ABSTACT-

In this seminar I have given brief discription about license plate recognition/Automatic number plate
recognition which is a software that can be reads the license plates of vehicals.
At the onset I have included a brief discription about case study for control access system that can gives
the vehicles approaches the gate & LPR unit automatically “reads” the license plate recognition number.
In later stages I included advantages & disadvantages of LPR.Finally, I gives includeds application of
LPR.
INTRODUCTION- Automatic Number Plate Recognition(ANPR) is also know as License Plate
Recognition(LPR) or Number Plate Recognition(NPR).
ANPR/LPR is a mass sureillance method that uses optical character recognition(ocr) on images to read
license plates on vehicals.They can use existing closed circuit television(cctv) or road rule enforcement
cameras or ones specifically designed for task..
LPR consist of cameras linked to a computer.As vehical passes LPR reads vehical registration marks or
number known as number plates from digital images captured through cameras located either in a mobile
unit ,in built trffic vehicals or via cctv.LPR/ANPR is used for by various police enforcement & as amethod
of electronic toll collection on pay per use rodes.
 WHAT IS LPR-
ANPR/LPR is a teconlogy that uses pattern recognition to read number plates .
In simple terms ANPR/LPR cameras photograph or capture the number plates of the vehicles that pass
them.This photograph is then fed in a computer system to find out details about the driver & owner of the
vehicals & details about vehicals itself.
It is a special software to read vehical number plate or license plate which is then compares with those of
its database .The database is either-
The police national computer(PNC),which holds extensive data on criminals, vehicals & property.
The driver & vehical lincencing agency(DVLA), showing untaxed or unlicenced vehicals.
Other forces hotlists. These are constantly updated & sharing this information between forces.

What is this technology -

It is the technical method of artificial vision (OCR) that allows the recognition of number plates in images of
vehicles. Historically, it has been applied on security systems to control accesses of vehicles and car parks.
Nowadays, the ANPR technology has improved its reliability, some systems are able to offer recognition rates
between 95 and 98%. Also, some ANPR equipment are able to recognize the number plate of vehicles that drive
up tol 200km/h.
Generally, the ANPR technology can be bought in two modalities :
• The ANPR engyne

• The ANPR equipment (Hardware + recognition engine)

The ANPR engine can recognize the number plate directly from the images stored in a hard disk. This type of
software allows to take good use of images that have been obtained from other systems like CCTV or cameras.
The ANPR equipment incorporates all the hardware necessary to capture the images of the vehicles and to
recognize the number plate. Moreover, it incorporates the ANPR engine. The ANPR equipment are designed to
offer the maximum reliability.
Depending on each case the ANPR equipment or ANPR engine will have different uses and advantages:
To recognize number
To make a good use
To optain high plates directly from
of CCTV and camera
reliability images stored in a
systems
hard disc
It is not
ANPR engine It is a habitual use It is a habitual use
recommended
ANPR equipment It is a habitual use No No
2. Parts of the generic system,
Capture Unit (CU) + Process Unit (PU)

Although there already exist some All-in-One equipment, the great majority of systems are still using "CU+PU"
architecture:
• (CU) Capture unit
o Camera housing

o Camera

o Infrared focus

• (PU) Process unit

o Embeded computer

 Framegraber
 Recognition engine
Operation of the system

The "UC+UP" system consists of two parts. The Capture Unit that takes the image of the vehicle, and the
Process Unit that receive the image from the Capture Unit and makes the recognition of the number plate. The
Process Units can control one or more Capture Units simultaneously.
The quality of the solution depends on each manufacturer, although generally the "CU+PU" architecture has
disadvantages respect the ANPR All-in-One, they are the following ones:
• 1º - Nonrobust architecture
o The Capture Units controlled from the one only Process Unit will fall if the Process Unit does not
work

• 2º - Complex installation and start-up

o It is necessary to install video and control wire for each one of the cameras

o Furthermore, it is necessary to provide power supply cable to the cameras, focus and Process
Units
o If the distance between the lanes are too long, the signal of the cameras will not arrive with
clearness to the Process Unit. For example:
  If we have to control 4 lanes gathered in groups of two and separated by a distance of 2 km, It
will not be possible to control the 4 lanes with the same Process Unit. Sometimes the cost of
the installation may increase because of the limitation of distances between the Capture Unit
and the Process Unit .
o If the Process Units are installed directly on the lane it will be necessary to protect it with a
weatherproof rack

• 3º - High cost
o The wiring and the time of installation are mulplied

o The maintenance of the system is multiplied

Evolution to All-in-One equipment

By contrast to the generic ANPR, the ANPR equipment integrates directly in the housing the camera, the
processor, the communications and the power supply unit
How does it work?

