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

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

______________________________________ 2. Examiners: 1.5 The Project entitled “LICENSE PLATE RECOGNITION SOFTWARE” By Abhinandan Singh . Pune.08070121232 Is approved for the degree of BACHELOR OF ENGINEERING – Electronics & Telecommunication Symbiosis International University. _______________________________________ Date : Place: 5 .08070121224 Pathikrit Guha .08070121202 Mayank Kishore .

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

1 Introduction to matlab 4. Algorithm 8.1 Project Background 3. 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 .2 Image Processing 4. 8.3 Objectives 3.2 Conversion of RGB Images to Binary Images 7 Page no.4 Constraints 3.4 Segmentation 8.6 Save to file in given format Chapter 9.5 Various Types of Vehicle License Plate 3.1 Algorithm for ANPR system 8.1 Problem Statement 2.7 Table of Contents Contents List of Figures Abstract Chapter 1. Introduction 3.2 Features of project Chapter 3.1Image Cropping 9. 8. Literature Survey Chapter 2.5 Number identification 8. Imaging Hardware Chapter 7.2 How the Vehicle License Plate System works 3.3 Convert image into binary. Problem Definition 2.3 Comparison Between MATLAB and Artificial Intelligence Chapter 5. Image Acquisition 9.2 Input Image from file.6 Commercial Products Chapter 4 Platform / Technology 4. Development History Chapter 8. Components Chapter 6.

2 Vehicle Quantization and Equalization 15.1 Extracting of Individual Digits 15.8 9.3 Filtering of Digits 12.2 Binary Area Open(Bwareaopen) 12.3 Checking and verification of the Static Chapter 16 List of Functions Used Chapter 17 Code 17.1 Normalization 14.3 Colour Image Processing Chapter 10.1 Experimental results 18.2 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 .2 Database Chapter 14 Character Recognition 14.1 Filtering 12.2 Algorithm to normalisation of characters 17.2 Template Matching Chapter 15 Analysis of Result 15. Image Enhancement 10.1 Algorithm to extract digits 17.3 Algorithm to read characters Chapter 18 Result Analysis 18.2 Medfilt2 Chapter 11 Thresholding 11.1 Feature Extraction from Digital Image 13.2 Global Thresholding 11.1 Threshold Selection 11.1 Imcomplement 10.3 Adaptive thresholding Chapter 12 Image Noise 12.4 Identify and remove away the small connected objects Chapter 13 Image Segmentation 13.

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 .

..................................................2 Captured image of vehicle2...........38 9.....39 9.....3 Characteristic function of binary image.............53 15....................5 Histogram of object and background which is close..................................1 Binary image with noise.................................1 Comparison of MATLAb with other softwares........................................48 13............................................53 15.....................................................................................................................................................................2 Block diagram of Image processing system........................................................................................18 3..........................41 9..............17 3.........................4 Histogram of light object with dark background....41 12............................37 9....47 12.............20 4..2 Cropped image of the vehicle......................................55 10 ......................................................................................................19 3.............39 9.....1 Automatic Number Plate Recognition System.....................................2 Binary image after filtering.......................................................................................3Morphologically open binary image.........................7 Captured image of the vehicle...................................................25 8................1 Original image of the vehicle.........37 9........1 Segmented image............5 Commercial and Private vehicle license plate......................................................................40 9.................................4 Morphologically open binary image............24 4..................................................2 A car approaching a License Plate Recognition System........3 Indian car license plate...................................50 15.4 System Block Diagram............................................1 Overview of the vehicle license plate system.6 RGB schematic block diagram...8 Binary image of the vehicle...............................16 3...1 Captured image of vehicle1.........................10 List Of Figures 3.....................36 9...........................................54 15..........

