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

Dr. in partial fulfillment of the requirement for the award of Degree of Bachelor of Engineering ( Electronics & Telecommunication ) of Symbiosis International University. Roll No. is record of bonafide work carried out by her/him . Date : Place : Prof. _ 08070121232 _. Mrudang Shukla Guide . Narayan Pisharoty Head. Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115. Department of E & TC Engineering Symbiosis Institute of Technology Pune – 412 115.4 CERTIFICATE This is to certify that the project entitled LICENSE PLATE RECOGNITION SOFTWARE submitted by _ Pathikrit Guha _ . Prof. under my guidance. 4 .

_______________________________________ Date : Place: 5 .08070121202 Mayank Kishore .08070121224 Pathikrit Guha . Pune. ______________________________________ 2.5 The Project entitled “LICENSE PLATE RECOGNITION SOFTWARE” By Abhinandan Singh .08070121232 Is approved for the degree of BACHELOR OF ENGINEERING – Electronics & Telecommunication Symbiosis International University. Examiners: 1.

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

6 Save to file in given format Chapter 9. Algorithm 8.5 Number identification 8.4 Segmentation 8.5 Various Types of Vehicle License Plate 3. Components Chapter 6.4 Constraints 3.2 Image Processing 4.7 Table of Contents Contents List of Figures Abstract Chapter 1. Literature Survey Chapter 2.1 Problem Statement 2. Imaging Hardware Chapter 7. Development History Chapter 8.1 Introduction to matlab 4. 8.6 Commercial Products Chapter 4 Platform / Technology 4.3 Objectives 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 . Image Acquisition 9. Problem Definition 2.1 Project Background 3.3 Convert image into binary. Introduction 3.2 Input Image from file.2 How the Vehicle License Plate System works 3.2 Features of project Chapter 3.1Image Cropping 9. 8.2 Conversion of RGB Images to Binary Images 7 Page no.3 Comparison Between MATLAB and Artificial Intelligence Chapter 5.1 Algorithm for ANPR system 8.

8 9.3 Filtering of Digits 12.1 Algorithm to extract digits 17.2 Medfilt2 Chapter 11 Thresholding 11.1 Feature Extraction from Digital Image 13.2 Global Thresholding 11.1 Normalization 14.3 Algorithm to read characters Chapter 18 Result Analysis 18.2 Binary Area Open(Bwareaopen) 12.3 Colour Image Processing Chapter 10.1 Threshold Selection 11.3 Checking and verification of the Static Chapter 16 List of Functions Used Chapter 17 Code 17.2 Database Chapter 14 Character Recognition 14.2 Template Matching Chapter 15 Analysis of Result 15.1 Extracting of Individual Digits 15.3 Adaptive thresholding Chapter 12 Image Noise 12.4 Identify and remove away the small connected objects Chapter 13 Image Segmentation 13.2 Vehicle Quantization and Equalization 15.1 Filtering 12. Image Enhancement 10.2 Algorithm to normalisation of characters 17.1 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 .1 Imcomplement 10.

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

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

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

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

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

Concerns about these systems have centered on privacy fears of government tracking citizens' movements. 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. 2. human is needed to observe and list the user car plate number manually. or ones specifically designed for the task.14 2 Problem Definition 2. with some configurable to store a photograph of the driver. owing to plate variation from place to place.[ANPR technology tends to be region-specific. Besides that.2 Features Automatic number plate recognition (ANPR) is a mass surveillance method that uses optical character recognition on images to read vehicle registration plates. ANPR can be used to store the images captured by the cameras as well as the text from the license plate. and increased government spending. So this project is developing to replace human to monitor the car and automatically capture the image. misidentification. the system can automatically display the status of the car which it will compare between the car plate numbers recognized with the database. high error rates. Systems commonly use infrared lighting to allow the camera to take the picture at any time of the day. 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. Previously. 14 .

