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

Under the Guidance of

In partial fulfilment of
B.Tech ( E& TC )




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.




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.


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

08070121202 Mayank Kishore . Pune.08070121232 Is approved for the degree of BACHELOR OF ENGINEERING – Electronics & Telecommunication Symbiosis International University.08070121224 Pathikrit Guha .5 The Project entitled “LICENSE PLATE RECOGNITION SOFTWARE” By Abhinandan Singh . ______________________________________ 2. Examiners: 1. _______________________________________ Date : Place: 5 .

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

Algorithm 8. Introduction 3.3 Objectives 3.2 Features of project Chapter 3.5 Various Types of Vehicle License Plate 3.1 Introduction to matlab 4.1 Problem Statement 2.2 Input Image from file. 8. Development History Chapter 8.7 Table of Contents Contents List of Figures Abstract Chapter 1.2 Image Processing 4.4 Constraints 3.3 Comparison Between MATLAB and Artificial Intelligence Chapter 5. 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 9.5 Number identification 8.6 Commercial Products Chapter 4 Platform / Technology 4.2 Conversion of RGB Images to Binary Images 7 Page no. Literature Survey Chapter 2.2 How the Vehicle License Plate System works 3. Problem Definition 2.4 Segmentation 8. 8.1Image Cropping 9.6 Save to file in given format Chapter 9. Components Chapter 6.1 Algorithm for ANPR system 8.1 Project Background 3. Imaging Hardware Chapter 7.3 Convert image into binary.

3 Filtering of Digits 12.1 Algorithm to extract digits 17.1 Normalization 14.3 Algorithm to read characters Chapter 18 Result Analysis 18.2 Template Matching Chapter 15 Analysis of Result 15.3 Checking and verification of the Static Chapter 16 List of Functions Used Chapter 17 Code 17.2 Vehicle Quantization and Equalization 15. Image Enhancement 10.1 Feature Extraction from Digital Image 13.2 Binary Area Open(Bwareaopen) 12.3 Colour Image Processing Chapter 10.8 9.1 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 .4 Identify and remove away the small connected objects Chapter 13 Image Segmentation 13.2 Medfilt2 Chapter 11 Thresholding 11.2 Database Chapter 14 Character Recognition 14.1 Threshold Selection 11.2 Global Thresholding 11.1 Extracting of Individual Digits 15.3 Adaptive thresholding Chapter 12 Image Noise 12.1 Filtering 12.2 Algorithm to normalisation of characters 17.1 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 .

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

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

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

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

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

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

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

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

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

19 System block Diagram Fig 3.4 19 .

 Format Vehicle owner who register the car as private vehicle have a white background and black text. Fig 3. The third part is a 4 digit number unique to each plate. 22 UN 14).g..  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. Instead they have the Emblem of India in gold embossed on a red plate. Due to heavy volume of vehicle registration. Commercial vehicles such as taxis and trucks have a yellow background and black text (e.5 20 . This scheme of numbering has some advantages:   the State or District of registration of a particular vehicle In the case of a police investigation of an accident or vehicle-related crime. The President of India and state governors travel in official cars without licence plates.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.20 3.g. The next two digit numbers are the sequential number of a district. A letter(s) is prefixed when the 4 digit number runs out and then two letters and so on. DL 2C 0001). 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. witnesses usually remember the initial area code letters — it is then quite simple to narrow down suspect vehicles to a much smaller number by checking the database without having to know the full number.