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

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

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

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

15 3 INTRODUCTION 3. For example.2 How the Vehicle License Plate System works Firstly. such as parking. Automatic number plate recognition systems can be used in access control. Automatic Line Tracking Robot (ALR) is used in this project as a vehicle which contains circuitry for moving in a guided track. 3. This can be achieved by a human agent. the vehicle will stop at the car gantry. It will activate a signal to the Vehicle License Plate System of the presence of the vehicle. vehicles can be directed to different lanes for a better congestion control in busy urban communications during the rush hours. In some countries. number plate is automatically recognized and stored in database and black-listed number is not given permission. When a vehicle enters an input gate. In entrance gate. ANPR systems installed on country borders automatically detect and monitor border crossings. various recognition techniques have been developed and number plate recognition systems are today used in various traffic and security applications.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. access and border control. 15 . It will have mechanism to detect the opened and closed door. 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. 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. . number plate is recognized again and paired with the first-one stored in the database and it is taken a count. In traffic control. Vehicle License Plate Recognition is an image processing system whereby it is used to recognize the vehicles by identifying the license plate. Because of this. The cycle will start when the vehicle steps over the detector. It also will have capacity to park in the given parking area. When a vehicle later exits the place through the gate. or tracking of stolen cars. there was also a need to transform information about vehicles between the reality and information systems. this technology is used in many companies to grant access only to vehicles of authorized personnel.

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

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

due to the limited time frame given. we have to set a list of constraints to make the project more systematic and manageable. Try on zoom in image of the car and image consists of headlamp. 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.4 Constraints Due to limited time that we possess and dealing with image vision software. The constraint is listed as below:           Image taken only when vehicle is stationary. Deal with only Indian Car License Plate with Times new roman font. There will be no motion capture image. Take only the front view image of the car. Captured images on location where light is proportional. Thus. Thus. 3. it is not advisable for me to cover all aspects in this project. Captured image of vehicle at fixed distance. Captured image of vehicle at fixed angle. it is not advisable to include all of the possible cases.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. There is definitely a lot more room for further improvement on this project. However. The image should be taken with the height of 50cm to 70 cm above the ground level. in discussion with my tutor. Fig 3.3 18 .

4 19 .19 System block Diagram Fig 3.

 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.g. 22 UN 14). A letter(s) is prefixed when the 4 digit number runs out and then two letters and so on.  Format Vehicle owner who register the car as private vehicle have a white background and black text..g. Fig 3. The next two digit numbers are the sequential number of a district. The President of India and state governors travel in official cars without licence plates. Instead they have the Emblem of India in gold embossed on a red plate. Due to heavy volume of vehicle registration. DL 2C 0001).20 3. The third part is a 4 digit number unique to each plate. 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. Vehicles belonging to foreign consulates have white lettering on a light blue background (e. Commercial vehicles such as taxis and trucks have a yellow background and black text (e. the numbers were given to the RTO offices of registration as well.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. 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.5 20 .

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

7 days a week.6. easy installation and has accessories and features for most parking security surveillance needs.6. 3. uses video imaging for better recognition. combined template and neural network recognizers. It is a high performing robust system that gives consistent results under all weather conditions.3 Vehicle Identification System for Parking Areas (VISPA) PPI's Vehicle Identification System for Parking Areas (VISPA) [28]. however. • Reads accurately in most weather conditions. 3. • Automatic and within milliseconds. With milliseconds the LPR system locates. 3. VISPA provides for state-of-the-art video technology.22 3.6. it automatically locates vehicle license plates and reads the numbers accurately each time every time. Features of this LPR technology includes. fuzzy logic and an arsenal of image processing tools. 22 .2 Perceptics Perceptics [27] is the world leader in license plate reader technology. • Reads accurately at highway speeds.6 Commercial Products The various products in the market today are described briefly below. • Works 24 hours a day. Using advanced image processing and artificial intelligent techniques such as AI best first breadth-wise search algorithm. 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. captures and identifies a vehicle's license plate data and makes a read decision. Current LPR system read Latin (A-Z) and Korean (Hangul) letter and Arabic number (09).1 IMPS (Integrated Multi-Pass System) An IMP [26] is a Singaporean commercially developed license plate recognition system. identification and improved security. The system's reliability and flexibility allow it to accommodate some of the most stringent needs in some of the worst conditions.

