Automatic Number Plate Recognition PDF
Uploaded by
George CatalinAutomatic Number Plate Recognition PDF
Uploaded by
George CatalinAutomatic number plate recognition
The system must be able to deal with dierent styles of license
plates
Automatic number plate recognition (ANPR; see also
other names below) is a mass surveillance method that
uses optical character recognition on images to read
vehicle registration plates. They can use existing closedcircuit television or road-rule enforcement cameras, or
ones specically designed for the task. 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 trac or individuals.
License-plate recognition process
ANPR can be used to store the images captured by the
cameras as well as the text from the license plate, with
some congurable to store a photograph of the driver.
Systems commonly use infrared lighting to allow the camera to take the picture at any time of the day.[1][2][3]
ANPR technology tends to be region-specic, owing to
plate variation from place to place.
Automatic license-plate recognition (ALPR)
Automatic license-plate reader (ALPR)
Automatic vehicle identication (AVI)
Concerns about these systems have centered on privacy fears of government tracking citizens movements,
misidentication, high error rates, and increased government spending.
Car plate recognition (CPR)
License-plate recognition (LPR)
Lecture
automatique
d'immatriculation (LAPI)
Etymology
de
plaques
Mobile license-plate reader (MLPR)
Vehicle license-plate recognition (VLPR)
ANPR is sometimes known by various other terms:
1
4 TECHNOLOGY
Development history
ANPR was invented in 1976 at the Police Scientic Development Branch in the UK. Prototype systems were
working by 1979, and contracts were let to produce industrial systems, rst at EMI Electronics, and then at Computer Recognition Systems (CRS) in Wokingham, UK.
Early trial systems were deployed on the A1 road and at
the Dartford Tunnel. However it did not become widely
used until new developments in cheaper and easier to use
software was pioneered during the 1990s. The rst arrest through detection of a stolen car was made in 1981
and the rst documented case of ANPR in helping solve
a murder occurred in November 2005 after the murder
of Sharon Beshenivsky, in which City of Bradford based The font on Dutch plates was changed to improve plate recognition.
ANPR played a vital role in locating and subsequently
convicting her killers.[4]
with such dierences in order to be truly eective. More
complicated systems can cope with international variants,
though many programs are individually tailored to each
3 Components
country.
The software aspect of the system runs on standard home
computer hardware and can be linked to other applications or databases. It rst uses a series of image manipulation techniques to detect, normalize and enhance
the image of the number plate, and then optical character
recognition (OCR) to extract the alphanumerics of the
license plate. ANPR systems are generally deployed in
one of two basic approaches: one allows for the entire
process to be performed at the lane location in real-time,
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. When done
at the lane site, the information captured of the plate alphanumeric, date-time, lane identication, and any other
information required is completed in approximately 250
milliseconds. This information can easily be transmitted
to a remote computer for further processing if necessary,
or stored at the lane for later retrieval. In the other arrangement, there are typically large numbers of PCs used
in a server farm to handle high workloads, such as those
found in the London congestion charge project. Often in
such systems, there is a requirement to forward images to
the remote server, and this can require larger bandwidth
transmission media.
Technology
ANPR uses optical character recognition (OCR) on images taken by cameras. When Dutch vehicle registration
plates switched to a dierent style in 2002, one of the
changes made was to the font, introducing small gaps in
some letters (such as P and R) to make them more distinct and therefore more legible to such systems. Some
license plate arrangements use variations in font sizes
and positioningANPR systems must be able to cope
The cameras used can include existing road-rule enforcement or closed-circuit television cameras, as well as mobile units, which are usually attached to vehicles. Some
systems use infrared cameras to take a clearer image of
the plates.[5][6][7][8][9] [10] [11][12][13][14]
4.1 ANPR in mobile systems
The Dubai police use ANPR cameras to monitor vehicles in front
and either side of the patrol car
During the 1990s, signicant advances in technology
took automatic number plate recognition (ANPR) systems from limited expensive, hard to set up, xed based
applications to simple point and shoot mobile ones.
This was made possible by the creation of software that
ran on cheaper PC based, non-specialist hardware that
also no longer needed to be given the pre-dened angles,
direction, size and speed in which the plates would be
passing the cameras eld of view. Further scaled-down
components at more cost-eective price points led to a
record number of deployments by law enforcement agencies around the world. Smaller cameras with the ability
to read license plates at higher speeds, along with smaller,
5 Algorithms
A Merseyside Police car equipped with mobile ANPR.
Steps 2, 3 and 4: The license plate is normalized for brightness
more durable processors that t in the trunks of police and contrast, and then the characters are segmented to be ready
vehicles, allowed law enforcement ocers to patrol daily for OCR.
with the benet of license plate reading in real time, when
There are seven primary algorithms that the software rethey can interdict immediately.
quires for identifying a license plate:
Despite their eectiveness, there are noteworthy challenges related with mobile ANPRs. One of the biggest is
1. Plate localization responsible for nding and isothat the processor and the cameras must work fast enough
lating the plate on the picture.
to accommodate relative speeds of more than 100 mph
(160 km/h), a likely scenario in the case of oncoming
2. Plate orientation and sizing compensates for the
trac. This equipment must also be very ecient since
skew of the plate and adjusts the dimensions to the
the power source is the vehicle battery, and equipment
required size.
must be small to minimize the space it requires.
3. Normalization adjusts the brightness and contrast
Relative speed is only one issue that aects the cameras
of the image.
ability to actually read a license plate. Algorithms must be
4. Character segmentation nds the individual charable to compensate for all the variables that can aect the
acters on the plates.
ANPRs ability to produce an accurate read, such as time
of day, weather and angles between the cameras and the
5. Optical character recognition.
license plates. A systems illumination wavelengths can
also have a direct impact on the resolution and accuracy
6. Syntactical/Geometrical analysis check characters
of a read in these conditions.
and positions against country-specic rules.
Installing ANPR cameras on law enforcement vehicles
requires careful consideration of the juxtaposition of the
cameras to the license plates they are to read. Using
the right number of cameras and positioning them accurately for optimal results can prove challenging, given
the various missions and environments at hand. Highway patrol requires forward-looking cameras that span
multiple lanes and are able to read license plates at very
high speeds. City patrol needs shorter range, lower focal
length cameras for capturing plates on parked cars. Parking lots with perpendicularly parked cars often require a
specialized camera with a very short focal length. Most
technically advanced systems are exible and can be congured with a number of cameras ranging from one to
four which can easily be repositioned as needed. States
with rear-only license plates have an additional challenge
since a forward-looking camera is ineective with oncoming trac. In this case one camera may be turned
backwards.
7. The averaging of the recognised value over multiple
elds/images to produce a more reliable or condent
result. Especially since any single image may contain a reected light are, be partially obscured or
other temporary eect.
The complexity of each of these subsections of the program determines the accuracy of the system. During the
third phase (normalization), some systems use edge detection techniques to increase the picture dierence between the letters and the plate backing. A median lter
may also be used to reduce the visual noise on the image.
6 Diculties
There are a number of possible diculties that the software must be able to cope with. These include:
IMAGING HARDWARE
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.
Early ANPR systems were unable to read white or silver lettering
on black background, as permitted on UK vehicles built prior to
1973.
Swedish license plate
On some cars, tow bars may obscure one or two characters of the license plate. Bikes on bike racks can also
obscure the number plate, though in some countries and
jurisdictions, such as Victoria, Australia, bike plates are
supposed to be tted. Some small-scale systems allow for
some errors in the license plate. When used for giving
specic vehicles access to a barricaded area, the decision
may be made to have an acceptable error rate of one character. This is because the likelihood of an unauthorized
car having such a similar license plate is seen as quite
small. However, this level of inaccuracy would not be
acceptable in most applications of an ANPR system.
7 Imaging hardware
Must be able to recognize
international license plates as such.
At the front end of any ANPR system is the imaging hardware which captures the image of the license plates. The
initial image capture forms a critically important part of
the ANPR system which, in accordance to the garbage in,
garbage out principle of computing, will often determine
the overall performance.