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

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

Tracks and reads Shipping container identification marking. and transmits the ID string to the port or gate computer. the records include both the image plus the extracted result. Windows DLL or Linux library. VISPA is available in two forms Basic Version: . Enhanced Version:. traffic surveillance. SeeContainer Identification System:. 8. The image will be linked to the ticket.6. 3.4 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. such as SeeGate . or in form of different special-task systems. the system read the camera images and extract the identification data from the images. access control. • Can be customized according to specific user needs. There technology is based on computer vision.23 Features are • Open architecture to most common video-systems. The recognition result is then logged together with the images. Available as a complete system which is based on a background Windows application. Available as complete systems. or to a client process. law enforcement and security applications.crane mounted Container recognition system. There product includes.License Plate Identification.a recognition system for the Tracks and Containers. or SeeCrane . as a stand-alone turn-key version. The basic system version connects to 4 cameras and can be upgraded to 8 cameras. The VISPA controller with an integrated frame grabber card for 4. or 16 cameras automatically identifies the license plate from the video image and stores it in a database. SeeCar License Plate Recognition:. The license plate can then be encoded on the ticket.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. 23 . This is the main advantage of vision based recognition. • Compatible with standard hardware and software.Detects and reads Vehicle license plates for parking.

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

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

 Disadvantage of Artificial Intelligence: 1. 3. Not good in common sense reasoning. We can changed and add individual rules. 3. 26 . . Slow response. 4. 2. Expensive. MATLAB coding is shorter and simpler. 4.26 4. Good for solving complex problems where humans or programmer have expert knowledge in it. 2. Data can be represented in terms of matrices or vectors. 3. 5. The system will perform faster when using “Matrix Approach”.  Advantage of MATLAB 1. Algorithm used in MATLAB can be converted to use in hardware. Non-programmers can easily understand the rules of artificial intelligence. There are difficulty in getting expert knowledge and putting it in used in the system. MATLAB possess power graphic visualization tools. 5.3 Comparison Between MATLAB and Artificial Intelligence  Advantage of Artificial Intelligence: 1. Unpredictable. 2.

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

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

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

the intercept team took some action (e. In 2005 and 2006. serious crime. 2004). ANPR technology continues to be used across the United Kingdom. Over this one year period. an average. or prohibited drivers.000 pounds total). 2006). On an annual basis.543 vehicles were stopped by intercept teams resulting in 13. three instances involving the recovery of other stolen goods (equivalent to approximately 23. over 1. In total. these units made. The results of this evaluation also demonstrated that the ANPR technology contributed to a substantial increase in arrests (Pughe.499 arrests. the number of vehicles used in the commission of other criminal offences. The Metropolitan Police Service operates four ANPR units who work across London. In nearly two-thirds (61 per cent) of these stops. and fatal and serious injury road traffic accidents (Hampshire Constabulary. the data also highlighted the limited ability of the intercept teams to respond to the volume of hits they received. and 8. seven instances of drug seizures (equivalent to approximately 3. enforced an arrest). 2004). There are deployment teams who are used to assist in targeting hot spots for vehicle and other crime. volume crime. ANPR was beneficial to police forces by providing better efficiency in the deployment of officers.30 In total. In effect. uninsured. 2003). For instance. The results also indicated that the police could expect a substantial increase in the amount and value of goods they recovered. Currently. A second evaluation was conducted between June 2003 and June 2004 with 24 police forces (PA Consulting Group. 2007). A further 16. 2003).8% of arrests were made for theft or burglary offences.g. equivalent to approximately one stop per hour. The results of this study were similar to the first study. arrests were made in nearly 4-8% of the vehicle stops. the Hampshire Constabulary uses ANPR to prevent and detect terrorism. 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. a constable using ANPR technology could expect to encounter: the recovery of 11 stolen vehicles (equivalent to approximately 68.2% for drug offences. 2003). two seizures of weapons and/or firearms. 180. again suggesting a need for policy outlining a response priority scheme. no date).000 stolen vehicles were recovered over this period (PA Consulting. and the number of vehicles owned or operated by persons of interest (PA Consulting Group. workload concerns continued to exist. however. 10. police were only able to respond to 13% of hits (PA Consulting Group. However. One-quarter of the arrests were for disqualified. In effect. on average.3% for theft of or from a vehicle. This initial study also provided the Home Office with descriptions of the quantity of vehicles on the road violating insurance or other traffic regulations. 30 .000 pounds). and five instances of recovery of other stolen property (PA Consulting Group.300 pounds total).

