signal.2 Binary area open (Bwareaopen) The MATLAB toolbox function provide a bwareaopen function in which it removes the connected component which have fewer than P pixel.45 12 IMAGE NOISE Digital camera with long exposure time setting and high ISOs will produced images with lots of noise. the electrical noise in the background is also being amplified. The reason of noise contamination on the image is categorised as below:  There will be not enough light source for proper exposure to activate in a low light area/ Therefore. we have managed to obtain the black and white image of the Vehicle License Plate. Noise in the images is appears as the colour speckles whereby there should not be any. 12. 45 .

4 Identify and remove away the small connected objects For this stage. The component can have a value of either 4-connected or 8-connected. we are able to remove or filter out the unwanted substances or noise that is not a character or digits. After the component has been labelled. sand. The elements of labels (stated in the algorithm) contains integer values that will be greater than or equal to 0. Lastly. we need to identify the connected components. so on and so for. The 2 stages for the algorithm is as follows: 1) Remove out the small objects or connected components. effects on JPEG compression. The pixel of 0 represents the background and pixel of 1 will make up the first object. 141 connected components are found in the BW image. Below illustrate an example of filtering process. Fig 12. 2) Identify the frame line that is connected to the digits and separate it. By Filtering. the pixel of 2 will label the second object. they will obtain a unique number. 46 . 12.1 : Binary image with Noise For the above image. frame lines. In this algorithm. we use 8-connected (8 specify 8-connected objects). the image is only left with characters and digits in which we are interested.46 The non-digits substance which appears in the image is caused by the noise (quantization that will transform to ‗Black‘). object or substance which is not digits/characters such as screws. water droplet.

2 : Binary Image after Filtering. Next. we have apply the median filter and bwareaopen (Image Processing Toolbox) whereby it will remove all the connected components from the binary image that have value less than P pixels. in which it will produce another binary image. components with less than 6000 is classify as non digits components and need to be taken away. 47 . Therefore.47 Fig 12.

Lastly will be the edge-based segmentation. which is by using threshold. The color or texture of the image is basically the internal representation whereas the external representation is based on the characteristic of the shapes. The feature of the image is represented by a histogram. imshow(~n1). letter=read_letter(img_r). Segmentation process can be categorized into several parts.48 13 Image Segmentation Image segmentation plays an important and critical step that lead to the analysis of the processed image data. The normalized character description is based on the external characteristics as we only work for properties on the shape of the character. word=[word letter].c] = find(L==n). end 48 . n1=imagen(min(r):max(r). If we classify the similar character into classes. we will be trying out first category segmentation method. disp(Ne). the descriptor of the character from the same class is close to each other in the vector space. The process of the feature extraction is to transform the bitmap data into a form of descriptor in which more suitable for computer. The process uses the edge detection to obtain the region contours and the objects will construct from the obtain contours. The algorithm below will represent how the extraction is being carried out and extracted figure is illustrated as below. This will lead to a success in pattern recognition process. The descriptor vector includes the characteristics as the number of lines.1 FEATURE EXTRACTION FROM DIGITAL IMAGE The digital image description is depends on the external and internal representation. Secondly is the boundary-based segmentation.min(c):max(c)). In order to extract and analyzed the object characteristic. Firstly is the global Knowledge of an image. [L Ne]=bwlabel(imagen). 13. for n=1:Ne [r. vertical or diagonal edges etc. img_r=same_dim(~n1). For this project. the process need to partition the image into different parts that will have a strong correlation with the objects.

It will ignore the class if the image thresholding is too low. If the class has match correctly. contents and images. Database is needed to make sure that the image space can contained enough characters which have been extracted and the vehicle license plated number stored in the excel sheet for the purpose of comparison.2 Database It is a collection of information or data which it is being orderly organize. it will be compare with data set in the database and provide an output if the image is recognized correctly.1 13. thus it can be accessed easily and updated. Database can be in the form of text. 49 . The class recognition will check if the computed ratio is correct.49 Plotted Bounding Box Fig 13. The database would be enlarged in order to improve the accuracy and better chances of obtaining the correct result.