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

the images will be enhance. Thirdly. Lastly. The system will read the information pixels of the vehicle and run the recognition process. Next.1 Besides. Next. Below are the non-constant variables which will affect the accuracy of recognition:  Speed of the vehicle 16 . Fig 3.16 Secondly. the gantry will open and allowed the vehicle to pass through. locating the vehicle plate position and extract the characters from the vehicle plate. 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 characters will be recognized by using Neural Network. Besides analyzing. Diagram is illustrate in Fig 1. If ―Access Granted‖. the system will try to match the recognized vehicle plate number with the car plate database. illumination (infra-red) will be activated and images of the front picture of the vehicle will be taken. we also need to look into other facts of variables that are not constant. 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. There are difficulties for Vehicle License Plate Recognition in which it will affect the efficiency and accuracy of the system. the system will apply certain algorithm to analyses the vehicle image.

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

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

19 System block Diagram Fig 3.4 19 .

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

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

3 Vehicle Identification System for Parking Areas (VISPA) PPI's Vehicle Identification System for Parking Areas (VISPA) [28].6. • Works 24 hours a day.22 3. fuzzy logic and an arsenal of image processing tools. Using advanced image processing and artificial intelligent techniques such as AI best first breadth-wise search algorithm. It is a high performing robust system that gives consistent results under all weather conditions. • Reads accurately at highway speeds.6.1 IMPS (Integrated Multi-Pass System) An IMP [26] is a Singaporean commercially developed license plate recognition system. captures and identifies a vehicle's license plate data and makes a read decision. 3. The system's reliability and flexibility allow it to accommodate some of the most stringent needs in some of the worst conditions. however. 22 . • Reads accurately in most weather conditions. it automatically locates vehicle license plates and reads the numbers accurately each time every time.6. combined template and neural network recognizers. 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. • Automatic and within milliseconds.6 Commercial Products The various products in the market today are described briefly below. Current LPR system read Latin (A-Z) and Korean (Hangul) letter and Arabic number (09). Features of this LPR technology includes.2 Perceptics Perceptics [27] is the world leader in license plate reader technology. 7 days a week. 3. easy installation and has accessories and features for most parking security surveillance needs. 3. With milliseconds the LPR system locates. identification and improved security. uses video imaging for better recognition. VISPA provides for state-of-the-art video technology.

Available as complete systems. or 16 cameras automatically identifies the license plate from the video image and stores it in a database. • Can be customized according to specific user needs. There technology is based on computer vision. the records include both the image plus the extracted result.Detects and reads Vehicle license plates for parking. The basic system version connects to 4 cameras and can be upgraded to 8 cameras. SeeCar License Plate Recognition:. or in form of different special-task systems.Tracks and reads Shipping container identification marking. or SeeCrane . such as SeeGate . access control.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. The recognition result is then logged together with the images.License Plate Identification. 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. • Compatible with standard hardware and software. traffic surveillance.crane mounted Container recognition system.a recognition system for the Tracks and Containers.23 Features are • Open architecture to most common video-systems. or to a client process. The license plate can then be encoded on the ticket. law enforcement and security applications. There product includes. The VISPA controller with an integrated frame grabber card for 4. 3. SeeContainer Identification System:. 8.6. 23 . The image will be linked to the ticket. This is the main advantage of vision based recognition. Enhanced Version:. the system read the camera images and extract the identification data from the images. as a stand-alone turn-key version. Windows DLL or Linux library. and transmits the ID string to the port or gate computer. Available as a complete system which is based on a background Windows application.

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

or even a 3D view of an unborn baby. Traffic Control etc.2 25 .png . .Jpg . This useful information may be the dimensions of an engineering component. Graphic Interchange Format Windows bitmap Portable network Graphics X Window Dump Extension .bmp .tif. Block Diagram of Image Processing Steps Fig 4.25 Format Name TIFF JPEG GIF BMP PNG XWD Description Tagged image file format Joint photographs Expert Group. Engineering.xwd 4. Quality Control.2 Image Prcessing Image Processing generally involves extraction of useful information from an image.gif . Face Detection.Jpeg . size of diagnosed tumour. The main areas of application of Image Processing are Bio-Medical.tiff . .