License plate capture is typically performed by specialized cameras designed specically for the task, although
new software techniques are being implemented that supPoor le resolution, usually because the plate is too port any I.P.-based surveillance camera and increase the
far away but sometimes resulting from the use of a utility of ANPR for perimeter security applications. Faclow-quality camera.
tors which pose diculty for license plate imaging cameras include the speed of the vehicles being recorded,
Blurry images, particularly motion blur.
varying level of ambient light, headlight glare and harsh
Poor lighting and low contrast due to overexposure, environmental conditions. Most dedicated license plate
capture cameras will incorporate infrared illumination in
reection or shadows.
order to solve the problems of lighting and plate reecAn object obscuring (part of) the plate, quite often tivity.
a tow bar, or dirt on the plate.
Read license plates that are dierent at the front and
the back because of towed trailers, campers, etc.
Vehicle lane change in the cameras angle of view
during license plate reading.
A dierent font, popular for vanity plates (some
countries do not allow such plates, eliminating the
problem).
Circumvention techniques.
Lack of coordination between countries or states. Portable trac enforcement system used by the Hungarian police.
Two cars from dierent countries or states can have The rows of infrared LEDs are visible on the right.
the same number but dierent design of the plate.
Many countries now use license plates that are
While some of these problems can be corrected within retroreective.[15] This returns the light back to the
the software, it is primarily left to the hardware side of source and thus improves the contrast of the image. In
the system to work out solutions to these diculties. In- some countries, the characters on the plate are not recreasing the height of the camera may avoid problems ective, giving a high level of contrast with the reective
5
background in any lighting conditions. A camera that
makes use of active infrared imaging (with a normal
colour lter over the lens and an infrared illuminator
next to it) benets greatly from this as the infrared waves
are reected back from the plate. This is only possible
on dedicated ANPR cameras, however, and so cameras
used for other purposes must rely more heavily on the
software capabilities. Further, 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.
ne of up to US $2,000 and 180 days in jail) if it can
be proven that the owner did it to deliberately obscure
their plates.[18] The law was later claried in 2007 to allow
Novelty frames.
If an ANPR system cannot read the plate, it can ag the
image for attention, with the human operators looking to
see if they are able to identify the alphanumerics.
In order to avoid surveillance or penalty charges, there has
been an upsurge in car cloning. This is usually achieved
by copying registration plates from another car of a similar model and age. This can be dicult to detect, espeTo avoid blurring it is ideal to have the shutter speed of a cially as cloners may change the registration plates and
dedicated camera set to 1/1000 of a second. It is also im- travel behavior to hinder investigations.
portant that the camera uses a global shutter, as opposed
to rolling shutter, to assure that the taken images are In 2013 researchers at Sunex Zone Ltd created a privacy
distortion-free. Because the car is moving, slower shut- license plate frame that uses near infrared light to make
ter speeds could result in an image which is too blurred the license plate unreadable to license plate recognition
[19]
to read using the OCR software, especially if the camera systems.
is much higher up than the vehicle. In slow-moving trafc, or when the camera is at a lower level and the vehicle
is at an angle approaching the camera, the shutter speed 9 Police enforcement
does not need to be so fast. Shutter speeds of 1/500 of
a second can cope with trac moving up to 40 mph (64
km/h) and 1/250 of a second up to 5 mph (8 km/h). License plate capture cameras can produce usable images
from vehicles traveling at 120 mph (190 km/h).
To maximize the chances of eective license plate capture, installers should carefully consider the positioning of
the camera relative to the target capture area. Exceeding
threshold angles of incidence between camera lens and
license plate will greatly reduce the probability of obtaining usable images due to distortion. Manufacturers have
developed tools to help eliminate errors from the physical
installation of license plate capture cameras.
Circumvention techniques
Mobile ANPR cameras tted to a New South Wales Police Force
Highway Patrol vehicle.
Vehicle owners have used a variety of techniques in an attempt to evade ANPR systems and road-rule enforcement
cameras in general. One method increases the reective
properties of the lettering and makes it more likely that
the system will be unable to locate the plate or produce a
high enough level of contrast to be able to read it. This
is typically done by using a plate cover or a spray, though
claims regarding the eectiveness of the latter are disputed. In most jurisdictions, the covers are illegal and
covered under existing laws, while in most countries there
is no law to disallow the use of the sprays.[16][17] Other
users have attempted to smear their license plate with dirt
or utilize covers to mask the plate.
Novelty frames around Texas license plates were made
illegal in Texas on 1 September 2003 by Texas Senate Bill Closed-circuit television cameras such as these can be used to
439 because they caused problems with ANPR devices. take the images scanned by automatic number plate recognition
That law made it a Class C misdemeanor (punishable by systems
a ne of up to US $200), or Class B (punishable by a
9.1
POLICE ENFORCEMENT
Australia
Several State Police Forces, and the Department of Justice (Victoria)[20] use both xed and mobile ANPR systems. The New South Wales Police Force Highway Patrol
were the rst to trial and use a xed ANPR camera system
in Australia in 2005. In 2009 they began a roll-out of a
mobile ANPR system (known ocially as MANPR)[21]
with three infrared cameras tted to its Highway Patrol
eet.[22] The system identies unregistered and stolen vehicles as well as disqualied or suspended drivers as well
as other 'persons of interest' such as persons having out- Road gantry trac enforcement and data point on the M7 highway at rd, Hungary
standing warrants.[23]
9.2
Belgium
The city of Mechelen uses an ANPR system since
September 2011 to scan all cars crossing the city limits (inbound and outbound). Cars listed on 'black lists'
(no insurance, stolen, etc.) generate an alarm in the dispatching room, so they can be intercepted by a patrol. As
of early 2012, 1 million cars per week are automatically
checked in this way.[24]
9.3
Denmark
The technique is tested by the Danish police. It will be in
permanent use from the end of 2015.[25]
9.4
France
180 gantries over major roads have been built throughout the country. These together with a further 250 xed
cameras is to enable a levy of an eco tax on lorries over
3.5 tonnes. The system is currently being opposed and
whilst they may be collecting data on vehicles passing the
cameras, no eco tax is being charged.[26]
9.5
quarters and the Central Commission of Public Administration and Electronic Services with the aim to install
and operate a unied intelligent transportation system
(ITS) with nationwide coverage by the end of 2015.[29]
Within the system, 160 portable trac enforcement and
data-gathering units and 365 permanent gantry installations were brought online with ANPR, speed detection, imaging and statistical capabilities. Since all the
data points are connected to a centrally located ITS, each
member of the consortium is able to separately utilize its
range of administrative and enforcement activities, such
as remote vehicle registration and insurance verication,
speed, lane and trac light enforcement and wanted or
stolen vehicle interception among others.
Several Hungarian auxiliary police units also use a system
called Matrix Police[30] in cooperation with the police.
It consists of a portable computer equipped with a web
camera that scans the stolen car database using automatic
number plate recognition. The system is installed on the
dashboard of selected patrol vehicles (PDA-based handheld versions also exist) and is mainly used to control the
license plate of parking cars. As the Auxiliary Police do
not have the authority to order moving vehicles to stop, if
a stolen car is found, the formal police is informed.
Germany
On 11 March 2008, the Federal Constitutional Court of
Germany ruled that some areas of the laws permitting the
use of automated number plate recognition systems in
Germany violated the right to privacy.[27] More specifically, the court found that the retention of any sort of
information (i.e., number plate data) which was not for
any pre-destined use (e.g., for use tracking suspected terrorists or for enforcement of speeding laws) was in violation of German law. These systems were provided by
Jenoptik Robot GmbH, and called TraCapture.[28]
9.7 Turkey
Several cities have testedand some have put into
servicethe City Security Administration System, i.e.,
capital Ankara, has debuted KGYS- Kent Guvenlik Yonetim Sistemi which consists of a registration plate number recognition system on the main arteries and city
exits.[31] The system has been used with two cameras per
lane, one for plate recognition, one for speed detection.