An algorithm for obtaining normalized cross correlation from transform domain convolution has been developed.y under the window containing the feature t positioned at u. 14. In the expansion of d2 50 .2. Unfortunately the normalized form of correlation (correlation coefficient) preferred in template matching does not have a correspondingly simple and efficient frequency domain expression. For the project. each character is normalized to the size of (42x24) binary image and then follow by reshape to standard dimension before sending the data set to the next for comparison with the templates. For this reason normalized cross-correlation has been computed in the spatial domain.v).2 Template Matching The correlation between two signals (cross correlation) is a standard approach to feature detection as well as a component of more sophisticated techniques. The new algorithm in some cases provides an order of magnitude speedup over spatial domain computation of normalized cross correlation. see Lewis . Textbook presentations of correlation describe the convolution theorem and the attendant possibility of efficiently computing correlation in the frequency domain using the fast Fourier transform. Due to the computational cost of spatial domain convolution. (where f is the image and the sum is over x.1 Normalization In this phase. the extracted characters are resized to fit the characters into a window. several inexact but fast spatial domain matching methods have also been developed.50 14 Character Recognition 14. 14.1 Cross Correlation The use of cross-correlation for template matching is motivated by the distance measure (squared Euclidean distance) .

If the term constant then the remaining cross-correlation term is approximately is a measure of the similarity between the image and the feature. 51 .51 the term is constant.

1 Extracting of Individual Digits Determine the angle of the Vehicle License Plate. Fig 15.2 : Recognition: MH01AX7946 52 .52 15 ANALYSIS OF RESULT Tests are conducted according to the modular form 15. the figure illustrate below lead to wrong recognition of the character. It is generally important when capturing the vehicle image. For instance.1 Recognition : D6LH4CNEB800 Fig 15.

imshow(imagen). This will result fail recognition of the vehicle license plate. figure. high contrast image. we can improve on the accuracy of capturing of vehicle image. 15. the binarized image do not allow to make the difference between the background and the digits. such as very dark image. low contrast image. we can make the difference between the digits and background inside the license plate. I have experience loosing out character when performing the extracting process. Fig 15.2 Vehicle Quantization and Equalization For some rare cases. Below illustrate a example of the scenario: Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen. we can also include an algorithm where we can change the image of the four coordinates to a standard rectangle size or manually crop the image. Next.53 To improve in the cropping of image. After much study the MATLAB toolbox syntax. To improve on the performance of the character recognition. 15. we have managed to make adjustment on the value and apply the skill of binary area open (BWAREAOPEN) in which help to remove the small object too.6000).3 53 . Equalization and quantization allow to obtain a gray scale image with improve contrast between digit and the background.3 Checking and Verification of the Statistic In the midst of trying out other car plate.

4 54 . figure.imshow(imagen).54 Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen. Fig 15.7000).

11.Convert RGB image or colormap to grayscale.Bwlabel . When you are finished sizing and positioning the crop rectangle. black and white are reversed.returns in num the number of connected objects found in BW.Bwareaopen . 2. Imcrop . Size . imcrop returns the cropped image 7. create the cropped image by double-clicking the left mouse button or by choosing Crop Image from the context menu. The Crop Image tool is a moveable. based on threshold. called the target image. 9. 5.computes the complement of the image. the pointer changes to cross hairs when you move it over the target image.Regionprops . 8.55 16 List of functions used 1. resizable rectangle that you can position interactively using the mouse.measures a set of properties for each labelled region.Morphologically open binary image (remove small objects).Global image threshold using Otsu's method. 6. You can move or resize the crop rectangle using the mouse. you specify the crop rectangle by clicking and dragging the mouse. When the Crop Image tool is active.returns the sizes of each dimension of an image in matrix a and b.creates an interactive Crop Image tool associated with the image displayed in the current figure. 3. zeros become ones and ones become zeros. 12. Imread : Read image from graphics file. or obtain information about open files. In the complement of a binary image. Using the mouse. 4. Rgb2gray . 55 .Performs median filtering of the matrix A using the default 3by-3 neighborhood. The output image BW replaces all pixels in the input image with luminance greater than level with the value 1 (white) and replaces all other pixels with the value 0 (black).Convert image to binary image. Im2bw . 10. Graythresh . Medfilt2 . Fopen . Imcomplement .Open file.