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

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

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

The central ANPR system. the patrol officer is provided with information regarding the vehicle.e. and police forces were provided with computers that were able to store ANPR information in real time (Pughe. a text file containing information on the car registration number. the heart of London‘s financial district (1993 Bishops gate bombing. such as whether the car was stolen. In 2002 to 2003. a British company operating a premier global marketplace for shipbrokers and charterers. 2006). 1992. 1993. Instead. As of 2001. The bombing was massive in size and destroyed several buildings with many others suffering shattered windows. 2006). 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. On April 10.29 7 Development History The United Kingdom: In 1992. 2003). the United Kingdom evaluated the use of ANPR with nine police forces. This resulted in an increase in arrests to 100 per year. NADC stores plate data and lists of suspect vehicles (Pughe. ALPR technology was developed at Cambridge University in the United Kingdom in response to terrorism. and injured 44 others. the databases. Approximately four seconds after a plate is read by the camera. officers were able to spend more of their time investigating hits. 29 . and the GPS location of the camera is created. partially destroying the façade of the Exchange‘s offices and extensively damaging the rest of the building (Baltic exchange. When a plate is photographed by an ANPR camera. the time and date of the scan. stationary (roadside) and mobile (mounted on police cars). scanning up to 5 million plates a day (Pughe. 10 times the national average (PA Consulting Group. The United Kingdom is at the forefront in the use of plate recognition technology. the Irish Republican Army detonated a truck bomb at Bishops gate. there are 3. 2006). Almost a year later on April 24. killed one person. or if it was uninsured (Pughe. 2006). 2008). a JPEG image of the plate is produced. the Irish Republican Army bombed the Baltic Exchange. 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. In addition. 2006). The blast caused approximately £1 billion in damage. 2008).000 cameras across the United Kingdom. as well as a video image of the plate and a video of the vehicle occupants (Pughe. if it had been involved in another crime. As a part of its intelligence network. is stored at the National ANPR1 This term is synonymous with ALPR and will be used interchangeably 3 Data Center (NADC) in London. i.

2006). and the number of vehicles owned or operated by persons of interest (PA Consulting Group. In 2005 and 2006. no date). For instance. the intercept team took some action (e. a constable using ANPR technology could expect to encounter: the recovery of 11 stolen vehicles (equivalent to approximately 68. ANPR was beneficial to police forces by providing better efficiency in the deployment of officers. and five instances of recovery of other stolen property (PA Consulting Group.000 stolen vehicles were recovered over this period (PA Consulting. In nearly two-thirds (61 per cent) of these stops. 2007). 30 . The Metropolitan Police Service operates four ANPR units who work across London. 200 arrests per month (Metropolitan Police Service. approximately one out of every 200 cars photographed by the ANPR cameras was stopped by an ANPR intercept team. equivalent to approximately one stop per hour. 2004). The results of this evaluation also demonstrated that the ANPR technology contributed to a substantial increase in arrests (Pughe. or prohibited drivers. In effect. an average. There are deployment teams who are used to assist in targeting hot spots for vehicle and other crime.000 pounds).499 arrests.g. The results of this study were similar to the first study. however. However.300 pounds total). 2003). three instances involving the recovery of other stolen goods (equivalent to approximately 23. enforced an arrest). One-quarter of the arrests were for disqualified.2% for drug offences. volume crime. and 8. arrests were made in nearly 4-8% of the vehicle stops. uninsured. and fatal and serious injury road traffic accidents (Hampshire Constabulary. serious crime. 10. again suggesting a need for policy outlining a response priority scheme. A second evaluation was conducted between June 2003 and June 2004 with 24 police forces (PA Consulting Group. police were only able to respond to 13% of hits (PA Consulting Group. On an annual basis. ANPR technology continues to be used across the United Kingdom. 180. This initial study also provided the Home Office with descriptions of the quantity of vehicles on the road violating insurance or other traffic regulations. the Hampshire Constabulary uses ANPR to prevent and detect terrorism. seven instances of drug seizures (equivalent to approximately 3. The results also indicated that the police could expect a substantial increase in the amount and value of goods they recovered. 2003). on average.8% of arrests were made for theft or burglary offences. 2004). over 1. 2003).30 In total. two seizures of weapons and/or firearms. the data also highlighted the limited ability of the intercept teams to respond to the volume of hits they received. In effect. In total. A further 16.543 vehicles were stopped by intercept teams resulting in 13.3% for theft of or from a vehicle.000 pounds total). Currently. Over this one year period. these units made. the number of vehicles used in the commission of other criminal offences. workload concerns continued to exist.

