automatic number plate recognition.pdf

8/20/2019 Automatic number plate recognition.pdf

1/18

Automatic number plate recognition

The system must be able to deal with different styles of license plates

Automatic number plate recognition (ANPR; see alsoother names below) is a mass surveillance method thatuses optical character recognition on images to readvehicle registration plates. They can use existing closed-circuit television or road-rule enforcement cameras, orones specifically designed for the task. They are used byvarious police forces and as a method of electronic tollcollection on pay-per-use roads and cataloging the move-ments of traffic or individuals.

ANPR can be used to store the images captured by thecameras as well as the text from the license plate, with

some configurable to store a photograph of the driver.Systemscommonly use infrared lightingto allow thecam-era to take the picture at any time of the day.[1][2][3]

ANPR technology tends to be region-specific, owing toplate variation from place to place.

Concerns about these systems have centered on pri-vacy fears of government tracking citizens’ movements,misidentification, high error rates, and increased govern-ment spending.

1 Etymology

ANPR is sometimes known by various other terms:

License-plate recognition process

• Automatic license-plate recognition (ALPR)

• Automatic license-plate reader (ALPR)

• Automatic vehicle identification (AVI)

• Car plate recognition (CPR)

• License-plate recognition (LPR)

• Lecture automatique de plaques

d'immatriculation (LAPI)

• Mobile license-plate reader (MLPR)

• Vehicle license-plate recognition (VLPR)

1

https://en.wikipedia.org/wiki/Infraredhttps://en.wikipedia.org/wiki/Road_pricinghttps://en.wikipedia.org/wiki/Electronic_toll_collectionhttps://en.wikipedia.org/wiki/Electronic_toll_collectionhttps://en.wikipedia.org/wiki/Road-rule_enforcement_camerahttps://en.wikipedia.org/wiki/Closed-circuit_televisionhttps://en.wikipedia.org/wiki/Closed-circuit_televisionhttps://en.wikipedia.org/wiki/Vehicle_registration_platehttps://en.wikipedia.org/wiki/Optical_character_recognitionhttps://en.wikipedia.org/wiki/Mass_surveillancehttps://en.wikipedia.org/wiki/Automatic_number_plate_recognition#Etymologyhttps://en.wikipedia.org/wiki/License_platehttps://en.wikipedia.org/wiki/License_plate


2/18

2 4 TECHNOLOGY

2 Development history

ANPR was invented in 1976 at the Police Scientific De-velopment Branch in the UK. Prototype systems wereworking by1979, andcontracts were let to produce indus-trial systems, first at EMI Electronics, and then at Com-puter Recognition Systems (CRS) in Wokingham, UK.Early trial systems were deployed on the A1 road and atthe Dartford Tunnel. However it did not become widelyused until new developments in cheaper and easier to usesoftware was pioneered during the 1990s. The first ar-rest through detection of a stolen car was made in 1981and the first documented case of ANPR in helping solvea murder occurred in November 2005 after the murderof Sharon Beshenivsky, in which City of Bradford basedANPR played a vital role in locating and subsequentlyconvicting her killers.[4]

3 Components

The software aspect of the system runs on standard homecomputer hardware and can be linked to other applica-tions or databases. It first uses a series of image ma-nipulation techniques to detect, normalize and enhancethe image of the number plate, and then optical characterrecognition (OCR) to extract the alphanumerics of thelicense plate. ANPR systems are generally deployed inone of two basic approaches: one allows for the entireprocess to be performed at the lane location in real-time,

and the other transmits all the images from many lanesto a remote computer location and performs the OCRprocess there at some later point in time. When doneat the lane site, the information captured of the plate al-phanumeric, date-time, lane identification, and any otherinformation required is completed in approximately 250milliseconds. This information can easily be transmittedto a remote computer for further processing if necessary,or stored at the lane for later retrieval. In the other ar-rangement, there are typically large numbers of PCs usedin a server farm to handle high workloads, such as thosefound in the London congestion charge project. Often in

such systems, there is a requirement to forward images tothe remote server, and this can require larger bandwidthtransmission media.

4 Technology

ANPR uses optical character recognition (OCR) on im-ages taken by cameras. When Dutch vehicle registrationplates switched to a different style in 2002, one of thechanges made was to the font, introducing small gaps insome letters (such as P and R) to make them more dis-

tinct and therefore more legible to such systems. Somelicense plate arrangements use variations in font sizesand positioning—ANPR systems must be able to cope

The font on Dutch plates was changed to improve plate recogni-tion.

with such differences in order to be truly effective. More

complicated systems can cope with international variants,though many programs are individually tailored to eachcountry.