The ANPR process is divided into three steps. The detection of the vehicle, the capture of the images and the
process of recognition. Next, we will detail step by step how it works and depending on each case what the
advantages and disadvantages are
1.Detection of the vehicle. The first step is to take an image of the vehicle at the right time. Thus, the number
plate of the vehicle will be visible in the image. Nowadays, three kind of triger control exist
o Hardware triger: The ANPR equipment controls physically a sensor directly installed in the lane.
Whenever a vehicle has been detected by the sensor, the ANPR equipment will know its presence,
and then the process of the capture begins

o Software triger: The ANPR equipment communicates with the client application, who physically
controls a sensor directlly installed in the lane. Whenever a vehicle has been detected by the sensor,
the client application knows the presence of the vehicle and communicates it to the ANPR
equipment. At this moment the process of the capture begins

o Free flow: The ANPR equipment does not need to receive signal from any external sensor. The
ANPR equipment takes images continuously and it is able to detect the vehicles automatically

2.Capture of the images. Once the vehicle is detected, the following step is the capture of the vehicle. In
order to take a right image, the following points will have to be considered

a.Type of cameras:

 Interlace camera: The capture of the images is made in two steps. First uneven lines and
later the even lines. This type of cameras are cheaper but its use is not recommended for
ANPR because if the vehicle is in movement, the number plate appears defocused .

 Progressive cameras: The capture of imagenes is made at once. The use of this type of
cameras is totally recommended because if the vehicle is in movement the number plate
always appears focused

b.Type of light. Infrared light is used generally for the ANPR equipment. Although some ANPR
equipment are able to use the daylight and the infrared light during the night.

 Infrared light: The ANPR systems uses infrared light because the human eye cannot detect
it without other devices. One infrared filter located in the camera allows to emphasize the
number plate, but, in the other hand, the rest of elements of the image are darkened.
 Daylight: It is perceived by the human eye. It allows to take images in which the vehicle is
distinguished.
o Light management: The type of light is as important as how it is managed. It is possible to use any
typical technique of photography, but the ANPR manufacturers have chosen two great ways:

 To control the light emitted by the focus

 To control the light that enters in the camera

3.Number plate recognition process. Each ANPR manufacturer has developed its own recognition
algorithms, although, these are the main ones and the common ones

o To locate and to isolate the number plate in the image

o To correct the brightness and the contrast of the number plate

o To separate each character of the number plate

o To recognize each character of the number plate

CASE STUDY -FOR ASSECE CONTROL SYSTEM-

LPR (License Plate Recognition) is an image-processing technology used to identify vehicles by their
license plates. This technology is used in various security and traffic applications, such as the access-control
system featured in the following animation:

In the above example: while the vehicle approaches the gate, the LPR unit automatically "reads" the license
plate registration number, compares to a predefined list and opens the gate if there is a match.
ffollowing example shows how a typical access-control system works. It follows
the order of the animation above.

The vehicle approached the secured area, and

starts the cycle by stepping over a magnetic
loop detector (which is the most popular
vehicle sensor). The loop detector senses the
car and its presence is signaled to the LPR unit.

The LPR unit activates the illumination

(invisible Infra-red in most cases) and takes
pictures of the front or rear plates from the LPR
camera (shown at the left side of the gate). The
images of the vehicle include the plate and the
pixel information is read by the LPR unit's
image processing hardware (the frame grabber).

The LPR unit analyzes the image with different

image processing software algorithms,
enhences the image, detects the plate position,
extracts the plate string, and identifies the fonts
using special artificial intelligence methods
(such as Neural Networks).
Most LPR units are based on an application
running on PC under Windows. Other systems
exist that do not require a PC (such as the
stand-alone unit shown in this illustration).
 The LPR unit checks if the vehicle appears on a
predefined list of authorized cars, and if found -
it signals to open the gate by activating its
relay. The unit can also switch on a green "go-
ahead" light or red "stop" light. The unit can
also display a Welcome! message with
personalized data.