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

As previously discussed. and other agencies that is linked with the ALPR technology in police cruisers. 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. did not provide information on unlicenced. in addition to the cost of buying. Schuurman (2007) recently produced an analysis of the use of this technology in parking lots in Surrey. criminal justice. using $61. the state highway patrol apprehended 23 criminal suspects and recovered 24 stolen vehicles valued at US $220. The cost of warehousing this data. 2004). have outstanding warrants. ALPR technology has been used in Toronto for toll-collection purposes. The United Kingdom established a central data warehouse in London containing information from insurance. and maintaining ALPR technology. use civilian volunteers.32 the recovery of two stolen trailers demonstrating the technology‘s potential utility for homeland security (McClellan. ALPR has the potential to allow Canadian police forces to engage in proactive policing. ALPR was introduced in British Columbia as part of a pilot study in 2006. including reductions in criminal activity. These results were 50% higher than results during the same time period one year previous. are prohibited from driving. updating the databases. police can use ALPR technology linked to criminal justice and insurance databases to identify those drivers who. The state of Ohio studied the effectiveness of ALPR technology over a four month period in 2004. By driving through traffic corridors in cities across Canada. Canada ALPR technology in Canada has only recently been implemented for use with traffic and other criminal violations. The Highway 407 Express Toll Route was introduced in 1997.000 in federal funding. there are several issues that must be considered prior to the widespread use of ALPR technology in Canada. Additional staffing costs may also be incurred. recovery of stolen goods. Over the four month period. One way to offset these resource increases may be to. and/or conducting further searches of licence plates.000 (McClellan. 2007). must be weighed against the costs recovered through the use of this system. no date). for instance. Using information obtained through 32 . the technology also offers police a potentially useful tool for identifying and recovering stolen vehicles. and increases in positive public perceptions of the police (Schuurman. whether in the form of additional police on the roads utilizing this technology or the hiring of additional staff to assist in confirming hits. 2004). installing. or are driving uninsured vehicles. uninsured. beginning in August 2004. British Columbia. or prohibited drivers. It allows drivers to use the express route for a toll fee that is recorded electronically. therefore. wherever possible. 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. Still.

Schuurman‘s (2007) results indicated that 1. The remaining hits were for unlicenced (i. especially to locate and recover stolen vehicles. nearly all (97.6% of scanned plates resulted in a ‗hit‘. 33 . Such research can be used to inform deployment strategies. Given that there is limited information available to date on the use of ALPR technology. 2007). for example. uninsured) vehicles (23. one unmarked patrol vehicle drove through 31 Surrey parking lots scanning the licence plates of parked cars over the period of one week. lists of vehicles of interest2 were populated on a daily basis and uploaded to the patrol car‘s onboard computer.4 per cent). and stolen vehicles. To collect the data for this initial study.33 the Canadian Police Information Centre (CPIC) and the Motor Vehicle Branch (MVB). Schuurman (2007) concluded that the deployment of ALPR technology exclusively to parking lots would not be the most efficient use of the system. 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.876 licence plates were scanned. The Hot Lists were for unlicenced vehicles. 21. and stolen cars (1. Nearly three-quarters (72 per cent) of the hits occurred between 3pm and 7pm. research must be conducted to determine the extent to which such technology is useful to Canadian police forces. prohibited drivers. prohibited drivers (4. 2007). on average.8 per cent). 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. there were.e.7 per cent) of the scans accurately captured the car‘s licence plate.8 per cent) of hits were for unlicenced drivers. and over two-thirds (69. The current study intends to provide some initial data regarding the use of ALPR technology in British Columbia. Over the course of this study. Scanned plate images were compared to the CPIC and MVB databases. Of these. In fact.9 per cent). Canada. four hits every hour (Schuurman. uninsured drivers.