Imshow .draws a rectangle with Position [0. 22. 16.0.Largest elements in array. 17.0] (i. 23.Resize .1] and Curvature [0. 18.Isempty .e.Display image..Find .displays an array.Disp .Max.Write text to device.Find indices and values of nonzero elements.56 13.2-D correlation coefficient. 20. 19.Smallest elements in array.Determine whether array is empty. no curvature).Fclose . 21.Close one or more open files. 56 .Fprintf . 14.Corr2 .Rectangle .Min .1. 15.Resize image. without printing the array name.

txt'. % Show image figure.57 17 CODE 17. title('INPUT IMAGE WITHOUT NOISE') word=[].title('binary image').%Opens a text for append in order to store the number plates for log. image =~im2bw(image.1) rectangle('Position'.1 Algorithm to extract characters ( extractdigit.jpg'). % Remove all object containing fewer than 6000 pixels image = bwareaopen(image. [L num]=bwlabel(image). end % Convert to binary image threshold = graythresh(image).imshow(image).imshow(~image). propied=regionprops(L. disp(num).'g'.BoundingBox.2) end hold off pause (1) 57 .3)==3 % RGB image imagen=rgb2gray(image).%Storage matrix word from image fid = fopen('log.m).imshow(image).%pause(10).propied(n). image = medfilt2(image).'LineWidth'. pause(1) image = imcrop(image). % Show image binary image figure. image=imread('exp4. title('INPUT IMAGE WITH NOISE') % Convert to gray scale if size(image.'BoundingBox').'EdgeColor'.threshold). hold on for n=1:size(propied. 'at'). figure.6000).

m) function letter=read_letter(imagn) comp=[]. letter=read_letter(img_r).3 Algorithm to read letters (read_letter.date).m) function img_r=same_dim(imagen_g) img_r=imresize(imagen_g. word=[].'Number Plate:-%s\nDate:-%s\n'. fprintf(fid. word=[word letter].%s .txt file to see the stored number.imagn). n1=image(min(r):max(r). if vd==1 letter='A'. msgbox(sprintf('Number Plate Extraction successful.\nSee the log.min(c):max(c)). img_r=same_dim(~n1).word. 17.[42 24]). comp=[comp sem].c] = find(L==n).'.2 Algorithm of Normalisation of characters (same_dim. end vd=find(comp==max(comp)).58 figure for n=1:num [r. pause(0. elseif vd==3 58 .n}. load templates for n=1:36 sem=corr2(templates{1. 17. figure.'------------------------------------\n'). elseif vd==2 letter='B'. fclose(fid).\nExtracted Number plate:.'Extraction Success').imshow(~n1).5) end fprintf(fid.word).

elseif vd==14 letter='N'. elseif vd==11 letter='K'. elseif vd==6 letter='F'. elseif vd==7 letter='G'. 59 . elseif vd==21 letter='U'. elseif vd==4 letter='D'. elseif vd==18 letter='R'. elseif vd==5 letter='E'. elseif vd==8 letter='H'. elseif vd==19 letter='S'. elseif vd==13 letter='M'. elseif vd==9 letter='I'. elseif vd==23 letter='W'. elseif vd==12 letter='L'. elseif vd==15 letter='O'. elseif vd==10 letter='J'. elseif vd==20 letter='T'. elseif vd==17 letter='Q'.59 letter='C'. elseif vd==16 letter='P'. elseif vd==24 letter='X'. elseif vd==22 letter='V'.

elseif vd==33 letter='7'. elseif vd==35 letter='9'. elseif vd==34 letter='8'. %*-*-*-*-* elseif vd==27 letter='1'.60 elseif vd==25 letter='Y'. elseif vd==30 letter='4'. elseif vd==28 letter='2'. elseif vd==31 letter='5'. elseif vd==26 letter='Z'. end 60 . elseif vd==29 letter='3'. elseif vd==32 letter='6'. else letter='0'.

61 18 Result Analysis and Discussion 18.1 Experimental results Extracted Number plate: MH12EM2587 Extracted Number plate: MH12FF7461 Extracted Number plate: MH12DM3909 61 .