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

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

and stolen cars (1. research must be conducted to determine the extent to which such technology is useful to Canadian police forces. The Hot Lists were for unlicenced vehicles. nearly all (97.7 per cent) of the scans accurately captured the car‘s licence plate. four hits every hour (Schuurman. Of these. Canada. The remaining hits were for unlicenced (i. 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. and over two-thirds (69. Over the course of this study.4 per cent). one unmarked patrol vehicle drove through 31 Surrey parking lots scanning the licence plates of parked cars over the period of one week. uninsured) vehicles (23. uninsured drivers. In fact. It was concluded that using the technology in a stationary format along major intersections or installing it in mobile units that patrolled the jurisdiction‘s main roads would likely be more effective for identifying stolen vehicles. 2007). and stolen vehicles.9 per cent). 21. To collect the data for this initial study. 33 . Given that there is limited information available to date on the use of ALPR technology.e. lists of vehicles of interest2 were populated on a daily basis and uploaded to the patrol car‘s onboard computer.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.8 per cent). 2007).8 per cent) of hits were for unlicenced drivers. Such research can be used to inform deployment strategies.6% of scanned plates resulted in a ‗hit‘. there were. especially to locate and recover stolen vehicles. on average. Schuurman‘s (2007) results indicated that 1. The current study intends to provide some initial data regarding the use of ALPR technology in British Columbia. prohibited drivers. Scanned plate images were compared to the CPIC and MVB databases. prohibited drivers (4. for example. Nearly three-quarters (72 per cent) of the hits occurred between 3pm and 7pm.876 licence plates were scanned.


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.


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.



Overview of the Vehicle license plate System

Fig 8.1

9. webcam etc can be used to capture the acquired images.1: Original Image Fig 9. Electronic devices such as optical (digital/video) camera. The images will be stored as colour JPEG format on the camera. vehicle images will be taken with a Panasonic FX 30 digital camera. The figure below shows the copping of image: Fig 9.2 : Cropped Figure 37 . we might proceed in using the Matlab function to convert the vehicle JPEG image into gray scale format.37 9 Image Acquisition The initial phase of image processing for Vehicle License Plate Recognition is to obtain images of vehicles. Next.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. As the license plate surrounding is of no importance. For this project. this cropping process will highly increase the speed of image processing.

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. Binary Images are obtained by converting the input image into grayscale format. the image obtain is being converted to Binary Image. white) and the rest will be set to 0 (black). The application is as:  Text interpreting  Identify the object orientations Next. then by converting the grayscale image to binary image by thresholding. The characteristic function for the image object is classify below: Fig 9. Binary images is the simplest process and has apply to many other application.2. The image is made up of a matrix squares which is called Pixel. The conversion is done by using the toolbox in MATLAB (im2bw). The pixel of grey level above the threshold will be set to 1 (equal to 255.3 38 .2 Conversion of RGB Images to Binary Images In order facilitate the next process smoothly and reducing the processing time.38 9. Each pixel in the image has a brightness value which is known as grey level. We will obtain white object with black background or vice versa. It is useful as the information we need can be obtained from the silhouette of the object.

5 : Histogram of object and background which is close 39 .4: Histogram of light object with dark background. Frequency Fig 9.39 Below will illustrate different type of histogram images Fig 9.

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

7 : Original Image Fig 9.41 Fig 9.8 : Binary mage 41 .

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

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

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

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

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

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

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

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

see Lewis . For the project.2. 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. (where f is the image and the sum is over x. 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. In the expansion of d2 50 .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. 14.v). 14. several inexact but fast spatial domain matching methods have also been developed. Due to the computational cost of spatial domain convolution.1 Normalization In this phase. For this reason normalized cross-correlation has been computed in the spatial domain. An algorithm for obtaining normalized cross correlation from transform domain convolution has been developed. Unfortunately the normalized form of correlation (correlation coefficient) preferred in template matching does not have a correspondingly simple and efficient frequency domain expression.y under the window containing the feature t positioned at u.1 Cross Correlation The use of cross-correlation for template matching is motivated by the distance measure (squared Euclidean distance) .50 14 Character Recognition 14. the extracted characters are resized to fit the characters into a window. The new algorithm in some cases provides an order of magnitude speedup over spatial domain computation of normalized cross correlation.