34

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

35

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

35

36

Overview of the Vehicle license plate System

Fig 8.1
36

2 : Cropped Figure 37 . Next. webcam etc can be used to capture the acquired images. Electronic devices such as optical (digital/video) camera. we might proceed in using the Matlab function to convert the vehicle JPEG image into gray scale format. this cropping process will highly increase the speed of image processing.37 9 Image Acquisition The initial phase of image processing for Vehicle License Plate Recognition is to obtain images of vehicles. As the license plate surrounding is of no importance. For this project.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. 9.1: Original Image Fig 9. vehicle images will be taken with a Panasonic FX 30 digital camera. The figure below shows the copping of image: Fig 9.

then by converting the grayscale image to binary image by thresholding.3 38 . 9. It is useful as the information we need can be obtained from the silhouette of the object.2 Conversion of RGB Images to Binary Images In order facilitate the next process smoothly and reducing the processing time.2. Binary images is the simplest process and has apply to many other application. Binary Images are obtained by converting the input image into grayscale format. 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). The application is as:  Text interpreting  Identify the object orientations Next. The image is made up of a matrix squares which is called Pixel. The characteristic function for the image object is classify below: Fig 9.1 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 obtain is being converted to Binary Image. We will obtain white object with black background or vice versa.38 9. Each pixel in the image has a brightness value which is known as grey level. The conversion is done by using the toolbox in MATLAB (im2bw).

39 Below will illustrate different type of histogram images Fig 9.4: Histogram of light object with dark background. Frequency Fig 9.5 : Histogram of object and background which is close 39 .

The schematic of the RGB cube that illustrate both the primary and secondary colour at each vertex is shown below. 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. Fig 9. Green and Blue) and the secondary colour (Cyan.40 In this circumstance.6 40 . The colour space is normally graphically shown as RGB colour cube. The cube vertex consists of the primary colour (Red. 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.

8 : Binary mage 41 .41 Fig 9.7 : Original Image Fig 9.

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

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

11. m2= average value of G2 4.2 Global Thresholding This is a method whereby the histogram of the image is being partitioned using a single threshold value. The average of each set is computed. m1= average value of G1 2. which has been proven to converge at a local minimum— meaning that a different initial threshold may give a different final result. Image is form up of square matrixes called pixels and each pixels in the image have a brightness level known as gray level. By using the adaptive thresholding. keep repeating until the new threshold matches the one before it (i.n) is the value of the pixel located in the mth column. 11. Go back to step two. 44 . This is a common reason why global thresholding fail.e. For other cases. The value of the gray level varies from the darkest (0) to the brightest (255). If the histogram is bimodal.3 Adaptive Thresholding The vehicle number plate can be partially illustrated. G2= {f(m. its can solve the disadvantages of the global thresholding as it computes the value of the threshold for every pixel separately using the neighborhood. We can use the graythresh toolbox function to calculate the threshold value by using Otsu‘s method.n):f(m.n)>T} (object pixels) 2. 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):f(m. nth row) 3. T‘ = (m1+m2)/2 5. the value of the threshold will be taken in the middle of the bimodal. until convergence has been reached). The threshold defines the value of the gray level in which the baseline boundary is in between the foreground pixels and the background. now using the new threshold computed in step four. The threshold value which is selected is use to reduce the intraclass variance between the white and black pixels.44 2.n) T} (background pixels) (note. G1= {f(m. creating two sets: 1. The image is segmented into object and background pixels as described above. in which the modes are overlapping. This iterative algorithm is a special one-dimensional case of the k-means clustering algorithm.. 1.