Now the system has been widened to network all the registration number cameras together, and enforcing average
speed over preset distances. Some arteries have 70Kmh
limit, and some 50 kmh, and photo evidence with date9.6 Hungary
time details are posted to registration address if speed viIn 2012 a state consortium was formed among the Hun- olation is detected. As of 2012, the ne for exceeding the
garian Ministry of Interior, the National Police Head- speed limit for more than 30% is approximately US$175.
9.10
United States
9.8
Ukraine
The project of system integration OLLI Technology
and the Ministry of Internal Aairs of Ukraine Department of State Trac Inspection (STI) experiments on
the introduction of a modern technical complex which
is capable to locate stolen cars, drivers deprived of driving licenses and other problem cars in real time. The
Ukrainian complex Video control[32] working by a principle of video xing of the car with recognition of license
plates with check under data base.
9.9
United Kingdom
A City of Alexandria police car equipped with mobile ALPR.
ANPR cameras in operation on the Brooklyn Bridge in New York.
An ANPR Equipped Vectra of the Greater Manchester Police
force
Main article: Police-enforced ANPR in the UK
The UK has an extensive (ANPR) automatic number
plate recognition CCTV network. Eectively, the police
and security services track all car movements around the
country and are able to track any car in close to real time.
Vehicle movements are stored for 2 years in the National
ANPR Data Center to be analyzed for intelligence and to
be used as evidence.
In 1997 a system of one hundred ANPR cameras, codenamed GLUTTON, was installed to feed into the automated British Military Intelligence Systems in Northern Ireland. Further cameras were also installed on the
British mainland, including unspecied ports on the east
and west coasts.
9.10 United States
In the United States, ANPR systems are more commonly referred to as ALPR (Automatic License Plate
Reader/Recognition) technology, due to dierences in
language (i.e., number plates are referred to as license
plates in American English)
Mobile ANPR use is widespread among US law enforcement agencies at the city, county, state and federal level.
According to a 2012 report by the Police Executive Research Forum, approximately 71% of all US police departments use some form of ANPR.[33] Mobile ANPR
is becoming a signicant component of municipal predictive policing strategies and intelligence gathering,[34]
as well as for recovery of stolen vehicles, identication
of wanted felons, and revenue collection from individuals who are delinquent on city or state taxes or nes,
or monitoring for Amber Alerts. Successfully recognized plates may be matched against databases including wanted person, protection order, missing person,
gang member, known and suspected terrorist, supervised
release, immigration violator, and National Sex Oender
lists.[35] In addition to the real-time processing of license
plate numbers, ALPR systems in the US collect (and can
indenitely store) data from each license plate capture.
Images, dates, times and GPS coordinates can be stockpiled and can help place a suspect at a scene, aid in witness identication, pattern recognition or the tracking of
individuals.
An early, private sector mobile ANPR application
has been applications for vehicle repossession and
recovery[36] ), although the application of ANPR by private companies to collect information from privately
11
owned vehicles or collected from private property (for example, driveways) has become an issue of sensitivity and
public debate.[37] Other ALPR uses include parking enforcement, and revenue collection from individuals who
are delinquent on city or state taxes or nes. The technology is often featured in the reality TV show Parking Wars
featured on A&E Network. In the show, tow truck drivers
and booting teams use the ALPR to nd delinquent vehicles with high amounts of unpaid parking nes.
9.11 Saudi Arabia
Vehicle registration plates in Saudi Arabia use white
background, but several vehicle types may have a different background. United States diplomatic plates have
the letters 'USD', which in Arabic reads 'DSU' when
read from right to left in the direction of Arabic script.
There are only 17 Arabic letters used on the registration plates.[38] A Challenge for plates recognition in Saudi
Arabia is the size of the digits. Some plates use both
Eastern Arabic numerals and the 'Western Arabic' equivalents. A research with source code is available for APNR
Arabic digits.[39]
9.12 Sweden
CRIME DETERRENT
10.2 The Netherlands
Average speed cameras (trajectcontrole) are in place in
the Netherlands since 2002. As of July 2009, 12 cameras were operational, mostly in the west of the country
and along the A12.[47] Some of these are divided in several sections to allow for cars leaving and entering the
motorway.
A rst experimental system was tested on a short stretch
of the A2 in 1997 and was deemed a big success by the
police, reducing overspeeding to 0.66%, compared to 5
to 6% when regular speed cameras were used at the same
location.[49] The rst permanent average speed cameras
were installed on the A13 in 2002, shortly after the speed
limit was reduced to 80 km/h to limit noise and air pollution in the area.[50] In 2007, average speed cameras resulted in 1.7 million nes for overspeeding out of a total
of 9.7 millions. According to the Dutch Attorney General, the average number of violation of the speed limits on motorway sections equipped with average speed
cameras is between 1 and 2%, compared to 10 to 15%
elsewhere.[51]
10.3 UK
See also: Road speed limit enforcement in the United
Kingdom
The technique is tested by the Swedish police at nine dif- One of the most notable stretches of average speed camferent places in Sweden.[40]
eras in the UK is found on the A77 road in Scotland, with
32 miles (51 km) being monitored between Glasgow and
Ayr.[52] In 2006 it was conrmed that speeding tickets
could potentially be avoided from the 'SPECS' cameras
10 Average-speed cameras
by changing lanes and the RAC Foundation feared that
people may play Russian Roulette changing from one
lane to another to lessen their odds of being caught.[46]
Main article: Speed limit enforcement
However, in 2007 the system was upgraded for multi-lane
use and in 2008 the manufacturer described the myth
ANPR is used for speed limit enforcement in Australia,
as categorically untrue.[53] There exists evidence that
Austria,[41] Belgium,[42] Dubai (UAE), France, Italy,[43]
implementation of systems such as SPECS has a considThe Netherlands,[44] Spain,[45] and the UK.[46]
erable eect on the volume of drivers travelling at excesThis works by tracking vehicles travel time between two sive speeds; on the stretch of road mentioned above (A77
xed points, and calculating the average speed. These Between Glasgow and Ayr) there has been noted a huge
cameras are claimed to have an advantage over traditional drop in speeding violations since the introduction of a
speed cameras in maintaining steady legal speeds over ex- SPECS system.[52]
tended distances, rather than encouraging heavy braking
on approach to specic camera locations and subsequent
acceleration back to illegal speeds.[47]
11 Crime deterrent
Recent innovations have contributed to the adoption of
ANPR for perimeter security and access control applications at government facilities. Within the US, homeIn Italian Highways has developed a monitoring system land security eorts to protect against alleged acts of
named Tutor covering more than 2500 km (2012). The terrorism have resulted in adoption of ANPR for sensiTutor system is also able to intercept cars while changing tive facilities such as embassies, schools, airports, marlanes.[48]
itime ports, military and federal buildings, law enforce-
10.1
Italy
9
ment and government facilities, and transportation centers. ANPR is marketed as able to be implemented
through networks of IP based surveillance cameras that
perform double duty alongside facial recognition, object tracking, and recording systems for the purpose of
monitoring suspicious or anomalous behavior, improving
access control, and matching against watch lists. ANPR
systems are most commonly installed at points of significant sensitivity, ingress or egress. Major US agencies
such as the Department of Homeland Security, the Department of Justice, the Department of Transportation
and the Department of Defense have purchased ANPR
for perimeter security applications.[54] Large networks
of ANPR systems are being installed by cities such as
Boston, London and New York City to provide citywide
protection against acts of terrorism, and to provide support for public gatherings and public spaces.[55]
12
Enterprise security and services
In addition to government facilities, many private sector
industries with facility security concerns are beginning to
implement ANPR solutions. Examples include casinos,
hospitals, museums, parking facilities, and resorts.[56] In
the US, private facilities typically cannot access government or police watch lists, but may develop and match
against their own databases for customers, VIPs, critical
personnel or banned person lists. In addition to providing perimeter security, private ANPR has service applications for valet / recognized customer and VIP recognition, logistics and key personnel tracking, sales and advertising, parking management, and logistics (vendor and
support vehicle tracking).