Available as complete systems. • Compatible with standard hardware and software. or to a client process. the system read the camera images and extract the identification data from the images. The recognition result is then logged together with the images. such as SeeGate . SeeCar License Plate Recognition:. as a stand-alone turn-key version. or SeeCrane . Available as a complete system which is based on a background Windows application. VISPA is available in two forms Basic Version: .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. and transmits the ID string to the port or gate computer. There technology is based on computer vision.crane mounted Container recognition system. 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. 23 . Enhanced Version:.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. 3. or in form of different special-task systems. SeeContainer Identification System:. 8. There product includes. The license plate can then be encoded on the ticket. The image will be linked to the ticket. access control.a recognition system for the Tracks and Containers.License Plate Identification.23 Features are • Open architecture to most common video-systems.6. The VISPA controller with an integrated frame grabber card for 4.Tracks and reads Shipping container identification marking.Detects and reads Vehicle license plates for parking. or 16 cameras automatically identifies the license plate from the video image and stores it in a database. law enforcement and security applications. This is the main advantage of vision based recognition. traffic surveillance. • Can be customized according to specific user needs. Windows DLL or Linux library.

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

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

2. Algorithm used in MATLAB can be converted to use in hardware. 3. 5. 3.  Disadvantage of Artificial Intelligence: 1. MATLAB possess power graphic visualization tools. There are difficulty in getting expert knowledge and putting it in used in the system. Expensive. The system will perform faster when using “Matrix Approach”. Data can be represented in terms of matrices or vectors. MATLAB coding is shorter and simpler. We can changed and add individual rules. Unpredictable. 2. Slow response.  Advantage of MATLAB 1. 2.3 Comparison Between MATLAB and Artificial Intelligence  Advantage of Artificial Intelligence: 1. 3. Non-programmers can easily understand the rules of artificial intelligence. Not good in common sense reasoning. 26 . 4. .26 4. 4. 5. Good for solving complex problems where humans or programmer have expert knowledge in it.

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

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

a British company operating a premier global marketplace for shipbrokers and charterers. ALPR technology was developed at Cambridge University in the United Kingdom in response to terrorism. if it had been involved in another crime. The blast caused approximately £1 billion in damage. the databases. the Irish Republican Army bombed the Baltic Exchange. 2006). the Irish Republican Army detonated a truck bomb at Bishops gate. 2003). Instead. killed one person. the heart of London‘s financial district (1993 Bishops gate bombing. is stored at the National ANPR1 This term is synonymous with ALPR and will be used interchangeably 3 Data Center (NADC) in London. the patrol officer is provided with information regarding the vehicle. 29 . and police forces were provided with computers that were able to store ANPR information in real time (Pughe. there are 3. 2006). 2008).29 7 Development History The United Kingdom: In 1992. 1993. officers were able to spend more of their time investigating hits. On April 10. a JPEG image of the plate is produced. and injured 44 others. NADC stores plate data and lists of suspect vehicles (Pughe. This resulted in an increase in arrests to 100 per year. The central ANPR system. 2006). 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. or if it was uninsured (Pughe. the United Kingdom evaluated the use of ANPR with nine police forces. The bombing was massive in size and destroyed several buildings with many others suffering shattered windows. scanning up to 5 million plates a day (Pughe. and the GPS location of the camera is created.e. the time and date of the scan. When a plate is photographed by an ANPR camera. As a part of its intelligence network. As of 2001. partially destroying the façade of the Exchange‘s offices and extensively damaging the rest of the building (Baltic exchange. Almost a year later on April 24. 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. The United Kingdom is at the forefront in the use of plate recognition technology. stationary (roadside) and mobile (mounted on police cars). Approximately four seconds after a plate is read by the camera. 2008). i. 2006). as well as a video image of the plate and a video of the vehicle occupants (Pughe. a text file containing information on the car registration number. 1992. In addition. 2006). such as whether the car was stolen. 10 times the national average (PA Consulting Group.000 cameras across the United Kingdom. In 2002 to 2003.