62 Extracted Number plate:LMH12CD9736 Extracted Number plate:LK00A53N6523 Extracted Number plate: MH12HN0389 62 .

the current results suggest that this capability is significantly overstated in actual road tests.63 Extracted Number plate: MH14CS7710 Extracted Number plate:MH12DE94 Extracted Number plate: MH01AX7946 18. but traffic volume and the design of Surrey streets may impede this read rate.2 Discussion Although ALPR technology has been promoted as being capable of reading in excess of 3.000 plates per hour. The initial analysis of parking lot data produced by Schuurman (2007) suggested that parking lot 63 . The technology may have the capacity to read more plates. Perhaps the most important conclusion reached from this study is that the utility of ALPR depends on volume.

in order to maximize efficiency. There are two main reasons why ALPR. the nature of hits was basically uniform for all of the assigned traffic corridors and the proportions held when considered by time of day or day of month. the fact that officers could expect several hits per hour requires the design of a response priority scheme and increase patrol units to manage the increased workload. until such time as ALPR-enabled vehicles have access to real-time data and there are many more ALPR-enabled police cruisers on the road at the same time. The likelihood of this scenario occurring is extremely low. Despite the promise that ALPR technology holds for catching stolen vehicles. for the most part. However. it may be possible. the frequency of hits exceeded what a typical patrol unit could respond to during a shift. substantiating which calls are valid and which must receive priority attention to lessen the burden on patrol officers. considering the results of this phase of the project. A large advertising campaign can inform the public about the nature and use of this technology which may result in the public being less willing to violate traffic regulations. the greater the number of raw hits. In both cases. as suggested above. Importantly. 64 . First. the hit list that the ALPR-enabled vehicle searched against was 24 hours old. Unfortunately. these statistics were not improved in the current analysis. for the most part. Rather. However. it may be more beneficial to use stationary cameras along a large number of intersections. Second. police forces operating ALPR technology may want to focus on high volume traffic corridors during the day shift. An important consideration raised by this research has to do with prioritizing responses and the allocation of scarce resources. as currently operated in Surrey. at least. In other words. this result should not have been unexpected. it was all about the number of hits. to train volunteers who can assist the police in filtering through database hits. the stolen car had to be on the road in Surrey. and. As a consequence.64 deployment was dependent upon the number of vehicles in parking lots and. If patrol officers are faced with a significant increase in the number of hits as a result ALPR deployment. was not effective in locating stolen vehicles. the more cars scanned. detachments must design response schemes to prioritize which hits officers respond to. along one of the four traffic corridors assigned for that day. and at the exact location where a moving ALPR-enabled vehicle could photograph its licence plate. for a stolen vehicle to be detected by an ALPR-enabled vehicle. the current study results also indicated that stolen vehicles represented a very small proportion (approximately one per cent) of all licence plate hits. at least 24 hours after the car had been stolen. the same conclusions applied to this road test of the technology. In effect. Given this. remove the variable of a roving ALPR which likely reduces success. if the objective is to identify stolen vehicles as this will. ALPR requires a meeting in time and space between the police cruiser and the stolen vehicle.

Increasing the height of the camera may avoid problems with objects (such as other vehicles) obscuring the plate but introduces and increases other problems. eliminating the problem).m file. usually because the plate is too far away but sometimes resulting from the use of a low-quality camera. A different font. such as the adjusting for the increased skew of the plate. this level of inaccuracy would not be acceptable in most applications of an ANPR system. This is because the likelihood of an unauthorized car having such a similar license plate is seen as quite small. Some small-scale systems allow for some errors in the license plate. "bike plates" are supposed to be fitted. While some of these problems can be corrected within the software. Poor lighting and low contrast due to overexposure. On some cars. though in some countries and jurisdictions. Blurry images. reflection or shadows. When used for giving specific vehicles access to a barricaded area. These include:        Poor image resolution. Circumvention techniques. For the future works and suggestion on improvements. it is able to detect and recognize some of the zoom in car vehicle license plate but fail on the image of cars with headlights. Lack of coordination between countries or states. such as Victoria. particularly motion blur. Bikes on bike racks can also obscure the number plate. 65 . Australia. When running the main. An object obscuring (part of) the plate. However. Two cars from different countries or states can have the same number but different design of the plate. or dirt on the plate. it is primarily left to the hardware side of the system to work out solutions to these difficulties. quite often a tow bar. popular for vanity plates (some countries do not allow such plates.65 19 Difficulties and Recommendations There are a number of possible difficulties that the software must be able to cope with. these are the steps which are recommended:  Modification is needed to be done on the offset of detecting the rectangular plate or by applying other technique to the system. the decision may be made to have an acceptable error rate of one character. tow bars may obscure one or two characters of the license plate.