The cameras used can include existing road-rule enforce-ment or closed-circuit television cameras, as well as mo-bile units, which are usually attached to vehicles. Somesystems use infrared cameras to take a clearer image ofthe 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, significant advances in technologytook automatic number plate recognition (ANPR) sys-tems from limited expensive, hard to set up, fixed basedapplications to simple “point and shoot” mobile ones.This was made possible by the creation of software thatran on cheaper PC based, non-specialist hardware thatalso no longer needed to be given the pre-defined angles,direction, size and speed in which the plates would bepassing the cameras field of view. Further scaled-downcomponents at more cost-effective price points led to a

record number of deployments by law enforcement agen-cies around the world. Smaller cameras with the abilityto read license plates at higher speeds, along with smaller,

https://en.wikipedia.org/wiki/Dubaihttps://en.wikipedia.org/wiki/Dutch_vehicle_registration_plateshttps://en.wikipedia.org/wiki/Typefacehttps://en.wikipedia.org/wiki/Typefacehttps://en.wikipedia.org/wiki/Dutch_vehicle_registration_plateshttps://en.wikipedia.org/wiki/Dutch_vehicle_registration_plateshttps://en.wikipedia.org/wiki/Optical_character_recognitionhttps://en.wikipedia.org/wiki/London_congestion_chargehttps://en.wikipedia.org/wiki/Server_farmhttps://en.wikipedia.org/wiki/Alphanumerichttps://en.wikipedia.org/wiki/Databasehttps://en.wikipedia.org/wiki/City_of_Bradfordhttps://en.wikipedia.org/wiki/Murder_of_Sharon_Beshenivskyhttps://en.wikipedia.org/wiki/Murder_of_Sharon_Beshenivskyhttps://en.wikipedia.org/wiki/Dartford_Tunnelhttps://en.wikipedia.org/wiki/A1_road_(Great_Britain)https://en.wikipedia.org/wiki/Wokingham


3/18

3

A Merseyside Police car equipped with mobile ANPR.

more durable processors that fit in the trunks of policevehicles, allowed law enforcement officers to patrol dailywith the benefit of license plate reading in real time, whenthey can interdict immediately.

Despite their effectiveness, there are noteworthy chal-lenges related with mobile ANPRs. One of the biggest isthat the processor and the cameras must work fast enoughto accommodate relative speeds of more than 100 mph(160 km/h), a likely scenario in the case of oncomingtraffic. This equipment must also be very efficient sincethe power source is the vehicle battery, and equipmentmust be small to minimize the space it requires.

Relative speed is only one issue that affects the camera’sability to actually read a license plate. Algorithms must beable to compensate for all the variables that can affect theANPR’s ability to produce an accurate read, such as timeof day, weather and angles between the cameras and thelicense plates. A system’s illumination wavelengths canalso have a direct impact on the resolution and accuracyof a read in these conditions.

Installing ANPR cameras on law enforcement vehiclesrequires careful consideration of the juxtaposition of thecameras to the license plates they are to read. Usingthe right number of cameras and positioning them ac-curately for optimal results can prove challenging, giventhe various missions and environments at hand. High-way patrol requires forward-looking cameras that spanmultiple lanes and are able to read license plates at veryhigh speeds. City patrol needs shorter range, lower focallength cameras for capturing plates on parked cars. Park-ing lots with perpendicularly parked cars often require aspecialized camera with a very short focal length. Mosttechnically advanced systems are flexible and can be con-figured with a number of cameras ranging from one tofour which can easily be repositioned as needed. Stateswith rear-only license plates have an additional challenge

since a forward-looking camera is ineffective with on-coming traffic. In this case one camera may be turnedbackwards.

5 Algorithms

Steps 2, 3 and 4: The license plate is normalized for brightness

and contrast, and then the characters are segmented to be ready for OCR.

There are seven primary algorithms that the software re-quires for identifying a license plate:

1. Plate localization – responsible for finding and iso-lating the plate on the picture.

2. Plate orientation and sizing – compensates for theskew of the plate and adjusts the dimensions to therequired size.

3. Normalization – adjusts the brightness and contrastof the image.

4. Character segmentation – finds the individual char-acters on the plates.

5. Optical character recognition.

6. Syntactical/Geometrical analysis – check charactersand positions against country-specific rules.

7. The averaging of the recognised value over multiplefields/images to produce a more reliable or confidentresult. Especially since any single image may con-

tain a reflected light flare, be partially obscured orother temporary effect.

The complexity of each of these subsections of the pro-gram determines the accuracy of the system. During thethird phase (normalization), some systems use edge de-tection techniques to increase the picture difference be-tween the letters and the plate backing. A median filtermay also be used to reduce the visual noise on the image.