three instances involving the recovery of other stolen goods (equivalent to approximately 23. or prohibited drivers. This initial study also provided the Home Office with descriptions of the quantity of vehicles on the road violating insurance or other traffic regulations. 2006). volume crime. enforced an arrest). workload concerns continued to exist. uninsured.8% of arrests were made for theft or burglary offences. the data also highlighted the limited ability of the intercept teams to respond to the volume of hits they received. For instance. however. The results of this evaluation also demonstrated that the ANPR technology contributed to a substantial increase in arrests (Pughe. an average. seven instances of drug seizures (equivalent to approximately 3. and the number of vehicles owned or operated by persons of interest (PA Consulting Group. the Hampshire Constabulary uses ANPR to prevent and detect terrorism. Currently. two seizures of weapons and/or firearms. equivalent to approximately one stop per hour.499 arrests. 2004). One-quarter of the arrests were for disqualified. In nearly two-thirds (61 per cent) of these stops. no date). In total. police were only able to respond to 13% of hits (PA Consulting Group. and 8. 2003). In effect. A second evaluation was conducted between June 2003 and June 2004 with 24 police forces (PA Consulting Group. The results of this study were similar to the first study. the number of vehicles used in the commission of other criminal offences.30 In total. However. 2007). 30 .3% for theft of or from a vehicle. ANPR was beneficial to police forces by providing better efficiency in the deployment of officers. and fatal and serious injury road traffic accidents (Hampshire Constabulary. 2003). serious crime. A further 16. In 2005 and 2006. The Metropolitan Police Service operates four ANPR units who work across London.000 stolen vehicles were recovered over this period (PA Consulting. 2004). the intercept team took some action (e. approximately one out of every 200 cars photographed by the ANPR cameras was stopped by an ANPR intercept team. 200 arrests per month (Metropolitan Police Service. and five instances of recovery of other stolen property (PA Consulting Group.300 pounds total). 180. There are deployment teams who are used to assist in targeting hot spots for vehicle and other crime. Over this one year period. 2003). a constable using ANPR technology could expect to encounter: the recovery of 11 stolen vehicles (equivalent to approximately 68. on average. arrests were made in nearly 4-8% of the vehicle stops. In effect.000 pounds).2% for drug offences. again suggesting a need for policy outlining a response priority scheme.000 pounds total). over 1. ANPR technology continues to be used across the United Kingdom.543 vehicles were stopped by intercept teams resulting in 13. 10.g. these units made. The results also indicated that the police could expect a substantial increase in the amount and value of goods they recovered. On an annual basis.

More recently. in several jurisdictions. 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. which use Automatic Number Plate Recognition (ANPR) technology. The US has also used plate recognition technology at border crossings with Mexico and Canada to track auto theft (Canadian Press NewsWire. The London congestion charge is an example of a system that charges motorists entering a payment area. The United States Over the past several years. This technology will also be used.500 cameras. Both front and back number plates are being captured. In 2007. There are also a number of mobile camera units which may be deployed anywhere in the zone. Fines for traveling within the zone without paying the charge are £60 per infraction if paid before the deadline. doubling to £120 per infraction thereafter. 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. 150 American cities utilized this technology to catch those who drove through red lights.m.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. 2007). A recent study of ALPR technology in the state of Ohio emphasized 31 . It is estimated that around 98% of vehicles moving within the zone are caught on camera. A second data centre provides a backup location for image data.m. ALPR has been used to track potential terrorists. Monday to Friday. These offenders have a photograph taken of their plate by the ALPR cameras and receive a ticket in the mail. Transport for London (TfL) uses ANPR systems and charges motorists a daily fee of £10 paid before 10pm if they enter. leave or move around within the congestion charge zone between 7 a. primarily in the form of ―red light cameras‖ (Jenkins. The registered owner of such a vehicle is looked up in a database provided by the DVLA.. and 6:00 p. 2006). A reduced fee of £9 is paid by vehicle owners who sign up for the automatic deduction scheme. There are currently 1. The video streams are transmitted to a data centre located in central London where the ANPR software deduces the registration plate of the vehicle. to catch drivers who violate speed limits (Jenkins. the United States has also introduced plate recognition technology. 2007).