 There should be improvement on the decision of the algorithm and ways to detect error. we can use RGB to HSV or RGB to CMY method to deal with other type of colour license plate. 66 .66  We only use the black and white image of the Vehicle license plate. For future implementation. When the probability of recognition guess is correct but falls below the threshold. the recognition system should refuse to make the decision.

we also encountered problems in detection. Next. After doing much research and absorbing more knowledge into MATLAB toolbox. research and with the help and understanding from the tutor. we chose MATLAB software as it is easier to implement.67 20 Critical Review and Reflection The development of the project is considered quite successful although we still faced some problems during the progress of the project we managed to solve the problem by doing more reading. The problem encountered during the progress of the project include the selection of suitable method such as : sourcing of car images. the problem encountered is the selection of software program. recognition of vehicle license plate characters. problems were resolved by using the suitable syntax and methods. segmentation. After doing much reading and research. methods on detection. 67 . method of segmentation and recognition of vehicle license plate character and writing of simulation program. During the initial project and development stage.

an officer‘s workload substantially increased. In other 68 . identified through experience. Most importantly. we presented application software designed for the recognition of car license plate. but to other calls for service. Finally it is proved to be %96 for the segmentation of the characters and %80 for the recognition unit accurate. This system can be redesigned for multinational car license plates in future studies. ALPR also offers an objectivity that may benefit police. it is highly plausible that through this process.57% recognition rates. with which to select those plates that appear more suspicious. increased police efficiency. officers may miss plates that are. While officers currently employ a set of indicators. then we separated the plate characters individually by segmentation and finally applied template matching with the use of correlation for recognition of plate characters. prohibited drivers. such as having an officer physically type in a licence plate to scan. ALPR has the ability to quickly and efficiently scan a large number of licence plates without any officer intervention. they are compelled to make a series of decisions concerning which plates to search. The ability of ALPR to scan a large number of plates allows for more plates to be scanned faster and more efficiently. detachment-specific schemes may need to be developed. Given that officers cannot check all the licence plates they encounter while on shift. officers could become overwhelmed by the increase in the number of problematic cars to respond to. The ALPR technology offers several benefits to police forces. however. namely. Research with ALPR has shown several benefits. and unlicensed drivers much more quickly than previous police strategies. Research in the United Kingdom suggested that in responding to the sheer number of hits identified through ALPR. With an increased number of ―hits‖. This system is designed for the identification INDIAN license plates and the system is tested over a large number of images. police are better able to identify more persons of interest. giving the overall system performance 92. As a consequence. With the potential for an increased number of hits. There are. However. or successful matching between a scanned plate image and a database of interest. in fact. police must develop strategies that enable officers to prioritize their responses. impeding their ability to efficiently respond not only to ALPR hits. The use of ALPR technology might also result in safer police driving as officers would no longer have the added distraction of turning away from the road periodically to manually type in licence plates of interest . untoward.68 21 Conclusion & Future Scope In this report. This increases the potential for the recovery of stolen goods as well as convictions. as the profile of crime is different in jurisdictions. some limitations inherent in the use of such advanced technology. The technology also allows the police to identify uninsured vehicles. Firstly we extracted the plate location.