6 Difficulties

There are a number of possible difficulties that the soft-ware must be able to cope with. These include:

https://en.wikipedia.org/wiki/File_noise_reductionhttps://en.wikipedia.org/wiki/Median_filterhttps://en.wikipedia.org/wiki/Edge_detectionhttps://en.wikipedia.org/wiki/Edge_detectionhttps://en.wikipedia.org/wiki/Algorithmhttps://en.wikipedia.org/wiki/Optical_character_recognitionhttps://en.wikipedia.org/wiki/Merseyside_Police


4/18

4 7 IMAGING HARDWARE

Early ANPR systems were unable to read white or silver lettering

on black background, as permitted on UK vehicles built prior to1973.

Swedish license plate

Must be able to recognizeinternational license plates as such.

• Poor file resolution, usually because the plate is toofar away but sometimes resulting from the use of alow-quality camera.

• Blurry images, particularly motion blur.

• Poor lighting and low contrast due to overexposure,reflection or shadows.

• An object obscuring (part of) the plate, quite oftena tow bar, or dirt on the plate.

• Read license plates that are different at the front andthe back because of towed trailers, campers, etc.

• Vehicle lane change in the camera’s angle of view

during license plate reading.

• A different font, popular for vanity plates (somecountries do not allow such plates, eliminating theproblem).

• Circumvention techniques.

• Lack of coordination between countries or states.Two cars from different countries or states can havethe same number but different design of the plate.

While some of these problems can be corrected within

the software, it is primarily left to the hardware side ofthe system to work out solutions to these difficulties. In-creasing the height of the camera may avoid problems

with objects (such as other vehicles) obscuring the platebut introduces and increases other problems, such as theadjusting for the increased skew of the plate.

On some cars, tow bars may obscure one or two char-acters of the license plate. Bikes on bike racks can also

obscure the number plate, though in some countries andjurisdictions, such as Victoria, Australia, “bikeplates” aresupposed to be fitted. Some small-scale systems allow forsome errors in the license plate. When used for givingspecific vehicles access to a barricaded area, the decisionmay be made to have an acceptable error rate of one char-acter. This is because the likelihood of an unauthorizedcar having such a similar license plate is seen as quitesmall. However, this level of inaccuracy would not beacceptable in most applications of an ANPR system.

7 Imaging hardware

At the front end of any ANPR system is the imaging hard-ware which captures the image of the license plates. Theinitial image capture forms a critically important part ofthe ANPR system which, in accordance to the garbage in,garbage out principle of computing, will often determinethe overall performance.

License plate capture is typically performed by special-ized cameras designed specifically for the task, althoughnew software techniques are being implemented that sup-port any I.P.-based surveillance camera and increase the

utility of ANPR for perimeter security applications. Fac-tors which pose difficulty for license plate imaging cam-eras include the speed of the vehicles being recorded,varying level of ambient light, headlight glare and harshenvironmental conditions. Most dedicated license platecapture cameras will incorporate infrared illumination inorder to solve the problems of lighting and plate reflec-tivity.

Portable traffic enforcement system used by the Hungarian police.The rows of infrared LEDs are visible on the right.

Many countries now use license plates that areretroreflective.[15] This returns the light back to the

source and thus improves the contrast of the image. Insome countries, the characters on the plate are not re-flective, giving a high level of contrast with the reflective

https://en.wikipedia.org/wiki/Retroreflectorhttps://en.wikipedia.org/wiki/Light-emitting_diodehttps://en.wikipedia.org/wiki/Law_enforcement_in_Hungaryhttps://en.wikipedia.org/wiki/Infraredhttps://en.wikipedia.org/wiki/Garbage_in,_garbage_outhttps://en.wikipedia.org/wiki/Garbage_in,_garbage_outhttps://en.wikipedia.org/wiki/Victoria,_Australiahttps://en.wikipedia.org/wiki/Computer_hardwarehttps://en.wikipedia.org/wiki/Vanity_platehttps://en.wikipedia.org/wiki/Angle_of_viewhttps://en.wikipedia.org/wiki/Reflection_(physics)https://en.wikipedia.org/wiki/Exposure_(photography)https://en.wikipedia.org/wiki/Motion_blurhttps://en.wikipedia.org/wiki/Focus_(optics)https://en.wikipedia.org/wiki/File_resolution


5/18

5

background in any lighting conditions. A camera thatmakes use of active infrared imaging (with a normalcolour filter over the lens and an infrared illuminatornext to it) benefits greatly from this as the infrared wavesare reflected back from the plate. This is only possibleon dedicated ANPR cameras, however, and so cameras

used for other purposes must rely more heavily on thesoftware capabilities. Further, when a full-colour imageis required as well as use of the ANPR-retrieved details,it is necessary to have one infrared-enabled camera andone normal (colour) camera working together.