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

Of these. and stolen cars (1. 2007). Over the course of this study. Given that there is limited information available to date on the use of ALPR technology. In fact. uninsured drivers. Schuurman (2007) concluded that the deployment of ALPR technology exclusively to parking lots would not be the most efficient use of the system.33 the Canadian Police Information Centre (CPIC) and the Motor Vehicle Branch (MVB). research must be conducted to determine the extent to which such technology is useful to Canadian police forces. one unmarked patrol vehicle drove through 31 Surrey parking lots scanning the licence plates of parked cars over the period of one week.8 per cent). uninsured) vehicles (23.7 per cent) of the scans accurately captured the car‘s licence plate. and over two-thirds (69. Such research can be used to inform deployment strategies. especially to locate and recover stolen vehicles. Schuurman‘s (2007) results indicated that 1. 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). 21. for example. 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. prohibited drivers (4. four hits every hour (Schuurman. on average. 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. Scanned plate images were compared to the CPIC and MVB databases. there were. nearly all (97.6% of scanned plates resulted in a ‗hit‘. and stolen vehicles. To collect the data for this initial study.876 licence plates were scanned. 33 . The Hot Lists were for unlicenced vehicles.e. Canada.8 per cent) of hits were for unlicenced drivers. The current study intends to provide some initial data regarding the use of ALPR technology in British Columbia.9 per cent). prohibited drivers.4 per cent). Nearly three-quarters (72 per cent) of the hits occurred between 3pm and 7pm.

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

As the license plate surrounding is of no importance. webcam etc can be used to capture the acquired images. Next. 9. this cropping process will highly increase the speed of image processing. we might proceed in using the Matlab function to convert the vehicle JPEG image into gray scale format. vehicle images will be taken with a Panasonic FX 30 digital camera. Electronic devices such as optical (digital/video) camera.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. The images will be stored as colour JPEG format on the camera.2 : Cropped Figure 37 .1: Original Image Fig 9.37 9 Image Acquisition The initial phase of image processing for Vehicle License Plate Recognition is to obtain images of vehicles. For this project. The figure below shows the copping of image: Fig 9.

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

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

The schematic of the RGB cube that illustrate both the primary and secondary colour at each vertex is shown below.40 In this circumstance. The cube vertex consists of the primary colour (Red. The colour space is normally graphically shown as RGB colour cube. 9. 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. Green and Blue) and the secondary colour (Cyan.6 40 . Magenta and Yellow).3 Colour Image Processing RGB Colour Space The RGB image is made of colour pixels of an M x N x 3 array. Fig 9.

8 : Binary mage 41 .7 : Original Image Fig 9.41 Fig 9.

The pixel value obtained by the differences will be used in the output image. Therefore. reducing noise. A median filter is more effective than convolution when the goal is to simultaneously reduce noise and preserve edges. the light areas will become darker and the darker area will become lighter. IM can intensity. For the complement binary image. contrast manipulation. zeros will become ones or ones will become zeros. binary or true color image. For the complement of the true color image. 10. 10.2 MEDFILT2 Median filtering is a nonlinear operation often used in image processing to reduce "salt and pepper" noise.42 10 IMAGE ENHANCEMENT The aim of this process is to increase and improve the visibility of the image.1 IMCOMPLEMENT Imcomplement will compute the complement image(IM). Image Enhancement techniques consists process of sharpening the edges image. 42 . color image processing and image segmentation as well. black will becomes white and white will be come black . the value of each pixel will be subtracted by the maximum pixel value which is supported by the class.

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

n)>T} (object pixels) 2.44 2. This is a common reason why global thresholding fail. its can solve the disadvantages of the global thresholding as it computes the value of the threshold for every pixel separately using the neighborhood..n) is the value of the pixel located in the mth column. This iterative algorithm is a special one-dimensional case of the k-means clustering algorithm. G1= {f(m. m2= average value of G2 4. nth row) 3. 11. m1= average value of G1 2. keep repeating until the new threshold matches the one before it (i. 44 . the value of the threshold will be taken in the middle of the bimodal. For other cases. 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. If the histogram is bimodal. 11. 1.e. which has been proven to converge at a local minimum— meaning that a different initial threshold may give a different final result. The image is segmented into object and background pixels as described above. By using the adaptive thresholding.n):f(m. the threshold will try to reduce the error of taking the background pixels as object pixel and vice versa. A new threshold is created that is the average of m1and m2 1.n) T} (background pixels) (note. T‘ = (m1+m2)/2 5. G2= {f(m. The value of the gray level varies from the darkest (0) to the brightest (255).n):f(m. Image is form up of square matrixes called pixels and each pixels in the image have a brightness level known as gray level. creating two sets: 1. Go back to step two. in which the modes are overlapping. until convergence has been reached).2 Global Thresholding This is a method whereby the histogram of the image is being partitioned using a single threshold value. The threshold defines the value of the gray level in which the baseline boundary is in between the foreground pixels and the background.3 Adaptive Thresholding The vehicle number plate can be partially illustrated. The average of each set is computed. f(m. now using the new threshold computed in step four.