13
Trac control
volved looking at historical data, estimates, observations
and statistics, such as:
Car park usage
Pedestrian crossing usage
Number of vehicles along a road
Areas of low and high congestion
Frequency, location and cause of road works
CCTV cameras can be used to help trac control centres
by giving them live data, allowing for trac management
decisions to be made in real-time. By using ANPR on
this footage it is possible to monitor the travel of individual vehicles, automatically providing information about
the speed and ow of various routes. These details can
highlight problem areas as and when they occur and help
the centre to make informed incident management decisions.
Some counties of the United Kingdom have worked with
Siemens Trac to develop trac monitoring systems for
their own control centres and for the public.[57] Projects
such as Hampshire County Councils ROMANSE provide an interactive and real-time web site showing details about trac in the city. The site shows information about car parks, ongoing road works, special events
and footage taken from CCTV cameras. ANPR systems
can be used to provide average point-to-point journey
times along particular routes, which can be displayed on
a variable-message sign(VMS) giving drivers the ability
to plan their route. ROMANSE also allows travellers to
see the current situation using a mobile device with an
Internet connection (such as WAP, GPRS or 3G), allowing them to view mobile device CCTV images within the
Hampshire road network.
The UK company Tracmaster has used ANPR since
1998 to estimate average trac speeds on non-motorway
roads without the results being skewed by local uctuations caused by trac lights and similar. The company
now operates a network of over 4000 ANPR cameras, but
claims that only the four most central digits are identied,
and no numberplate data is retained.[58][59][60]
IEEE transactions on Intelligent Transportation
Systems(IEEE Intelligent Transportation Systems
Society) published some papers on the plate number recognition technologies and applications.
14 Electronic toll collection
Video tolling at Schnberg, Austria
14.1 Toll roads
Many cities and districts have developed trac control Ontario's 407 ETR highway uses a combination of ANPR
systems to help monitor the movement and ow of ve- and radio transponders to toll vehicles entering and exithicles around the road network. This had typically in- ing the road. Radio antennas are located at each junction
10
14 ELECTRONIC TOLL COLLECTION
Saint John, New Brunswick
Quickpass[63] at the Golden Ears Bridge, crossing
the Fraser River between Langley and Maple Ridge
CityLink & Eastlink in Melbourne, Australia
Gateway Motorway and Logan Motorway, Brisbane,
Australia
FasTrak in California, United States
Highway 6 in Israel
The FasTrak system in Orange County uses ANPR and radio
transponders
Tunnels in Hong Kong
Autopista Central[64] in Santiago, Chile (site in
Spanish)
E-ZPass in New York, New Jersey, Massachusetts
(as Fast Lane until 2012), Virginia (formerly Smart
Tag), and other states. Maryland Route 200 uses a
combination of E-ZPass and ANPR.
TollTag in North Texas and EZ-Tag in Houston,
Texas.
I-Pass in Illinois
Pike Pass in Oklahoma
Peach Pass I-85 Atlanta, GA Gwinnett County
Film showing the approach to and passing of a toll station in Italy,
using a Telepass OBU. Note the yellow Telepass lane signs and
road markings and the sound emitted by the OBU when passing
the lane
OGS (Otomatik Gei Sistemi) used at Bosphorus
Bridge, Fatih Sultan Mehmet Bridge, and Trans European Motorway entry points in stanbul, Turkey
M50 Westlink Toll in Dublin, Ireland
Hi-pass in South Korea
and detect the transponders, logging the unique identity
Northern Gateway, SH 1, Auckland, New Zealand
of each vehicle in much the same way as the ANPR system does. Without ANPR as a second system it would not
Evergreen Point Floating Bridge, Seattle, and
be possible to monitor all the trac. Drivers who opt to
Washington State Route 167 HOT-lanes in western
rent a transponder for C$2.55 per month are not charged
Washington
the Video Toll Charge of C$3.60 for using the road,
with heavy vehicles (those with a gross weight of over
ETC[65] in Taiwan
5,000 kg) being required to use one. Using either system,
users of the highway are notied of the usage charges by
14.2 Portugal
post.
There are numerous other electronic toll collection netPortuguese roads have old highways with toll station
works which use this combination of Radio frequency
where drivers can pay with cards and also lanes where
identication and ANPR. These include:
there are electronic collection systems. However most
new highways only have the option of electronic toll col The Golden Gate Bridge in San Francisco, Cal- lection system. The electronic toll collection system comifornia, began using an all-electronic tolling sys- prises three dierent structures: ANPR which works
tem combining Fastrak and ANPR on March 27, with infrared cameras and reads license plates from ev2013.[61]
ery vehicle Lasers to measure the volumetry of the vehi NC Quick Pass for the Interstate 540 (North Car- cle to conrm whether it is a regular car or if it is a SUV
olina) Triangle Expressway in Wake County, North or truck as charges are very dierent RFID-like to read
smart tags that cars can have installed. When the smart
Carolina
tag is installed, the car is quickly identied and owners
Bridge Pass[62] for the Saint John Harbour Bridge in bank account is automatically deducted. This process is
14.4
Sweden
realized at any speed up to over 250 km per hour. If the
car does not have the smart tag, the driver is required to
go to a pay station to pay the tolls between 3rd and 5th
day after with a surplus charge. If he fails to do so, the
owner is sent a letter home with a heavy ne. If this is
not paid, it increases ve-fold and after that, the car is
inserted into a police database for vehicle impounding.
This system is also used in some limited access areas of
main cities to allow only entry from pre-registered residents. It is planned to be implemented both in more roads
and in city entrance toll collection/access restriction. The
ecacy of the system is considered to be so high that it
is almost impossible for the driver to complain.
11
Both front and back number plates are being captured,
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. 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 ned. The registered owner of such a vehicle is looked up in a database
provided by the DVLA.[67]
14.4 Sweden
In Stockholm, Sweden, ANPR is used for the Stockholm
congestion tax, owners of cars driving into or out of the
See also: List of electronic toll collection systems
inner city must pay a charge, depending on the time of
the day. From 2013, also for the Gothenburg congestion
tax, which also includes vehicles passing the city on the
14.3 Charge zones the London conges- main highways.
tion charge
15 Usage
Several UK companies and agencies use ANPR systems.
These include Vehicle and Operator Services Agency (VOSA),[68] Driver and Vehicle Licensing
Agency (DVLA)[69] and Transport for London.[70]
16 Challenges
16.1 Controversy
The introduction of ANPR systems has led to fears
of misidentication and the furthering of 1984-style
surveillance.[71] In the United States, some such as Gregg
Easterbrook oppose what they call machines that issue
The London congestion charge is an example of a system speeding tickets and red-light tickets as the beginning
that charges motorists entering a payment area. Transport of a slippery slope towards an automated justice system:
for London (TfL) uses ANPR systems and charges motorists a daily fee of 10 paid before 10pm if they enter,
A machine classies a person as an oender,
leave or move around within the congestion charge zone
and you can't confront your accuser because
between 7 a.m. and 6:00 p.m., Monday to Friday. A rethere is no accuser... can it be wise to esduced fee of 9 is paid by vehicle owners who sign up
tablish a principle that when a machine says
for the automatic deduction scheme. Fines for traveling
you did something illegal, you are presumed
within the zone without paying the charge are 60 per inguilty?"[72]
fraction if paid before the deadline, doubling to 120 per
infraction thereafter.
Similar criticisms have been raised in other countries.
There are currently 1,500 cameras which use automatic Easterbrook also argues that this technology is employed
number plate recognition (ANPR) technology.[66] There to maximize revenue for the state, rather than to proare also a number of mobile camera units which may be mote safety.[72] The electronic surveillance system prodeployed anywhere in the zone.
duces tickets which in the US are often in excess of $100,
It is estimated that around 98% of vehicles moving within and are virtually impossible for a citizen to contest in
the zone are caught on camera. The video streams are court without the help of an attorney. The revenues gentransmitted to a data centre located in central London erated by these machines are shared generously with the
where the ANPR software deduces the registration plate private corporation that builds and operates them, creatof the vehicle. A second data centre provides a backup ing a strong incentive to tweak the system to generate as
location for image data.
many tickets as possible.