To avoid blurring it is ideal to have the shutter speed of adedicated camera set to 1/1000 of a second. It is also im-portant that the camera uses a global shutter, as opposedto rolling shutter, to assure that the taken images aredistortion-free. Because the car is moving, slower shut-ter speeds could result in an image which is too blurredto read using the OCR software, especially if the camera

is much higher up than the vehicle. In slow-moving traf-fic, or when the camera is at a lower level and the vehicleis at an angle approaching the camera, the shutter speeddoes not need to be so fast. Shutter speeds of 1/500 ofa second can cope with traffic moving up to 40 mph (64km/h) and 1/250 of a second up to 5 mph (8 km/h). Li-cense plate capture cameras can produce usable imagesfrom vehicles traveling at 120 mph (190 km/h).

To maximize the chances of effective license plate cap-ture, installers should carefullyconsider the positioning ofthe camera relative to the target capture area. Exceedingthreshold angles of incidence between camera lens and

license plate will greatly reduce the probability of obtain-ing usable images due to distortion. Manufacturers havedeveloped tools to help eliminate errors from the physicalinstallation of license plate capture cameras.

8 Circumvention techniques

Vehicle owners have used a variety of techniques in an at-tempt to evade ANPR systemsand road-ruleenforcementcameras in general. One method increases the reflective

properties of the lettering and makes it more likely thatthe system will be unable to locate the plate or produce ahigh enough level of contrast to be able to read it. Thisis typically done by using a plate cover or a spray, thoughclaims regarding the effectiveness of the latter are dis-puted. In most jurisdictions, the covers are illegal andcovered under existing laws, while in most countries thereis no law to disallow the use of the sprays.[16][17] Otherusers have attempted to smear their license plate with dirtor utilize covers to mask the plate.

Novelty frames around Texas license plates were madeillegal in Texas on 1 September 2003 by Texas Senate Bill

439 because they caused problems with ANPR devices.That law made it a Class C misdemeanor (punishable bya fine of up to US $200), or Class B (punishable by a

fine of up to US $2,000 and 180 days in jail) if it canbe proven that the owner did it to deliberately obscuretheir plates.[18] The law was laterclarified in 2007 to allowNovelty frames.

If an ANPR system cannot read the plate, it can flag the

image for attention, with the human operators looking tosee if they are able to identify the alphanumerics.

In order to avoid surveillance or penalty charges, there hasbeen an upsurge in car cloning. This is usually achievedby copying registration plates from another car of a sim-ilar model and age. This can be difficult to detect, espe-cially as cloners may change the registration plates andtravel behavior to hinder investigations.

In 2013 researchers at Sunflex Zone Ltd created a privacylicense plate frame that uses near infrared light to makethe license plate unreadable to license plate recognitionsystems.[19]

9 Police enforcement

Mobile ANPR cameras fitted to a New South Wales Police ForceHighway Patrol vehicle.

Closed-circuit television cameras such as these can be used to

take the images scanned by automatic number plate recognitionsystems

https://en.wikipedia.org/wiki/Closed-circuit_televisionhttps://en.wikipedia.org/wiki/Highway_Patrolhttps://en.wikipedia.org/wiki/New_South_Wales_Police_Forcehttps://en.wikipedia.org/wiki/Travel_behaviorhttps://en.wikipedia.org/wiki/Vehicle_registration_plates_of_Texashttps://en.wikipedia.org/wiki/Rolling_shutterhttps://en.wikipedia.org/wiki/Shutter_speed


6/18

6 9 POLICE ENFORCEMENT

9.1 Australia

Several State Police Forces, and the Department of Jus-tice (Victoria)[20] use both fixed and mobile ANPR sys-tems. The New South Wales Police Force Highway Patrolwere the first to trial and use a fixed ANPR camera system

in Australia in 2005. In 2009 they began a roll-out of amobile ANPR system (known officially as MANPR)[21]

with three infrared cameras fitted to its Highway Patrolfleet.[22] The system identifies unregistered and stolen ve-hicles as well as disqualified or suspended drivers as wellas other 'persons of interest' such as persons having out-standing warrants.[23]

9.2 Belgium

The city of Mechelen uses an ANPR system sinceSeptember 2011 to scan all cars crossing the city lim-its (inbound and outbound). Cars listed on 'black lists'(no insurance, stolen, etc.) generate an alarm in the dis-patching room, so they can be intercepted by a patrol. Asof early 2012, 1 million cars per week are automaticallychecked in this way.[24]

9.3 Denmark

The technique is tested by the Danish police. It will be inpermanent use from the end of 2015.[25]

9.4 France

180 gantries over major roads have been built through-out the country. These together with a further 250 fixedcameras is to enable a levy of an eco tax on lorries over3.5 tonnes. The system is currently being opposed andwhilst they may be collecting data on vehicles passing thecameras, no eco tax is being charged.[26]