We will be enlarging the signal from the received light photons when we are using the digital camera with a higher ISO setting. The syntax is as bellowed: BW2 = bwareaopen(BW. we have managed to obtain the black and white image of the Vehicle License Plate. Next. 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. 12. Thus. it will reproduce another binary image. 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. filtering process is used for blurring and for noise reduction and thus resulting a more sharpen image. From the amplification of the signal. In this circumstance. we need longer time for the image sensor for collection of weak signal. blurring with liner/non liner filter is able to achieve noise reduction. It has been cropped to a rectangular shape in which it enhances the algorithm to be more uniformed in the further stages.1 Filtering In this pre-processing stage. bridging of gaps in curves and lines. In order to reduce the background noise.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. 12. softening is often applied to the low pass filter and it will affect the image to become blurring. Noise in the images is appears as the colour speckles whereby there should not be any.45 12 IMAGE NOISE Digital camera with long exposure time setting and high ISOs will produced images with lots of noise. 45 .3 FILTERING OF DIGITS Now. the electrical noise in the background is also being amplified. 12. the electrical noise from the background will be higher than the signal.P). We can apply convention techniques such as softening and sharpening.

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

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. Therefore. in which it will produce another binary image. 47 .2 : Binary Image after Filtering. components with less than 6000 is classify as non digits components and need to be taken away. Next.47 Fig 12.

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

contents and images. thus it can be accessed easily and updated. Database can be in the form of text.2 Database It is a collection of information or data which it is being orderly organize. It will ignore the class if the image thresholding is too low. The database would be enlarged in order to improve the accuracy and better chances of obtaining the correct result.1 13.49 Plotted Bounding Box Fig 13. 49 . 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. If the class has match correctly. it will be compare with data set in the database and provide an output if the image is recognized correctly. The class recognition will check if the computed ratio is correct.

14.2 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.2.50 14 Character Recognition 14.v). Unfortunately the normalized form of correlation (correlation coefficient) preferred in template matching does not have a correspondingly simple and efficient frequency domain expression. An algorithm for obtaining normalized cross correlation from transform domain convolution has been developed. 14. For the project. The new algorithm in some cases provides an order of magnitude speedup over spatial domain computation of normalized cross correlation. For this reason normalized cross-correlation has been computed in the spatial domain.y under the window containing the feature t positioned at u. Due to the computational cost of spatial domain convolution.1 Cross Correlation The use of cross-correlation for template matching is motivated by the distance measure (squared Euclidean distance) .1 Normalization In this phase. 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. (where f is the image and the sum is over x. In the expansion of d2 50 . 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. several inexact but fast spatial domain matching methods have also been developed. see Lewis . the extracted characters are resized to fit the characters into a window.

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 the term is constant. 51 .

the figure illustrate below lead to wrong recognition of the character. It is generally important when capturing the vehicle image.52 15 ANALYSIS OF RESULT Tests are conducted according to the modular form 15.1 Recognition : D6LH4CNEB800 Fig 15. For instance. Fig 15.1 Extracting of Individual Digits Determine the angle of the Vehicle License Plate.2 : Recognition: MH01AX7946 52 .