51 the term is constant. 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 .

Fig 15.2 : Recognition: MH01AX7946 52 . For instance. It is generally important when capturing the vehicle image.1 Extracting of Individual Digits Determine the angle of the Vehicle License Plate. the figure illustrate below lead to wrong recognition of the character.52 15 ANALYSIS OF RESULT Tests are conducted according to the modular form 15.1 Recognition : D6LH4CNEB800 Fig 15.

Fig 15.6000). This will result fail recognition of the vehicle license plate. Equalization and quantization allow to obtain a gray scale image with improve contrast between digit and the background.imshow(imagen).2 Vehicle Quantization and Equalization For some rare cases. 15. we can improve on the accuracy of capturing of vehicle image. Below illustrate a example of the scenario: Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen. low contrast image. such as very dark image.3 Checking and Verification of the Statistic In the midst of trying out other car plate. Next. 15. I have experience loosing out character when performing the extracting process.3 53 . we can make the difference between the digits and background inside the license plate. 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. the binarized image do not allow to make the difference between the background and the digits. figure.53 To improve in the cropping of image. To improve on the performance of the character recognition. high contrast image. After much study the MATLAB toolbox syntax. 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.

figure.imshow(imagen).4 54 .7000).54 Morphologically open binary image (remove small objects) imagen = bwareaopen(imagen. Fig 15.

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

0] (i.Find indices and values of nonzero elements.2-D correlation coefficient. 23. 22.Find .Determine whether array is empty.Isempty .Fclose .Display image.Imshow ..Disp .Rectangle .Resize image.Close one or more open files.Max. no curvature).0.1.56 13.displays an array.e. 15.Resize . 16. 21. 17. 19. 18. 56 .Corr2 .Smallest elements in array. 20.1] and Curvature [0.Min .Largest elements in array. 14.Fprintf .draws a rectangle with Position [0.Write text to device. without printing the array name.

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

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

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

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

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

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

The technology may have the capacity to read more plates.63 Extracted Number plate: MH14CS7710 Extracted Number plate:MH12DE94 Extracted Number plate: MH01AX7946 18. Perhaps the most important conclusion reached from this study is that the utility of ALPR depends on volume.2 Discussion Although ALPR technology has been promoted as being capable of reading in excess of 3. 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. The initial analysis of parking lot data produced by Schuurman (2007) suggested that parking lot 63 .

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

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

For future implementation.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. the recognition system should refuse to make the decision.  There should be improvement on the decision of the algorithm and ways to detect error. 66 .

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

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

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

smudges. This work can be further extended to minimize the errors due to them. blurred regions & different font style and sizes are need to be taken care of. policies may be put in place that regulate the deleting of collected data on a daily. there may be concerns regarding who has access to this data . Citizens may also have concerns with respect to the maintenance of data in warehouses. the issues like stains. the results of this study suggest that ALPR technology offers several substantial benefits to the police. Also. Citizens may fear the potential for breaches in security. although further research is needed to determine the extent to which ALPR increases the rate of arrest and has a deterrent effect. therefore. How to adequately respond to this situation will require careful thinking and planning on the part of the police. 70 . Future Scope Though we have achieved an accuracy of 80% by optimizing various parameters. 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. and thus make any firm conclusions on its general utility. The overriding benefit of ALPR is that it brings a far larger number of offenders to the attention of the police. In addition. However. weekly. or yearly basis. it is difficult to assess the impact of ALPR on police resources and workloads. monthly. Therefore to achieve this. it is required that for the task as sensitive as tracking stolen vehicles and monitoring vehicles for homeland security an accuracy of 100% cannot be compromised with. In responding to concerns of privacy. Essentially. It is. extremely important that considerable thought is given to the safe storage of data and strict regulations regarding who has access to the databases.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. Still. In conclusion. rather than the few offenders the police are able to find during their routine activities. 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. . further optimization is required.

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

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

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

74 74 .