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

the image is only left with characters and digits in which we are interested. they will obtain a unique number. Lastly. 2) Identify the frame line that is connected to the digits and separate it. In this algorithm. frame lines. we need to identify the connected components. The pixel of 0 represents the background and pixel of 1 will make up the first object. effects on JPEG compression. 46 . 141 connected components are found in the BW image. Below illustrate an example of filtering process.4 Identify and remove away the small connected objects For this stage. 12. object or substance which is not digits/characters such as screws. water droplet. we are able to remove or filter out the unwanted substances or noise that is not a character or digits. Fig 12.46 The non-digits substance which appears in the image is caused by the noise (quantization that will transform to ‗Black‘). so on and so for. The elements of labels (stated in the algorithm) contains integer values that will be greater than or equal to 0. The 2 stages for the algorithm is as follows: 1) Remove out the small objects or connected components. By Filtering. sand.1 : Binary image with Noise For the above image. The component can have a value of either 4-connected or 8-connected. After the component has been labelled. we use 8-connected (8 specify 8-connected objects). the pixel of 2 will label the second object.

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

The process uses the edge detection to obtain the region contours and the objects will construct from the obtain contours.min(c):max(c)). the descriptor of the character from the same class is close to each other in the vector space. The process of the feature extraction is to transform the bitmap data into a form of descriptor in which more suitable for computer. n1=imagen(min(r):max(r). For this project. img_r=same_dim(~n1). word=[word letter].c] = find(L==n). vertical or diagonal edges etc. Segmentation process can be categorized into several parts. we will be trying out first category segmentation method. The algorithm below will represent how the extraction is being carried out and extracted figure is illustrated as below. In order to extract and analyzed the object characteristic. If we classify the similar character into classes.48 13 Image Segmentation Image segmentation plays an important and critical step that lead to the analysis of the processed image data. Lastly will be the edge-based segmentation. letter=read_letter(img_r). The normalized character description is based on the external characteristics as we only work for properties on the shape of the character. disp(Ne). The feature of the image is represented by a histogram. This will lead to a success in pattern recognition process. Secondly is the boundary-based segmentation. end 48 . the process need to partition the image into different parts that will have a strong correlation with the objects. [L Ne]=bwlabel(imagen). 13.1 FEATURE EXTRACTION FROM DIGITAL IMAGE The digital image description is depends on the external and internal representation. imshow(~n1). 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. which is by using threshold. for n=1:Ne [r. The descriptor vector includes the characteristics as the number of lines.

thus it can be accessed easily and updated. 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. If the class has match correctly. 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.1 13.49 Plotted Bounding Box Fig 13. 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. contents and images. 49 .2 Database It is a collection of information or data which it is being orderly organize. Database can be in the form of text.

see Lewis . several inexact but fast spatial domain matching methods have also been developed.v). 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. 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.50 14 Character Recognition 14. The new algorithm in some cases provides an order of magnitude speedup over spatial domain computation of normalized cross correlation. (where f is the image and the sum is over x. 14.1 Normalization In this phase. For the project. 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) . Unfortunately the normalized form of correlation (correlation coefficient) preferred in template matching does not have a correspondingly simple and efficient frequency domain expression. For this reason normalized cross-correlation has been computed in the spatial domain.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. the extracted characters are resized to fit the characters into a window. An algorithm for obtaining normalized cross correlation from transform domain convolution has been developed. 14. In the expansion of d2 50 .y under the window containing the feature t positioned at u.

51 . 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.

For instance.1 Recognition : D6LH4CNEB800 Fig 15. the figure illustrate below lead to wrong recognition of the character.2 : Recognition: MH01AX7946 52 . Fig 15.1 Extracting of Individual Digits Determine the angle of the Vehicle License Plate.52 15 ANALYSIS OF RESULT Tests are conducted according to the modular form 15. It is generally important when capturing the vehicle image.

This will result fail recognition of the vehicle license plate.3 53 . 15. Next.2 Vehicle Quantization and Equalization For some rare cases. Below illustrate a example of the scenario: Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen. I have experience loosing out character when performing the extracting process. high contrast image. 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. low contrast image. Equalization and quantization allow to obtain a gray scale image with improve contrast between digit and the background.imshow(imagen). 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. 15.6000). we can make the difference between the digits and background inside the license plate. After much study the MATLAB toolbox syntax. figure. we can improve on the accuracy of capturing of vehicle image.3 Checking and Verification of the Statistic In the midst of trying out other car plate. such as very dark image. 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.53 To improve in the cropping of image. Fig 15.

figure.4 54 .imshow(imagen). Fig 15.54 Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen.7000).