I have experience loosing out character when performing the extracting process.2 Vehicle Quantization and Equalization For some rare cases. 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. high contrast image. 15. 15.53 To improve in the cropping of image. Next. To improve on the performance of the character recognition. the binarized image do not allow to make the difference between the background and the digits. low contrast image.imshow(imagen). Below illustrate a example of the scenario: Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen. we can improve on the accuracy of capturing of vehicle image. we can make the difference between the digits and background inside the license plate. This will result fail recognition of the vehicle license plate. Equalization and quantization allow to obtain a gray scale image with improve contrast between digit and the background. figure. 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. After much study the MATLAB toolbox syntax.3 Checking and Verification of the Statistic In the midst of trying out other car plate.3 53 .6000). Fig 15. such as very dark image.

Fig 15.4 54 .7000).54 Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen.imshow(imagen). figure.

12. You can move or resize the crop rectangle using the mouse. imcrop returns the cropped image 7.creates an interactive Crop Image tool associated with the image displayed in the current figure.returns in num the number of connected objects found in BW. create the cropped image by double-clicking the left mouse button or by choosing Crop Image from the context menu.Bwareaopen . 2. Rgb2gray .Morphologically open binary image (remove small objects).Bwlabel . or obtain information about open files.Regionprops . Im2bw . When you are finished sizing and positioning the crop rectangle. Imcomplement .computes the complement of the image. 4. Size . 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). 55 . Fopen .Open file. 9. the pointer changes to cross hairs when you move it over the target image. The Crop Image tool is a moveable. 3.returns the sizes of each dimension of an image in matrix a and b. 11.55 16 List of functions used 1. Imcrop .measures a set of properties for each labelled region.Convert image to binary image. 6. 10. black and white are reversed. Imread : Read image from graphics file. 5. based on threshold. In the complement of a binary image. Using the mouse. 8. you specify the crop rectangle by clicking and dragging the mouse. zeros become ones and ones become zeros.Global image threshold using Otsu's method. resizable rectangle that you can position interactively using the mouse. Graythresh . When the Crop Image tool is active.Convert RGB image or colormap to grayscale. called the target image.Performs median filtering of the matrix A using the default 3by-3 neighborhood. Medfilt2 .

draws a rectangle with Position [0. 23. without printing the array name.Close one or more open files.Corr2 .Disp . 16.Largest elements in array.2-D correlation coefficient.Determine whether array is empty. 15.1.1] and Curvature [0.Resize image.Write text to device.Rectangle . 56 . 17..Max.Smallest elements in array. 20.e.Resize .displays an array.0] (i.Fclose . 22. 21.56 13.Isempty .Find indices and values of nonzero elements. 18.Min .Imshow .Find .Fprintf .Display image. 14. no curvature).0. 19.

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

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

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

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

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

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

000 plates per hour. but traffic volume and the design of Surrey streets may impede this read rate. Perhaps the most important conclusion reached from this study is that the utility of ALPR depends on volume. 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. The technology may have the capacity to read more plates. The initial analysis of parking lot data produced by Schuurman (2007) suggested that parking lot 63 .2 Discussion Although ALPR technology has been promoted as being capable of reading in excess of 3.

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

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

For future implementation.66  We only use the black and white image of the Vehicle 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. When the probability of recognition guess is correct but falls below the threshold. 66 . the recognition system should refuse to make the decision.

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

In other 68 . The ALPR technology offers several benefits to police forces. police are better able to identify more persons of interest. namely. but to other calls for service. they are compelled to make a series of decisions concerning which plates to search. Most importantly. While officers currently employ a set of indicators. increased police efficiency. impeding their ability to efficiently respond not only to ALPR hits. This increases the potential for the recovery of stolen goods as well as convictions. This system can be redesigned for multinational car license plates in future studies. it is highly plausible that through this process. such as having an officer physically type in a licence plate to scan. and unlicensed drivers much more quickly than previous police strategies. With an increased number of ―hits‖. Finally it is proved to be %96 for the segmentation of the characters and %80 for the recognition unit accurate. There are. 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 . then we separated the plate characters individually by segmentation and finally applied template matching with the use of correlation for recognition of plate characters. untoward. The technology also allows the police to identify uninsured vehicles. some limitations inherent in the use of such advanced technology.68 21 Conclusion & Future Scope In this report. we presented application software designed for the recognition of car license plate. Given that officers cannot check all the licence plates they encounter while on shift. However. or successful matching between a scanned plate image and a database of interest. As a consequence. an officer‘s workload substantially increased. Research with ALPR has shown several benefits. officers may miss plates that are. detachment-specific schemes may need to be developed. in fact. officers could become overwhelmed by the increase in the number of problematic cars to respond to. This system is designed for the identification INDIAN license plates and the system is tested over a large number of images. with which to select those plates that appear more suspicious. police must develop strategies that enable officers to prioritize their responses. giving the overall system performance 92. With the potential for an increased number of hits. prohibited drivers. The ability of ALPR to scan a large number of plates allows for more plates to be scanned faster and more efficiently. Research in the United Kingdom suggested that in responding to the sheer number of hits identified through ALPR. Firstly we extracted the plate location.57% recognition rates. ALPR has the ability to quickly and efficiently scan a large number of licence plates without any officer intervention. identified through experience. as the profile of crime is different in jurisdictions. ALPR also offers an objectivity that may benefit police. however.