9.5 Germany

On 11 March 2008, the Federal Constitutional Court ofGermany ruled that some areas of the laws permitting theuse of automated number plate recognition systems inGermany violated the right to privacy.[27] More specif-ically, the court found that the retention of any sort ofinformation (i.e., number plate data) which was not forany pre-destined use (e.g., for use tracking suspected ter-rorists or for enforcement of speeding laws) was in vio-lation of German law. These systems were provided byJenoptik Robot GmbH, and called TraffiCapture.[28]

9.6 Hungary

In 2012 a state consortium was formed among the Hun-garian Ministry of Interior, the National Police Head-

Road gantry traffic enforcement and data point on the M7 high-way at Érd , Hungary

quarters and the Central Commission of Public Admin-istration and Electronic Services with the aim to installand operate a unified intelligent transportation system

(ITS ) with nationwide coverage by the end of 2015.

[29]

Within the system, 160 portable traffic enforcement anddata-gathering units and 365 permanent gantry instal-lations were brought online with ANPR, speed detec-tion, imaging and statistical capabilities. Since all thedata points are connected to a centrally located ITS, eachmember of the consortium is able to separately utilize itsrange of administrative and enforcement activities, suchas remote vehicle registration and insurance verification,speed, lane and traffic light enforcement and wanted orstolen 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 webcamera that scans the stolen car database using automaticnumber plate recognition. The system is installed on thedashboard of selected patrol vehicles (PDA-based hand-held versions also exist) and is mainly used to control thelicense plate of parking cars. As the Auxiliary Police donot have the authority to order moving vehicles to stop, ifa stolen car is found, the formal police is informed.

9.7 Turkey

Several cities have tested—and some have put intoservice—the “City Security Administration System”, i.e.,capital Ankara, has debuted KGYS- “Kent Guvenlik Yo-netim Sistemi” which consists of a registration plate num-ber recognition system on the main arteries and cityexits.[31] The system has been used with two cameras perlane, one for plate recognition, one for speed detection.Now the system has been widened to network all the reg-istration number cameras together, and enforcing averagespeed over preset distances. Some arteries have 70Kmhlimit, and some 50 kmh, and photo evidence with date-

time details are posted to registration address if speed vi-olation is detected. As of 2012, the fine for exceeding thespeed limit for more than 30% is approximately US$175.

http://www.ankara.pol.tr/kgys/goruntuleme_sistemi.phphttp://www.ankara.pol.tr/kgys/goruntuleme_sistemi.phphttps://en.wikipedia.org/wiki/Personal_digital_assistanthttps://en.wikipedia.org/wiki/Law_enforcement_in_Hungaryhttps://en.wikipedia.org/wiki/Auxiliary_policehttps://en.wikipedia.org/wiki/Intelligent_transportation_systemhttps://en.wikipedia.org/wiki/%C3%89rdhttps://en.wikipedia.org/wiki/M7_motorway_(Hungary)https://en.wikipedia.org/wiki/M7_motorway_(Hungary)https://en.wikipedia.org/wiki/Privacyhttps://en.wikipedia.org/wiki/Federal_Constitutional_Court_of_Germanyhttps://en.wikipedia.org/wiki/Federal_Constitutional_Court_of_Germanyhttps://en.wikipedia.org/wiki/Blacklistinghttps://en.wikipedia.org/wiki/Mechelenhttps://en.wikipedia.org/wiki/Highway_Patrolhttps://en.wikipedia.org/wiki/New_South_Wales_Police_Forcehttps://en.wikipedia.org/wiki/Department_of_Justice_(Victoria)https://en.wikipedia.org/wiki/Department_of_Justice_(Victoria)


7/18

9.10 United States 7

9.8 Ukraine

The project of system integration «OLLI Technology»and the Ministry of Internal Affairs of Ukraine Depart-ment of State Traffic Inspection (STI) experiments onthe introduction of a modern technical complex which

is capable to locate stolen cars, drivers deprived of driv-ing licenses and other problem cars in real time. TheUkrainiancomplex “Video control”[32] working bya prin-ciple of video fixing of the car with recognition of licenseplates with check under data base.

9.9 United Kingdom

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 numberplate recognition CCTV network. Effectively, the policeand security services track all car movements around thecountry and are able to track any car in close to real time.Vehicle movements are stored for 2 years in the NationalANPR Data Center to be analyzed for intelligence and tobe used as evidence.

In 1997 a system of one hundred ANPR cameras, co-denamed GLUTTON, was installed to feed into the au-tomated British Military Intelligence Systems in North-ern Ireland. Further cameras were also installed on theBritish mainland, including unspecified ports on the eastand west coasts.

9.10 United States

In the United States, ANPR systems are more com-monly referred to as ALPR (Automatic License Plate

Reader/Recognition) technology, due to differences inlanguage (i.e., “number plates” are referred to as “licenseplates” in American English)

A City of Alexandria police car equipped with mobile ALPR.