The London congestion charge scheme uses 230 cameras and
ANPR to help monitor vehicles in the charging zone
12
Older systems had been notably unreliable; in the UK this
has been known to lead to charges being made incorrectly
with the vehicle owner having to pay 10 in order to be
issued with proof (or not) of the oense. Improvements
in technology have drastically decreased error rates, but
false accusations are still frequent enough to be a problem.
Perhaps the best known incident involving the abuse of an
ANPR database in North America is the case of Edmonton Sun reporter Kerry Diotte in 2004. Diotte wrote an
article critical of Edmonton police use of trac cameras
for revenue enhancement, and in retaliation was added
to an ANPR database of high-risk drivers in an attempt to monitor his habits and create an opportunity
to arrest him.[73][74][75] The police chief and several ofcers were red as a result, and The Oce of the Privacy Commissioner of Canada expressed public concern
over the growing police use of technology to spy on
motorists.[76]
16
In 2013 the American Civil Liberties Union released
26,000 pages of data about ANPR systems obtained from
local, state, and federal agencies through freedom of information laws. The documents paint a startling picture of a technology deployed with too few rules that is
becoming a tool for mass routine location tracking and
surveillance wrote the ACLU. The ACLU reported that
in many locations the devices were being used to store location information on vehicles which were not suspected
of any particular oense. Private companies are also using license plate readers and sharing the information they
collect with police with little or no oversight or privacy
protections. A lack of regulation means that policies governing how long our location data is kept vary widely, the
ACLU said.[91] In 2012 the ACLU led suit against the
Department of Homeland Security, which funds many local and state ANPR programs through grants, after the
agency failed to provide access to records the ACLU had
requested under the Freedom of Information Act about
the programs.[92]
Other concerns include the storage of information that
could be used to identify people and store details about
their driving habits and daily life, contravening the
Data Protection Act along with similar legislation (see
personally identiable information). The laws in the UK
are strict for any system that uses CCTV footage and can
identify individuals.[77][77][78][79][80][81][82][83][84]
16.2
Also of concern is the safety of the data once it is mined,
following the discovery of police surveillance records lost
in a gutter.[85][86]
There is also a case in the UK for saying that use of ANPR
cameras is against the law under the Regulation of Investigatory Powers Act 2000.[87] The breach exists, some say,
in the fact that ANPR is used to monitor the activities
of law-abiding citizens and treats everyone like the suspected criminals intended to be surveyed under the act.
The police themselves have been known to refer to the
system of ANPR as a 24/7 trac movement database
which is a diversion from its intended purpose of identifying vehicles involved in criminal activities.[88] The opposing viewpoint is that where the plates have been cloned,
a 'read' of an innocent motorists vehicle will allow the
elimination of that vehicle from an investigation by visual examination of the images stored. Likewise, stolen
vehicles are read by ANPR systems between the time of
theft and report to the Police, assisting in the investigation.
The Associated Press reported in August 2011 that New
York Police Department cars and license plate tracking
equipment purchased with federal HIDTA (High Intensity Drug Tracking Area) funds were used to spy on
Muslims at mosques, and to track the license plate numbers of worshipers. [89] Police in unmarked cars outtted with electronic license plate readers would drive down
the street and automatically catalog the plates of everyone
parked near the mosque, amassing a covert database that
would be distributed among ocers and used to prole
Muslims in public.[90]
CHALLENGES
Plate inconsistency and jurisdictional
dierences
Many ANPR systems claim accuracy when trained to
match plates from a single jurisdiction or region, but can
fail when trying to recognize plates from other jurisdictions due to variations in format, font, color, layout, and
other plate features.[93] Some jurisdictions oer vanity or
anity plates (particularly in the US), which can create
many variations within a single jurisdiction.[94]
From time to time, US states will make signicant
changes in their license plate protocol that will aect
OCR accuracy. They may add a character or add a new
license plate design. ALPR systems must adapt to these
changes quickly in order to be eective. Another challenge with ALPR systems is that some states have the
same license plate protocol. For example, more than
one state uses the standard three letters followed by four
numbers. So each time the ALPR systems alarms, it is
the users responsibility to make sure that the plate which
caused the alarm matches the state associated with the license plate listed on the in-car computer. For maximum
eectiveness, an ANPR system should be able to recognize plates from any jurisdiction, and the jurisdiction to
which they are associated, but these many variables make
such tasks dicult.
Currently at least one US ANPR provider (PlateSmart)
claims their system has been independently reviewed
as able to accurately recognize the US state jurisdiction of license plates, and one European ANPR
provider claims their system can dierentiate all EU plate
jurisdictions.[95][96]
13
16.3
Accuracy and measurement of ANPR 18
system performance
A 2008 article in Parking Trend International discussed a
disparity in claimed vs. experienced license plate recognition read rates, with manufacturers claiming that their
recognition engines can correctly report 98% of the time,
although customers experience only 90% to 94% success,
even with new equipment under perfect conditions. Early
systems were reportedly only 60% to 80% reliable.[97]
True system error rate is the product of its subsystem error rates (image capture, license plate image extraction,
LP image interpretation); slight increases in subsystem
error rates can produce dramatic reductions of read rates.
The eects of real-world interfering factors on read rate
are not uniformly specied or tested by manufacturers.
The article states there is a need for the industry to adopt
a standard performance measurement protocol to enable
potential customers assess the best t for their particular
requirements.[97]
Related research society
IEEE Intelligent Transportation Systems Society
19 See also
AI eect
Applications of articial intelligence
Closed circuit television
Facial recognition system
Parking lot
Road Policing Unit
SPECS (speed camera)
Vehicle location data
Lists
17
Other uses
ANPR systems may also be used for/by:
Section control, to measure average vehicle speed
over longer distances.[98]
Border crossings
Automobile repossessions[36][99]
petrol stations to log when a motorist drives away
without paying for their fuel.
A marketing tool to log patterns of use
Targeted advertising, a-la Minority Report-style
billboards.[100][101]
Trac management systems, which determine trafc ow using the time it takes vehicles to pass two
ANPR sites[102]
Analyses of travel behaviour (route choice,
origin-destination etc.)
for transport planning
purposes[103][104]
Drive Through Customer Recognition, to automatically recognize customers based on their license
plate and oer them the items they ordered the last
time they used the service.
To assist visitor management systems in recognizing
guest vehicles.
Police and Auxiliary Police
Car parking companies
Hotels
List of emerging technologies
Outline of articial intelligence
20 References
[1] ANPR Tutorial. ANPR Tutorial. 15 August 2006. Retrieved 2012-01-24.
[2] Shan Du ; IntelliView Technol., Inc., Calgary, AB,
Canada ; Ibrahim, M. ; Shehata, M. ; Badawy, Wael; Automatic License Plate Recognition (ALPR): A State-ofthe-Art Review. IEEE. 1 Feb 2013. Retrieved 2014-0109.
[3] An introduction to ANPR.
Retrieved 2012-01-24.
Cctv-information.co.uk.
[4] CCTV network tracks 'getaway' car. BBC News. 21
November 2005. Retrieved 2013-08-12.
[5] Plate Recognition. PhotoCop.com.
[6] Algorithm for License Plate Recognition. VISL, Technion. 2002.
[7] A Real-time vehicle License Plate Recognition (LPR)".
VISL, Technion, 2003
[8] An Approach To License Plate Recognition (PDF).
University of Calgary. 1996. Retrieved 2012-01-24.
[9] Draghici, Sorin (1997). A neural network based articial
vision system for license plate recognition (PDF). Dept.
of Computer Science, Wayne State University. Retrieved
2012-01-24.
[10] License Plate Recognition in Turkey (Plaka Okuma Sistemi)". Grimedia.com. Retrieved 2012-01-24.