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

therefore. 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. Essentially. smudges. Still. the issues like stains. there may be concerns regarding who has access to this data . although further research is needed to determine the extent to which ALPR increases the rate of arrest and has a deterrent effect. and thus make any firm conclusions on its general utility.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. monthly. rather than the few offenders the police are able to find during their routine activities. It is. In responding to concerns of privacy. Citizens may fear the potential for breaches in security. Therefore to achieve this. . or yearly basis. However. policies may be put in place that regulate the deleting of collected data on a daily. 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. 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. In conclusion. In addition. Future Scope Though we have achieved an accuracy of 80% by optimizing various parameters. This work can be further extended to minimize the errors due to them. Citizens may also have concerns with respect to the maintenance of data in warehouses. weekly. extremely important that considerable thought is given to the safe storage of data and strict regulations regarding who has access to the databases. Also. 70 . it is difficult to assess the impact of ALPR on police resources and workloads. The overriding benefit of ALPR is that it brings a far larger number of offenders to the attention of the police. blurred regions & different font style and sizes are need to be taken care of. the results of this study suggest that ALPR technology offers several substantial benefits to the police. further optimization is required. How to adequately respond to this situation will require careful thinking and planning on the part of the police.

71 . 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. Task 4 Testing and Fine Tuning (30 March 2012 to 24th April 2012)  Fine tune on the filtering and calculation of connected components. 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. 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. it is important to choose the type of model and syntax that are suitable for Matlab is taken into consideration. Thus. we have drafted out the project schedule to follow up closely.  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.

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

Westenberg. D.anpr.  http://en. 1990. Bailey. R.Serkan Ozbay. Yang ―Test bed for number plate recognition applications‖.wikipedia. B. 2002. 1994.org/wiki/Automatic_number_plate_recognition  http://www.G.6/1-6/6. ―Car License Plate Automatic Vehicle Identification by Plate Recognition Author . Nijhuis.P.A. Ter Brugge.H.73  D. 1994  J.org/wiki/Vehicle_registration_plates_of_India  http://en.‖ IEE Colloquium on Electronic Image and Image Processing in Security and Forensic. Irecki.D. Helmholt. Lotufo.G.W. Bird. ―Number-plateMatching for Automatic Vehicle Identification. and AS. February 16. J. Venema.035. Morgan.  M. Johnson.M. Proceedings of First IEEE International Workshop on Electronic design. 1995.M. ―Automatic Number-plate Recognition : Neural Network Approach. IEEE Computer Society. A.  R. M.net/  http://www. L. 3 1 Aug-2 Sept. 1990.A. Spaanenburg.S.A.S. Fahmy.‖ Proceedings of the IEE Colloquium on Image analysis for Transport Applications.M. B.K. and Ergun Ercelebi. Test and Applications ( DELTA‘02 ). pp. M. Aprl. V01. 1990. Lim and L. Johnson.‖ Proceedings of VNIS‘94 Vehicle Navigation and Information System Conference. Pluim.wikipedia.info/ 73 .platerecognition. 1990.  A. ―Automatic NumberPlate Recognition. K.A.

74 74 .

Sign up to vote on this title
UsefulNot useful