ANPR cameras in operation on the Brooklyn Bridge in New York.

Mobile ANPR use is widespread among US law enforce-ment agencies at the city, county, state and federal level.According to a 2012 report by the Police Executive Re-search Forum, approximately 71% of all US police de-partments use some form of ANPR.[33] Mobile ANPRis becoming a significant component of municipal pre-dictive policing strategies and intelligence gathering,[34]

as well as for recovery of stolen vehicles, identificationof wanted felons, and revenue collection from individ-uals who are delinquent on city or state taxes or fines,or monitoring for “Amber Alerts”. Successfully recog-

nized plates may be matched against databases includ-ing “wanted person”, “protection order”, missing person,gang member, known and suspected terrorist, supervisedrelease, immigration violator, and National Sex Offenderlists.[35] In addition to the real-time processing of licenseplate numbers, ALPR systems in the US collect (and canindefinitely store) data from each license plate capture.Images, dates, times and GPS coordinates can be stock-piled and can help place a suspect at a scene, aid in wit-ness identification, pattern recognition or the tracking ofindividuals.

An early, private sector mobile ANPR application

has been applications for vehicle repossession andrecovery[36]), although the application of ANPR by pri-vate companies to collect information from privately

https://en.wikipedia.org/wiki/Brooklyn_Bridgehttps://en.wikipedia.org/wiki/Alexandria,_Virginiahttps://en.wikipedia.org/wiki/List_of_American_words_not_widely_used_in_the_United_Kingdom#Lhttps://en.wikipedia.org/wiki/British_Military_Intelligence_Systems_in_Northern_Irelandhttps://en.wikipedia.org/wiki/British_Military_Intelligence_Systems_in_Northern_Irelandhttps://en.wikipedia.org/wiki/Intelligencehttps://en.wikipedia.org/wiki/MI5https://en.wikipedia.org/wiki/British_policehttps://en.wikipedia.org/wiki/CCTVhttps://en.wikipedia.org/wiki/Police-enforced_ANPR_in_the_UKhttps://en.wikipedia.org/wiki/Greater_Manchester_Policehttps://en.wikipedia.org/wiki/Vauxhall_Vectrahttps://en.wikipedia.org/wiki/Ministry_of_Internal_Affairs_of_Ukraine


8/18

8 11 CRIME DETERRENT

owned vehicles or collected from private property (for ex-ample, driveways) has become an issue of sensitivity andpublic debate.[37] Other ALPR uses include parking en-forcement, and revenue collection from individuals whoare delinquent on city or state taxes or fines. The technol-ogy is often featured in the reality TV show Parking Wars

featured on A&E Network. In theshow, tow truck driversand booting teams use the ALPR to find delinquent vehi-cles with high amounts of unpaid parking fines.

9.11 Saudi Arabia

Vehicle registration plates in Saudi Arabia use whitebackground, but several vehicle types may have a dif-ferent background. United States diplomatic plates havethe letters 'USD', which in Arabic reads 'DSU' whenread from right to left in the direction of Arabic script.There are only 17 Arabic letters used on the registra-tion plates.[38] A Challenge for plates recognition in SaudiArabia is the size of the digits. Some plates use bothEastern Arabic numerals and the 'Western Arabic' equiv-alents. A research withsource code is available for APNRArabic digits.[39]

9.12 Sweden

The technique is tested by the Swedish police at nine dif-

ferent places in Sweden.[40]

10 Average-speed cameras

Main article: Speed limit enforcement

ANPR is used for speed limit enforcement in Australia,Austria,[41] Belgium,[42] Dubai (UAE), France, Italy,[43]

The Netherlands,[44] Spain,[45] and the UK.[46]

This works by tracking vehicles’ travel time between twofixed points, and calculating the average speed. Thesecameras are claimed to have an advantage over traditionalspeed cameras in maintaining steady legal speeds over ex-tended distances, rather than encouraging heavy brakingon approach to specific camera locations and subsequentacceleration back to illegal speeds.[47]

10.1 Italy

In Italian Highways has developed a monitoring system

named Tutor covering more than 2500 km (2012). TheTutor system is also able to intercept cars while changinglanes.[48]

10.2 The Netherlands

Average speed cameras (trajectcontrole) are in place inthe Netherlands since 2002. As of July 2009, 12 cam-eras were operational, mostly in the west of the countryand along the A12.[47] Some of these are divided in sev-

eral “sections” to allow for cars leaving and entering themotorway.