14
20
REFERENCES
[11] Kwanicka, Halina; Wawrzyniak, Bartosz (2002),
License plate localization and recognition in camera
pictures (PDF), AI-METH 2002 Articial Intelligence
Methods November 1315 (Gliwice, Poland), retrieved
2014-01-13
[29] VDA Kzti Intelligens Kamerahlzat (in Hungarian). Orszgos Rendr-fkapitnysg. Retrieved 201509-02.
[12] Kahraman, Fatih; Gokmen, Muhittin (2003). License
Plate Character Segmentation Based on the Gabor Transform and Vector Quantization (PDF). Archived from the
original (PDF) on 2006-05-24. Retrieved 2012-01-24.
[31] Turk Telekom deploys trac surveillance service in
Ankara. Telecompaper. 2010-12-09. Retrieved 201208-03.
[13] Ondrej Martinsky (2007). Algorithmic and mathematical principles of automatic number plate recognition systems (PDF). Brno University of Technology. Retrieved
2012-01-24.
[14] A License Plate Recognition algorithm for Intelligent
Transportation System applications. University of the
Aegean and National Technical University of Athens.
2006. Archived from the original on 2008-04-20. Retrieved 2012-01-24.
[15] Automatic Number Plate Recognition.
information.co.uk. Retrieved 2012-01-24.
Cctv-
[16] Sexton, Steve (3 July 2003). License-plate spray foils
trac cameras. Washington Times. Retrieved 2013-0702.
[30] Matrix Police. Hungary. Retrieved 2012-01-24.
[32] Video control. Ukraine: Ollie.com.ua.
[33] How are Innovations in Technology Transforming Policing?" (PDF). Police Executive Research Forum. January
2012.
[34] Cameras for insurance verication considered. Tulsa
World. 29 November 2009.
[35] License Plate Reader Technology Enhances the Identication, Recovery of Stolen Vehicles. FBI. September
2011.
[36] Belson, Ken (28 February 2010). The Wired Repo Man:
Hes Not As Seen on TV". New York Times. Retrieved
2012-01-24.
[37] License plate data not just for cops: Private companies
are tracking your car. NBC News. 19 July 2013.
[17] Sexton, Steve (3 July 2003). License-plate spray foils
trac cameras. Washington Times. Retrieved 2013-0702.
[38] Vehicle registration plates of Saudi Arabia
[18] Wentworth, Je. Obscured license plate could be motorists ticket to ne. Texas State Senate. Archived from
the original on 24 March 2005. Retrieved 5 April 2005.
[40] Polisens nya vapen: Terminator"-teknik. Sweden: Expressen.se.
[20]
[43] Ecco come funziona il Tutor in autostrada - Notizie brevi
- News - Informazione - A.S.A.P.S. Il Portale della Sicurezza Stradale. Asaps.it. Retrieved 2012-08-03.
[39] Arabic Licence Plate Recognition. Sourceforge.
[41] Section Control: 24.000 Raser angezeigt (in German).
Austria: ORF.at. 7 June 2010.
[19] http://www.sunflexzone.com/product/
stealth-anti-tracking-ir-infrared-license-plate-blocker-privacy-frame-alpr-countermeasure#
[42] Flitsers.net.
.VVrj2kbEnrg
[21] eTendering - Contract Award Notice Detail View 01092010RFT. Tenders.nsw.gov.au. Retrieved 201404-23.
[22] http://www.police.nsw.gov.au/__data/assets/pdf_file/
0008/184886/Annual_Report_-_Year_in_Review.pdf
[23] Hoctor, Michelle (2012-06-06). Mass surveillance system nicks drivers. Illawarra Mercury. Retrieved 201404-23.
[24] ANPR in Mechelen. Belgium.
[25] Politiet vil tjekke millioner af danske nummerplader.
Denmark: B.dk.
[26] Portiques cotaxe.
Ils copient la plaque
dimmatriculation de Hollande. OuestFrance. OuestFrance. Retrieved 21 Feb 2014.
[27] Das Bundesverfassungsgericht (in German). Bverfg.de.
3 November 2008. Retrieved 2009-02-16.
[28] TraCapture. Jenoptic.com.
[44] Description of the system (in Dutch). Dutch Attorney
General. 31 December 2009. Retrieved 2012-01-24.
[45] Llegan los radares de velocidad media a Espaa (in
Spanish). Noticias.coches.com. 23 September 2009. Retrieved 2012-01-24.
[46] Speeding tickets can potentially be avoided by changing
lanes. The Daily Mail (London). 15 October 2006. Retrieved 2012-01-24. The Home Oce admitted last night
that drivers can avoid being caught the by hi-tech 'SPECS'
cameras which calculate a cars average speed over a long
distance.
[47] Frequently Asked Question over Trajectcontrole (in
Dutch). Dutch Attorney General. Retrieved 2012-01-24.
[48] Autostrade S.p.A (in Italian). Autostrade.it. 2008-0525. Retrieved 2012-08-03.
[49] Niemand rijdt meer te hard op de A2 (in Dutch). Trouw.
18 October 1997. Retrieved 2012-01-24.
15
[50] Nummerborden lezen op de A13 (in Dutch). Trouw. 6
May 2002. Retrieved 2012-01-24.
[71] Mathieson, SA (19 June 2003). Keeping 1984 in the
past. The Guardian (UK).
[51] Kreling, Tom (28 August 2008). Een duur foutje van
de computer (in Dutch). NRC Handelsblad. Retrieved
2012-01-24.
[72] Easterbrook, Gregg (28 February 2005). Daily Express
- Lights, Camera, Action. The New Republic Online.
Archived from the original on 2005-09-03.(subscription
required)
[52] SPECS - average speed cameras on SPECS.
A77safetygroup.com.
14 July 2005.
Retrieved
2012-01-24.
[73] Edmonton ocer reprimanded for checking up on newspaper columnist. CBC News. 14 November 2005.
[53] Jeremy Clarkson tilts at windmills Speed camera avoidance is an urban myth. The Register. 21 July 2008. Retrieved 23 January 2012.
[74] CBC Edmonton - Features - Edmonton Police. CBC
News. Archived from the original on 2007-10-23. Retrieved 2 July 2013.
[54] base-security-and-investigations/ US Navy Selects
PlateSmart Exclusively to Help with Base Security
and Investigations Check |url= scheme (help). Defense
Procurement News. 4 March 2013.
[75] Ocer faces suspension for Overtime sting. Edmonton
Police Watch. 6 September 2008. Retrieved 2012-01-24.
[55] After Boston: The pros and cons of surveillance cameras. CNN Tech. 26 April 2013.
[56] License Plate Recognition, Tribal Casinos, and Banned
Persons (PDF). Indiangaming.com. February 2011.
[57] Recognising a new way to keep trac moving. Siemenstrac.com. Retrieved 2012-01-24.
[58] PIPS supplies Journey Time Measurement Systems to
Tracmaster. PIPS Technology. Archived from the
original on 2009-01-24. Retrieved 2012-01-24.
[59] BLURA License Plate Recognition Engine. Blura.com.
Retrieved 2012-01-24.
[60] Trunk Roads PTFM. Tracmaster.co.uk. Retrieved
2012-01-24.
[61] Hansen, Megan and Will Jason (27 Mar 2013). Golden
Gate Bridge sees smooth transition to all-electronic tolls.
Marin Independent Journal. Retrieved 17 May 2013.
[62] HugeDomains.com - SaintjohnHarbourBridge.com is for
Sale. Saintjohn Harbour Bridge. Retrieved 2014-04-23.
[63] http://www.translink.ca/en/Driving/
Golden-Ears-Bridge.aspx
[64] autopistacentral.cl. autopistacentral.cl. 2014-01-22.
Retrieved 2014-04-23.
[65] "
23.
". Fetc.net.tw. 2006-02-10. Retrieved 2014-04-
[66] Met given real time c-charge data. BBC. 17 July 2007.
Archived from the original on 13 September 2007. Retrieved 2007-09-20.
[67] Transport for London. Cclondon.com. 17 July 2011.