The authorized vehicle enters into the secured

area. After passing the gate its detector closes
the gate. Now the system waits for the next
vehicle to approach the secured area.

Other types of applications use the information retrieved from the image for different purposes. For
example, to prepare a speed or red-light violation ticket.

Plate and images-

LPR units are based on images of the front and/or rear plates. The following example shows a typical
installation of an access-control system in the gate of a secured office compound
The car, with the plate number: W856RKX, is just exiting from the secured area and is picked up by the
LPR system which identifies it as an authorized car and opens the gate. A welcome display (which includes
the vehicle number and driver name) is displayed in the large outdoor display in the back of the car.
A typical image captured by the Infra-red illumination and camera unit is shown in the following image
(this image is of the same car above). The image information is read by the LPR unit and is analyzed and
recognized automatically

Since the vehicle plates are based on different Country standards, they usually different in form, shape and
material. Therefore the LPR systems are Country specific and are adapted to the Country where they are
installed and used .

What's in an image
The above image of the front side of the car, shown in a typical format, is composed of 256 grey levels
ranging from black (grey level 0) to white (grey level 255). For a typical format there are 768 X 288 pixels
(PICture ELements), or about 0.2 Million elements. This vast amount of information is processed by the
recognition software in order to automatically locate and read the plate.
The computer processing needs to work on the global information

HOW DOES LPR WORKS FOR THIS SYSTEM-

LPR systems normally consist of the following units:
• Camera(s) - that take the images of the car (front or rear side)
• Illumination - a controlled light that can bright up the plate, and allow day and night operation. In
most cases the illumination is Infra-Red (IR) which is invisible to the driver.
• Frame grabber - an interface board between the camera and the PC, allows the software to read the
image information
 • Computer - normally a PC running Windows or Linux. It runs the LPR application which controls
the system, reads the images, analyzes and identifies the plate, and interfaces with other applications
and systems.
• Software - the application and the recognition package. Usually the recognition package is supplied
as a DLL (Dynamic Link Library).
• Hardware - various input/output boards used to interface the external world (such as control boards
and networking boards)
• Database - the events are recorded on a local database or transmitted over the network. The data
includes the recognition results and (optionally) the vehicle or drver-face image file

The following illustration shows a typical configuration of a LPR system (for example, for 2-lanes-in and 2-
lanes-out access control system). The system ("SeeLane") is a typical example of such system.
The SeeLane application runs as a background Windows application in the PC (shown in the center), and
interfaces to a set of SeeCarHead camera/illumination units (one for each vehicle) which are interfaced by
the frame grabber. The application controls the sensors and controls via an I/O card that is connected thru a
terminal block to the inputs and outputs.
The application displays the results and can also send them via serial communication and via DDE
messages to other application(s). It writes the information to local database or to optional remote databases
(via the network).

You can point on the items and the bottom text area will display a description.
Discription of seelane configuretion-

1.CAMERA &illumenation unit –

Camera & illumination unit are optimized for plate recognition.the camera output images to freamgrbber
.the illumination brighted upthe plate for improved recognition & images.
2. Supply-
Camera & illumination unit are powered by power supply.
3.Framegrbber-
The framegrabber interfaces the camera data,allowing the pc to capture & read the images as an bit-map
array.the framegrabber handles several camera input.
4.Pc-
The computer controls the LPR software(application & recognition engine) & hardware(I/O hard &
framegrabber).It is standred pc running window.
5.I/O card-
The i/p card receives i/p signals(such as loop sensor )& sends o/p(such as gate open or control over
illumination level).
6.Terminal block(TBL)-
This is mechnical interface between the i/o card &external conection.it has array of screw-for easy
conection. It has leds to indicate on i/o status.
7.Window application –
The application control the recognition sequence interfaes, recognition of network element , runs the
recognition process & o/p result.the application runs as a background application.
8.DDE Messege-
The seelane o/p DDE message (dynamic data exchange) messege to other window application additional
o/p includes : serial communication(RS232) or COM/DOM window interfaces.
9.Client application-
This window application receives recognition results and does additional function –such as writing the
data to a log file or site, specific tasks.
10.DATABASE-
the local database stores local LPR events : date ,time, plate numbers. this data can be used for local
search & analysis.
11.REMOTE DATABASE-
The recognition data can be transmitted over network to a remote database. The data contains recognition
results from LPR units , which can be searched & reported or used as parts of a application.
12.NETWORK-
The cluster of LPR units linked together to a central processer via the network , such as TCP/IP.
ADVANTAGES-