A first experimental system was tested on a short stretchof the A2 in 1997 and was deemed a big success by thepolice, reducing overspeeding to 0.66%, compared to 5to 6% when regular speed cameras were used at the samelocation.[49] The first permanent average speed cameraswere installed on the A13 in 2002, shortly after the speedlimit was reduced to 80 km/h to limit noise and air pol-lution in the area.[50] In 2007, average speed cameras re-sulted in 1.7 million fines for overspeeding out of a totalof 9.7 millions. According to the Dutch Attorney Gen-

eral, the average number of violation of the speed lim-its on motorway sections equipped with average speedcameras is between 1 and 2%, compared to 10 to 15%elsewhere.[51]

10.3 UK

See also: Road speed limit enforcement in the UnitedKingdom

One of the most notable stretches of average speed cam-

eras in the UK is found on the A77 road in Scotland, with32 miles (51 km) being monitored between Glasgow andAyr.[52] In 2006 it was confirmed that speeding ticketscould potentially be avoided from the 'SPECS' camerasby changing lanes and the RAC Foundation feared thatpeople may play “Russian Roulette” changing from onelane to another to lessen their odds of being caught. [46]

However, in 2007 the system was upgraded for multi-laneuse and in 2008 the manufacturer described the “myth”as “categorically untrue”.[53] There exists evidence thatimplementation of systems such as SPECS has a consid-erable effect on the volume of drivers travelling at exces-

sive speeds; on the stretch of road mentioned above (A77Between Glasgow and Ayr) there has been noted a “hugedrop” in speeding violations since the introduction of aSPECS system.[52]

11 Crime deterrent

Recent innovations have contributed to the adoption ofANPR for perimeter security and access control appli-cations at government facilities. Within the US, “home-land security” efforts to protect against alleged “acts of

terrorism” have resulted in adoption of ANPR for sensi-tive facilities such as embassies, schools, airports, mar-itime ports, military and federal buildings, law enforce-

https://en.wikipedia.org/wiki/RAC_Foundationhttps://en.wikipedia.org/wiki/Ayrhttps://en.wikipedia.org/wiki/Glasgowhttps://en.wikipedia.org/wiki/A77_roadhttps://en.wikipedia.org/wiki/Road_speed_limit_enforcement_in_the_United_Kingdomhttps://en.wikipedia.org/wiki/Road_speed_limit_enforcement_in_the_United_Kingdomhttps://en.wikipedia.org/wiki/A12_motorway_(Netherlands)https://en.wikipedia.org/wiki/A12_motorway_(Netherlands)https://it.wikipedia.org/wiki/Tutor%2520(dispositivo)https://it.wikipedia.org/wiki/Autostrade%2520per%2520l%2527Italiahttps://en.wikipedia.org/wiki/Speed_limithttps://en.wikipedia.org/wiki/Speed_limit_enforcementhttps://en.wikipedia.org/wiki/Saudi_Arabia


9/18

9

ment and government facilities, and transportation cen-ters. ANPR is marketed as able to be implementedthrough networks of IP based surveillance cameras thatperform “double duty” alongside facial recognition, ob-ject tracking, and recording systems for the purpose ofmonitoring suspicious or anomalous behavior, improving

access control, and matching against watch lists. ANPRsystems are most commonly installed at points of signif-icant sensitivity, ingress or egress. Major US agenciessuch as the Department of Homeland Security, the De-partment of Justice, the Department of Transportationand the Department of Defense have purchased ANPRfor perimeter security applications.[54] Large networksof ANPR systems are being installed by cities such asBoston, London and New York City to provide citywideprotection against acts of terrorism, and to provide sup-port for public gatherings and public spaces.[55]

12 Enterprise security and services

In addition to government facilities, many private sectorindustries with facility security concerns are beginning toimplement ANPR solutions. Examples include casinos,hospitals, museums, parking facilities, and resorts.[56] Inthe US, private facilities typically cannot access govern-ment or police watch lists, but may develop and matchagainst their own databases for customers, VIPs, criticalpersonnel or “banned person” lists. In addition to provid-ing perimeter security, private ANPR has service appli-

cations for valet / recognized customer and VIP recog-nition, logistics and key personnel tracking, sales and ad-vertising, parking management, and logistics (vendor andsupport vehicle tracking).

13 Traffic control

Video tolling at Schönberg , Austria

Many cities and districts have developed traffic controlsystems to help monitor the movement and flow of ve-hicles around the road network. This had typically in-

volved looking at historical data, estimates, observationsand 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 traffic control centresby giving them live data, allowing for traffic managementdecisions to be made in real-time. By using ANPR onthis footage it is possible to monitor the travel of individ-ual vehicles, automatically providing information aboutthe speed and flow of various routes. These details canhighlight problem areas as and when they occur and help

the centre to make informed incident management deci-sions.