Retrieved 2012-01-24.
[68] vosa.gov.uk
[69] https://www.gov.uk/government/organisations/
driver-and-vehicle-licensing-agency
[70] cclondon.com
[76] Canada: Privacy Commissioner Concerned Over License Plate Spying. Thenewspaper.com. 3 July 2007.
Retrieved 2012-01-24.
[77] Lettice, John (21 February 2003). The London charge
zone, the DP Act, and MS .NET. London: The Register.
Retrieved 2012-01-24.
[78] ANPR Strategy for the Police Service 2005/2006.
ACPO (Association of Chief Police Ocers) ANPR
Steering Group. 17 March 2005. Archived from the original on 2010-03-31. Retrieved 2012-01-24.
[79] Driving crime down (PDF). London: UK Government
Home Oce. 22 October 2004. Archived from the original (PDF) on 2007-01-08. Retrieved 2013-07-02.
[80] Constant, Mike. ANPR. CCTV Information. Archived
from the original on 21 March 2005. Retrieved 30 March
2005.
[81] Hofman, Yoram. License Plate Recognition A Tutorial. Archived from the original on 24 March 2005. Retrieved 28 March 2005.
[82] Lucena, Raul (24 August 2006). Automatic Number
Plate Recognition Tutorial. ANPR-tutorial.com.
[83] Lettice, John (24 March 2005). No hiding place?
UK number plate cameras go national. The Register.
Archived from the original on 28 March 2005. Retrieved
28 March 2005.
[84] Recognizing a new way to keep trac moving. Siemens
Trac. Archived from the original on 17 April 2005. Retrieved 3 April 2005.
[85] UK: Trac Camera Data Dropped in Gutter. thenewspaper.com. Retrieved 2012-01-24.
[86] Clements, Jon (11 March 2008). A police memory stick
containing secret data is found in gutter. The Mirror
(UK). Retrieved 2013-07-02.
[87] Regulation of Investigatory Powers Act 2000. legislation.gov.uk. The National Archives. 2000. Retrieved
2012-01-24.
[88] Police number plate cameras may breach RIPA - Commissioner. TheRegister.com. 17 July 2006. Retrieved
2012-01-24.
16
[89] Money for nothing: the drug war and the war on Muslims.
[90] Green, Jonah (24 February 2012). NYPD Defends Tactics Over Mosque Spying; Records Reveal New Details
On Muslim Surveillance. Hungton Post.
[91] ACLU raises privacy concerns about police technology
tracking drivers - CNN.com. CNN. 18 July 2013.
[92] Klein, Allison (26 September 2012). ACLU les suit
over info on license plate readers. The Washington Post.
[93] Automated License Plate Recognition Systems: Policy
and Operational Guidance for Law Enforcement (PDF).
U.S. Department of Justice, National Institute of Justice.
2012.
[94] New Developments In ALPR. Police Technology Magazine. 15 February 2011.
[95]
[96] the license plate recognition company (2004-10-20).
License Plate Recognition Algorithms and Technology.
Platerecognition.info. Retrieved 2014-04-23.
[97] Measuring ANPR System Performance (PDF). Parking
Trend International. June 2008. Retrieved 2012-01-24.
[98] Section control.
Verkeershandhaving Dossiers.
Archived from the original on 2006-05-12. Retrieved
2012-01-24.
[99] High-Tech System Helps Repo Man Find Cars. WFTV.
November 11, 2009.
[100] UK Billboards Equipped with License Plate Spy Cameras. TheNewspaper.com. 25 September 2009. Retrieved 2013-07-02.
[101] UK Billboards Equipped with License Plate Spy Cameras. 25 September 2009. Retrieved 2013-07-02.
[102] Extreme CCTV Announces Contract for Stockholm
Trac Cameras (PDF). Extremecctv.com. 22 April
2004. Archived from the original (PDF) on 2008-04-09.
Retrieved 2012-01-24.
[103] Friedrich, Markus; Jehlicka, Prokop; Schlaich, Johannes
(2008). Automatic number plate recognition for the observance of travel behavior. Universitt Stuttgart Institut
fr Straen und Verkehrswesen. Retrieved 2013-07-02.
[104] Friedrich, Markus; Jehlicka, Prokop; Schlaich, Johannes
(2008). Automatic number plate recognition for the observance of travel behavior (PDF). 8th International Conference on Survey Methods in Transport: Harmonisation
and Data Comparability, May 2008, Annecy, France. Universitt Stuttgart Institut fr Straen und Verkehrswesen.
Retrieved 2013-07-02.
20
REFERENCES
17
21
21.1
Text and image sources, contributors, and licenses
Text
Automatic number plate recognition Source: https://en.wikipedia.org/wiki/Automatic_number_plate_recognition?oldid=684516297
Contributors: Rbrwr, Edward, Michael Hardy, Pnm, Delirium, Ahoerstemeier, Ronz, Kingturtle, Ehn, Timwi, Dcoetzee, Snickerdo, Tpbradbury, , Shantavira, Phil Boswell, Je8765, Kadin2048, Auric, Hadal, Alan Liefting, Yama, Hylaride, Lupin, Bobblewik, Tagishsimon,
Gadum, John Foley, Necrothesp, Elwell, Picapica, Corti, Grstain, Discospinster, Shermozle, Neko-chan, Violetriga, Tooto, Pmcm, Vinsci,
Chairboy, Shanes, Webgeer, Brendansa, Cavrdg, Slambo, Licon, Alansohn, Thebeginning, 119, Jeltz, SlimVirgin, Kocio, Mailer diablo,
Dark Shikari, GL, Danhash, Dtcdthingy, Jheald, Geraldshields11, Henry W. Schmitt, Ericl234, Jef-Infojef, Ukulele~enwiki, Tckma, Tabletop, Torqueing, Gimboid13, Mandarax, Stefan h~enwiki, Yurik, Jyran, Rjwilmsi, Harry491, Ashuttleworth, Alaney2k, Rillian, Oblivious,
Renaissance Man, Sapient, RobertG, Musser, Josh~enwiki, Gurch, Zotel, Reetep, Duckypedia, Gwernol, YurikBot, Assawyer, MarkH,
Rsrikanth05, Bovineone, Ugur Basak, Maylett, ENeville, Tgsh2005, Orioneight, Tony1, Ckamaeleon, Rwxrwxrwx, YEPPOON, Zzuuzz,
Pb30, Lynbarn, BorgQueen, Shyam, Thomas Blomberg, SmackBot, Londonlinks, Video99, KYN, Saros136, Chris the speller, Master
Jay, Bluebot, Cryngo, Robth, Chendy, Frap, DeFacto, Chainz, Dev1n, JonHarder, Thisisbossi, Kittybrewster, Zvar, Mrt doulaty, BIL,
Downwards, B jonas, MichaelBillington, Wkerney, Ryan Roos, Kc2idf, ALR, JackLumber, Kricket~enwiki, Makyen, Beetstra, Erwin,
Dl2000, 08-15, Iridescent, Chris55, CmdrObot, Stevo1000, MeekMark, Ravensfan5252, CompRhetoric, Cydebot, Khatru2, Mindjuicer,
BMG~enwiki, Greatderren, Kozuch, NorthernThunder, Christonard, Mark tb, Mojo Hand, Moulder, Tapir Terric, FearedInLasVegas, Ladybirdintheuk, RichardVeryard, LionFlyer, Mentisto, AntiVandalBot, Luna Santin, Ndorr, Rlucena, Leuqarte, The Transhumanist, Albany
NY, Zorro CX, Haku8645, JamesBWatson, CS46, Bubba hotep, Tandras, Rlucenatalavera, Cropredy, R'n'B, CommonsDelinker, Nono64,
AtholM, Dispenser, Innovationinsight, Ondrejmartinsky, Pandaplodder, Fullmetal2887, Something Original, GS3, Lexein, GimmeBot,