Imcrop .55 16 List of functions used 1. You can move or resize the crop rectangle using the mouse.computes the complement of the image.Morphologically open binary image (remove small objects). 5. The Crop Image tool is a moveable. resizable rectangle that you can position interactively using the mouse. In the complement of a binary image. you specify the crop rectangle by clicking and dragging the mouse. When you are finished sizing and positioning the crop rectangle.Open file. Im2bw . Size . Rgb2gray . Fopen . 8.measures a set of properties for each labelled region.returns the sizes of each dimension of an image in matrix a and b. the pointer changes to cross hairs when you move it over the target image. 11.Convert image to binary image.Global image threshold using Otsu's method. or obtain information about open files.Bwlabel .Performs median filtering of the matrix A using the default 3by-3 neighborhood. based on threshold.Regionprops . 12. Medfilt2 . Graythresh . 6. 10. Using the mouse. imcrop returns the cropped image 7. create the cropped image by double-clicking the left mouse button or by choosing Crop Image from the context menu.Bwareaopen . 9.creates an interactive Crop Image tool associated with the image displayed in the current figure. 55 . When the Crop Image tool is active. 4.returns in num the number of connected objects found in BW. black and white are reversed. called the target image. Imread : Read image from graphics file.Convert RGB image or colormap to grayscale. 2. Imcomplement . 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). 3. zeros become ones and ones become zeros.

Min .56 13.Fprintf .Resize image.1. 21.Determine whether array is empty.displays an array.Rectangle .Fclose .draws a rectangle with Position [0.Display image. no curvature).2-D correlation coefficient.Close one or more open files. 17.Disp . 23.Isempty . 22.1] and Curvature [0.0] (i. 16.Find .Max. 20.Find indices and values of nonzero elements.Write text to device. 15.Largest elements in array..Resize .e.Imshow .Smallest elements in array. without printing the array name. 18.Corr2 . 14. 19. 56 .0.

% Remove all object containing fewer than 6000 pixels image = bwareaopen(image.imshow(image).%pause(10). [L num]=bwlabel(image).57 17 CODE 17.3)==3 % RGB image imagen=rgb2gray(image).threshold).1 Algorithm to extract characters ( extractdigit. end % Convert to binary image threshold = graythresh(image). % Show image binary image figure.title('binary image').m).6000). image=imread('exp4.1) rectangle('Position'.'g'.'BoundingBox'). hold on for n=1:size(propied. disp(num).imshow(image).txt'.propied(n).'LineWidth'. % Show image figure. 'at'). propied=regionprops(L.BoundingBox. title('INPUT IMAGE WITH NOISE') % Convert to gray scale if size(image.imshow(~image). figure.jpg').'EdgeColor'.2) end hold off pause (1) 57 .%Storage matrix word from image fid = fopen('log. title('INPUT IMAGE WITHOUT NOISE') word=[]. image = medfilt2(image).%Opens a text for append in order to store the number plates for log. pause(1) image = imcrop(image). image =~im2bw(image.

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

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

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

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 .

The technology may have the capacity to read more plates. Perhaps the most important conclusion reached from this study is that the utility of ALPR depends on volume. The initial analysis of parking lot data produced by Schuurman (2007) suggested that parking lot 63 . the current results suggest that this capability is significantly overstated in actual road tests. but traffic volume and the design of Surrey streets may impede this read rate.000 plates per hour.2 Discussion Although ALPR technology has been promoted as being capable of reading in excess of 3.63 Extracted Number plate: MH14CS7710 Extracted Number plate:MH12DE94 Extracted Number plate: MH01AX7946 18.

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

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

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

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

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

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

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

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

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

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

74 74 .

Sign up to vote on this title
UsefulNot useful