2007). priority schemes may need to be individualized. and the motor vehicle branch. given current fiscal realities in many detachments in Canada. where police simply scan all plates until they get a hit. Citizens may equate the use of ALPR technology to ―fishing expeditions‖. depending on the geographic location of hotspots. such as insurance companies. However. and the specific needs of the community.69 words. Concerned citizens may accuse police or the government of using the technology to track law-abiding citizens. Moreover. the number of officers on patrol. lists are updated as cars or plates are reported stolen or it can be updated every 24 hours. without the successful coordination between police forces and agencies. e. In effect. drivers that have been prohibited or have lost their licence. Without the provision of data by which to compare scanned plates. some companies have begun to sell products to thwart the technology. Schuurman 69 . research suggested that the ALPR technology reads plates correctly 95% of the time. police forces may find it necessary to increase the number of officers on the road which. there will be those who develop the means to defeat these techniques. While advances in technology allow for the successful use of systems. in the event that a plate is not read correctly and the officer deems the plate suspicious. as the police develop new technologies. In the past. The efficiency of ALPR technology is entirely dependent upon the successful coordination of agencies. other criminal justice agencies. Lastly. it also provides new methods with which to avoid being screened by such technology. it is important that officers to retain the ability to investigate the plate more fully and to follow their instincts when observing a suspicious vehicle. those using ALPR technology must have access to data that details information about stolen plates or cars. such as licence plate recognition. vehicles that have been involved in other criminal activity. Yet. recognition software has produced extremely low successful recognition rates (Gordon and Wolf. For instance. Either way. ALPR technology simply will not succeed. to better respond to priority hits. Information can either be provided in real time. Much of the work involved in implementing ALPR technology involves building these initial relationships between agencies. 2007).g. Gordon and Wolf (2007) reported that since the advent of ALPR. Deisman (2003) identified that there are limits to the extent that police in Canada can engage in continuous and non-selective monitoring of citizens. as opposed to specifically searching out particular plates based on prior intelligence. Concerns in Canada already exist regarding the use of Closed Circuit Television (CCTV) systems in public (Schuurman. may not be feasible. They noted that one company sells a clear spray (US $30 per can) that the manufacturers claim can make licence plates invisible when read by a camera. privacy concerns are also a limitation to the use of ALPR technology. more recently. ALPR cannot possibly identify plates of interest. Again. invading their right to privacy. or drivers who are uninsured.

or yearly basis. In addition. smudges. extremely important that considerable thought is given to the safe storage of data and strict regulations regarding who has access to the databases. This work can be further extended to minimize the errors due to them. and thus make any firm conclusions on its general utility. The overriding benefit of ALPR is that it brings a far larger number of offenders to the attention of the police. further optimization is required. blurred regions & different font style and sizes are need to be taken care of. weekly. the issues like stains. Also. . monthly. Therefore to achieve this. therefore. there may be concerns regarding who has access to this data . ALPR does have a specific utility as its strategic deployment will assist police departments to more effectively response to a variety of auto and driving-related offences. However. It is. Citizens may fear the potential for breaches in security. the results of this study suggest that ALPR technology offers several substantial benefits to the police. Still. more research needs to be conducted in order to determine how ALPR technology can be balanced with respect to citizens right for privacy and civil rights. policies may be put in place that regulate the deleting of collected data on a daily. In responding to concerns of privacy.70 (2007) also noted that the Canadian Charter of Rights and Freedoms states that privacy rights of citizens are breached by indiscriminate video surveillance without cause. it is required that for the task as sensitive as tracking stolen vehicles and monitoring vehicles for homeland security an accuracy of 100% cannot be compromised with. although further research is needed to determine the extent to which ALPR increases the rate of arrest and has a deterrent effect. How to adequately respond to this situation will require careful thinking and planning on the part of the police. Citizens may also have concerns with respect to the maintenance of data in warehouses. 70 . Essentially. In conclusion. it is difficult to assess the impact of ALPR on police resources and workloads. Future Scope Though we have achieved an accuracy of 80% by optimizing various parameters. rather than the few offenders the police are able to find during their routine activities.