BuickCenturyDriver, Kiranwashindkar, Pawanrh, Davin, Billinghurst, Haseo9999, D053, TML, Soyboyrama, Asiavision01, Zatoichi1564,
Radon210, Lightmouse, Flightman123, Byeshaswi, SallyForth123, Zandorgreb, Rumping, Binksternet, Francis45, Mild Bill Hiccup, Saboorian, Gu1dry, Kitchen Knife, Alexbot, John Nevard, Sun Creator, Arjayay, Night-vision-guru, Codumon, Versus22, Jammmie999,
XLinkBot, Afpre, Sponsion, Silvia20, Paperboyz, C.n.anag, Addbot, PahaOlo, Harrymph, MrOllie, Debresser, LinkFA-Bot, Splodgeness, Tassedethe, Muyagi~enwiki, Peridon, Wireless friend, Luckas-bot, Yobot, Fraggle81, AnomieBOT, Anthony 1l, Thiagoa1, Elsagna,
Materialscientist, Citation bot, Quebec99, LilHelpa, Mononomic, Shirik, Adrignola, Ashematian, Thehelpfulbot, FrescoBot, Devnullnor,
Kennedia, PeterEastern, HamburgerRadio, Pinethicket, Codebum2000, Lprguru, Lotje, Connelly90, J-Georg, MegaSloth, RjwilmsiBot,
TankMiche, Lyne9854, DASHBot, EmausBot, John of Reading, Idgs78, GoingBatty, Illegitimate Barrister, RaptureBot, Casia wyq, Ego
White Tray, Lilinjing cas, Russianbill, Anpr expert, Rhollis7, ClueBot NG, Driver8888, Widr, Carnetnoir, Strike Eagle, BG19bot, Jay8g,
BattyBot, NWRGeek, Kunio toba, Dexbot, Mogism, Mparlione, Lagoset, Erdvid01, Ben89129, Hants.romanse, Surfhun, Neiljdillon, Zorak03 and Anonymous: 295
21.2
Images
File:ARH_CAM-S1.jpg Source: https://upload.wikimedia.org/wikipedia/commons/e/e8/ARH_CAM-S1.jpg License: CC BY 4.0 Contributors: Own work Original artist: Cameramann
File:ARH_TrafficSpot_Gantry_Data_Point_Front.jpg Source:
https://upload.wikimedia.org/wikipedia/commons/c/ca/ARH_
TrafficSpot_Gantry_Data_Point_Front.jpg License: CC BY-SA 4.0 Contributors: Own work Original artist: Cameramann
File:Alexandria_VA_Dodge_Charger_Police_Car_ANPR.JPG Source:
https://upload.wikimedia.org/wikipedia/commons/f/f6/
Alexandria_VA_Dodge_Charger_Police_Car_ANPR.JPG License: CC BY-SA 3.0 Contributors: Transferred from en.wikipedia;
transferred to Commons by User:Kafuffle using CommonsHelper.
Original artist: Something Original (talk). Original uploader was Something Original at en.wikipedia
File:BE_license_plate.jpg Source: https://upload.wikimedia.org/wikipedia/commons/d/de/BE_license_plate.jpg License: CC-BY-SA3.0 Contributors: Own work Original artist: CNB
File:Brookyn_Bridge_ANPR.jpg Source: https://upload.wikimedia.org/wikipedia/en/2/20/Brookyn_Bridge_ANPR.jpg License: CCBY-SA-3.0 Contributors:
Own work
Original artist:
Jammmie999 (talk) (Uploads)
File:California_license_plate_ANPR.png Source: https://upload.wikimedia.org/wikipedia/commons/9/9c/California_license_plate_
ANPR.png License: CC-BY-SA-3.0 Contributors: ? Original artist: ?
File:Closed.circuit.twocameras.arp.750pix.jpg Source:
https://upload.wikimedia.org/wikipedia/commons/8/80/Closed.circuit.
twocameras.arp.750pix.jpg License: Public domain Contributors: Own work Original artist: Adrian Pingstone
File:Commons-logo.svg Source: https://upload.wikimedia.org/wikipedia/en/4/4a/Commons-logo.svg License: ? Contributors: ? Original
artist: ?
File:Dubai-anpr-camera.png Source: https://upload.wikimedia.org/wikipedia/commons/d/d6/Dubai-anpr-camera.png License: Public
domain Contributors: Own work Original artist: Driver8888
File:Dutch_license_plate_segment.jpg Source: https://upload.wikimedia.org/wikipedia/commons/3/3c/Dutch_license_plate_segment.
jpg License: Public domain Contributors: ? Original artist: ?
File:EW_206_full_LED_lightbar_and_ANPR_camera{}s_-_Flickr_-_Highway_Patrol_Images.jpg
Source:
https:
//upload.wikimedia.org/wikipedia/commons/c/c1/EW_206_full_LED_lightbar_and_ANPR_camera%27s_-_Flickr_-_Highway_
Patrol_Images.jpg License: CC BY 2.0 Contributors: EW 206 full LED lightbar and ANPR cameras Original artist: Highway Patrol
Images
File:FasTrak_Orange_County.jpg Source: https://upload.wikimedia.org/wikipedia/commons/2/2e/FasTrak_Orange_County.jpg License: CC-BY-SA-3.0 Contributors: Transferred from en.wikipedia; transferred to Commons by User:Jay8g using CommonsHelper. Original artist: Original uploader was Gary D at en.wikipedia. Later version(s) were uploaded by Ingolfson at en.wikipedia.
18
21
TEXT AND IMAGE SOURCES, CONTRIBUTORS, AND LICENSES
File:FrenchNumberPlates.jpg Source: https://upload.wikimedia.org/wikipedia/commons/0/06/FrenchNumberPlates.jpg License: CCBY-SA-3.0 Contributors: ? Original artist: ?
File:GMP_Vectra.jpg Source: https://upload.wikimedia.org/wikipedia/commons/1/18/GMP_Vectra.jpg License: CC BY 2.0 Contributors: GMP Vectra Original artist: Mikey from Wythenshawe, Manchester, UK
File:LPR_Process.JPG Source: https://upload.wikimedia.org/wikipedia/commons/1/1a/LPR_Process.JPG License: Public domain Contributors: LPR device Original artist: Amir shahram Hematian
File:London-cc-mobile-l.jpg Source: https://upload.wikimedia.org/wikipedia/commons/e/ec/London-cc-mobile-l.jpg License: CCBY-SA-3.0 Contributors: ? Original artist: ?
File:Merseyside_Police_ANPR_Car_August_09_2010.jpg
Source:
https://upload.wikimedia.org/wikipedia/commons/b/b1/
Merseyside_Police_ANPR_Car_August_09_2010.jpg License: CC BY-SA 3.0 Contributors: Own work Original artist: John Bradley
File:Numberplate_old_GB.jpg Source: https://upload.wikimedia.org/wikipedia/commons/6/6c/Numberplate_old_GB.jpg License:
Public domain Contributors: ? Original artist: User Colin99 on en.wikipedia
File:Question_book-new.svg Source: https://upload.wikimedia.org/wikipedia/en/9/99/Question_book-new.svg License: Cc-by-sa-3.0
Contributors:
Created from scratch in Adobe Illustrator. Based on Image:Question book.png created by User:Equazcion Original artist:
Tkgd2007
File:Swedish_licenseplate.jpg Source: https://upload.wikimedia.org/wikipedia/commons/0/0b/Swedish_licenseplate.jpg License: Public domain Contributors: Transferred from en.wikipedia to Commons by Unsonique using CommonsHelper. Original artist: The original
uploader was E70 at English Wikipedia
File:Telepass-A9-20060209.ogg Source: https://upload.wikimedia.org/wikipedia/commons/f/fc/Telepass-A9-20060209.ogg License:
CC BY 2.5 Contributors: Own work Original artist: Markus Stamm
File:Videomaut-A13-Schoenberg.ogg Source: https://upload.wikimedia.org/wikipedia/commons/0/03/Videomaut-A13-Schoenberg.
ogg License: CC BY 3.0 Contributors: Own work Original artist: Markus Stamm
21.3
Content license