1.It is more simple: All the necessary elements for the ANPR process are integrated in the
same housing. Only one device is necessary for each lane to be controlled. The equipment
may be connected by Ethernet or serial communication with the client application

2.Modular architecture: If an equipment with All-in-One architecture does not work, its fall
does not affect to the other lanes, because the Process Unit are deleted

3.Installation and start-up is easier:

o It is only necessary to provide 220v, Ethernet network or serial communication to each
equipment
o The instalation is as easy as to screw the equipment with the support, to identify
ANPR equipment with an IP and to adjust the optics
o If one equipment falls, it is possible to replace it by another one

4.It reduces the cost:

o The wiring is reduced
o The installation and start-up time is reduced
o The maintenance of the system is reduced

5.Is that the system can keep an image record of the vehicle which is useful in order to fight crime and
fraud ("an image is worth a thousand words").
6.An additional camera can focus on the driver face and save the image for security reasons.
7.Additionally, this technology does not need any installation per car (such as in all the other
technologies that require a transmitter added on each car or carried by the driver).
DISADVANTAGES-
1.Poor image resolution, usually because the plate is too far away but sometimes resulting from the use
of a low-quality camera.
2.Blurry images, particularly motion blur
3.A different font, popular for vanity plates.
Typical applications-
1.Parking - the plate number is used to automatically enter pre-paid members and calculate parking fee for
non-members
2.Access Control - a gate automatically opens for authorized members in a secured area, thus replacing or
assisting the security gaurd.
3.Tolling - the car number is used to calculate the travel fee in a toll-road, or used to double-check the
ticket.
4.Border Control - the car number is registered in the entry or exits to the Country, and used to monitor the
border crossings.
5.Stolen cars - a list of stolen cars or unpaid fines is used to alert on a passing 'hot' cars. The 'black list' can
be updated in real time and provide immediate alarm to the police force. The LPR system is deployed on the
roadside, and performs a real-time match between the passing cars and the list.
6.Enforcement - the plate number is used to produce a violation fine on speed or red-light systems The
manual process of preparing a violation fine is replaced by an automated process which reduces the
overhead and turnaround time
7.Traffic control - the vehicles can be directed to different lanes according to their entry permits.The
system effectively reduces traffic congestions and the number of attendents.
8.Marketing Tool - the car plates may be used to compile a list of frequent visitors for marketing purposes,
or to build a traffic profile

9.Travel - A number of LPR units are installed in different locations in city routes and the passing vehicle
plate numbers are matched between the points. The average speed and travel time between these points can
be calculated and presented in order to monitor municipal traffic loads.
10.Airport Parking - In order to reduce ticket fraud or mistakes, the LPR unit is used to capture the plate
number and image of the cars. The information may be used to calculate the parking time or provide a proof
of parking in case of a lost ticket - a typical problem in airport parking which have relatively long (and
expensive) parking durations.
REFERANCE-
1.Hofman, Yoram. "License Plate Recognition - A Tutorial".
2.Lucena, Raul. http://www.anpr-tutorial.com Automatic Number Plate Recognition Tutorial.
3."Automatic Number Plate Recognition (ANPR)". Police Standards Unit, PoliceReform.gov.uk. Accessed.

• Self Reallization-
1.LPR systems should have fast shutter speeds to avoid motion blur
To avoid blurring it is ideal to have the shutter speed of a dedicated camera set to 1/1000th of a second.
Because the car is moving, slower shutter speeds could result in an image which is too blurred to read using
the OCR software, especially if the camera is much higher up than the vehicle.
2.Increasing the height of the camera may avoid problems with objects (such as other vehicles) obscuring
the plate.
3.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.
4.when the camera is at a lower level , 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.