Thus. Task 3 Construct Matlab software for simulation (24 Feb 2012 to 20 Mar 2012)  Writing and create algorithm for extraction of vehicle license plate character  Writing and simulate the block by integrating all the written algorithm together  Version R2008a for editing. we have drafted out the project schedule to follow up closely. 71 . There is interconnected link between the research work and the designing and Implementation process.71 Annexure A: Project Plan & Progress Report For developing the project.  Fine tuning of the integrated block algorithm Task 5 Reporting Writing (28 April 2008 to 1 May 2012)  Allocate at least 1 week for writing the final report. Task1 Research (24 Jan 2012 to 10 Feb 2012)        Research on various methods used for Vehicle License Plate Recognition Conversion of Images Image Thresholding Noise filtering Vehicle License Plate Detection Vehicle License Plate Extraction/Segmentation Vehicle License Plate Recognition Task 2 Development (11 Feb 2012 to 23 Feb 2012)  Determine the value of pixel need for filtering  Determine algorithm for plate detection  Determine algorithm for extraction/segmentation  Determine algorithm for plate recognition. it is important to choose the type of model and syntax that are suitable for Matlab is taken into consideration. Task 4 Testing and Fine Tuning (30 March 2012 to 24th April 2012)  Fine tune on the filtering and calculation of connected components.

Richard E. Gonzalez and Richard E.Hopgood.72 References  Rafael C. Eddins. LICENSE PLATE RECOGNITION TECHNOLOGY (LPR) IMPACT EVALUATION AND COMMUNITY ASSESSMENT . Woods and Steven L.  CYNTHIA LUM.  Dr. Dr.com/access/helpdest/help/techdoc/mathlab_product_page2. ― International Edition Digital Image Processing Second Edition‖  John C. Gonzalez. Darryl Plecas. LINDA MEROLA.Edward B.ht ml  Matlab software version R2008a. and Amanda V. Cohen. Author ONDREJ MRTINSKY  Lecture notes  Mathworks. ―Introduction To Matlab 7 For Engineers  Magrab. ―The Image Processing Handbook‖  Adrian A.  Mathworks. Irwin M. It is a very user friendly device as it will guide and explain to us on the specific toolbox in which we will be using. Russ.ht ml#printable_pdf. Palm III.‖Intelligent Systems for Engineers and Scientists‖  William J. A Report on the Utility of the Automated Licence Plate Recognition System in British Columbia 72 . McCormick SCHOOL of CRIMINOLOGY and CRIMINAL JUSTICE University College of the Fraser Valley. Center for Evidence-Based Crime Policy. JULIE WILLIS. AND BREANNE CAVE . George Mason University . Woods.com/access/helpdesk/help/toolbox/nnet/nnet_product_page.‖An Engineer‘s Guide To Matlab‖  ALGORITHMIC AND MATHEMATICAL PRINCIPLES OF AUTOMATIC NUMBER PLATE RECOGNITION SYSTEMS. ―Digital ImageProcessing using MATLAB‖  Rafael C.

anpr.‖ IEE Colloquium on Electronic Image and Image Processing in Security and Forensic.platerecognition.  R. Test and Applications ( DELTA‘02 ). M. 1990.035. 1990. Johnson.wikipedia. February 16. Helmholt. Aprl.G.M.info/ 73 .S. Proceedings of First IEEE International Workshop on Electronic design. IEEE Computer Society.A. K. 1995. Yang ―Test bed for number plate recognition applications‖. pp.W. 1990. Lim and L.  M. ―Automatic NumberPlate Recognition. J. ―Car License Plate Automatic Vehicle Identification by Plate Recognition Author .org/wiki/Vehicle_registration_plates_of_India  http://en. Morgan.org/wiki/Automatic_number_plate_recognition  http://www.S. Ter Brugge. 1990.D. Nijhuis.‖ Proceedings of the IEE Colloquium on Image analysis for Transport Applications. B. 2002.Serkan Ozbay. 3 1 Aug-2 Sept. A. 1994. Pluim.G. M. ―Number-plateMatching for Automatic Vehicle Identification. Johnson. Lotufo. ―Automatic Number-plate Recognition : Neural Network Approach. Bird. Bailey.net/  http://www. V01. and AS.A. Fahmy. Irecki. B.  http://en.A. L.wikipedia.K. D.  A. and Ergun Ercelebi.6/1-6/6. Spaanenburg.M. R.M.H.73  D. Westenberg.A.‖ Proceedings of VNIS‘94 Vehicle Navigation and Information System Conference.P. 1994  J. Venema.

74 74 .