Some counties of the United Kingdom have worked withSiemens Traffic to develop traffic monitoring systems fortheir own control centres and for the public.[57] Projectssuch as Hampshire County Council’s ROMANSE pro-vide an interactive and real-time web site showing de-tails about traffic in the city. The site shows informa-tion about car parks, ongoing road works, special eventsand footage taken from CCTV cameras. ANPR systemscan be used to provide average point-to-point journeytimes along particular routes, which can be displayed on

a variable-message sign(VMS) giving drivers the abilityto plan their route. ROMANSE also allows travellers tosee the current situation using a mobile device with anInternet connection (such as WAP, GPRS or 3G), allow-ing them to view mobile device CCTV images within theHampshire road network.

The UK company Trafficmaster has used ANPR since1998 to estimate average traffic speeds on non-motorwayroads without the results being skewed by local fluctu-ations caused by traffic lights and similar. The companynow operates a network of over 4000 ANPR cameras, butclaims that only the four most central digits are identified,

and no numberplate data is retained.[58][59][60]

• IEEE transactions on Intelligent TransportationSystems(IEEE Intelligent Transportation SystemsSociety) published some papers on the plate num-ber recognition technologies and applications.

14 Electronic toll collection

14.1 Toll roads

Ontario's 407 ETR highway uses a combination of ANPRand radio transponders to toll vehicles entering and exit-ing the road. Radio antennas are located at each junction

https://en.wikipedia.org/wiki/Transponderhttps://en.wikipedia.org/wiki/Ontario_Highway_407https://en.wikipedia.org/wiki/Ontariohttps://en.wikipedia.org/wiki/IEEE_Intelligent_Transportation_Systems_Societyhttps://en.wikipedia.org/wiki/IEEE_Intelligent_Transportation_Systems_Societyhttp://www.romanse.org.uk/CCTVmobile.htmhttps://en.wikipedia.org/wiki/3Ghttps://en.wikipedia.org/wiki/GPRShttps://en.wikipedia.org/wiki/Wireless_Application_Protocolhttps://en.wikipedia.org/wiki/Variable-message_signhttps://en.wikipedia.org/wiki/Web_sitehttp://www.romanse.org.uk/https://en.wikipedia.org/wiki/Hampshirehttps://en.wikipedia.org/wiki/Siemens_AGhttps://en.wikipedia.org/wiki/Pedestrian_crossinghttps://en.wikipedia.org/wiki/Sch%C3%B6nberg_im_Stubaitalhttps://en.wikipedia.org/wiki/Video_tolling


10/18

10 14 ELECTRONIC TOLL COLLECTION

The FasTrak system in Orange County uses ANPR and radiotransponders

Film showing theapproachto andpassing ofa tollstation in Italy,

using a Telepass OBU. Note the yellow Telepass lane signs and road markings and the sound emitted by the OBU when passingthe lane

and detect the transponders, logging the unique identityof each vehicle in much the same way as the ANPR sys-temdoes. Without ANPR as a second system it would notbe possible to monitor all the traffic. Drivers who opt torent a transponder for C$2.55 per month are not chargedthe “Video Toll Charge” of C$3.60 for using the road,with heavy vehicles (those with a gross weight of over5,000 kg) being required to use one. Using either system,users of the highway are notified of the usage charges bypost.

There are numerous other electronic toll collection net-works which use this combination of Radio frequencyidentification and ANPR. These include:

• The Golden Gate Bridge in San Francisco, Cal-ifornia, began using an all-electronic tolling sys-tem combining Fastrak and ANPR on March 27,2013.[61]

• NC Quick Pass for the Interstate 540 (North Car-olina) Triangle Expressway in Wake County, NorthCarolina

• Bridge Pass[62] for the Saint John Harbour Bridge in

Saint John, New Brunswick

• Quickpass[63] at the Golden Ears Bridge, crossingthe Fraser River between Langley and Maple Ridge

• CityLink & Eastlink in Melbourne, Australia

• Gateway Motorwayand LoganMotorway, Brisbane,Australia

• FasTrak in California, United States

• Highway 6 in Israel

• Tunnels in Hong Kong

• Autopista Central[64] in Santiago, Chile (site inSpanish)

• E-ZPass in New York, New Jersey, Massachusetts(as Fast Lane until 2012), Virginia (formerly Smart

Tag), and other states. Maryland Route 200 uses acombination 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

• OGS (Otomatik Geçiş Sistemi) used at BosphorusBridge, Fatih Sultan Mehmet Bridge, and Trans Eu-

ropean Motorway entry points in İstanbul, Turkey• M50 Westlink Toll in Dublin, Ireland

• Hi-pass in South Korea

• Northern Gateway, SH 1, Auckland, New Zealand

• Evergreen Point Floating Bridge, Seattle, andWashington State Route 167 HOT-lanes in westernWashington

• ETC[65] in Taiwan

14.2 Portugal

Portuguese roads have old highways with toll stationwhere drivers can pay with cards and also lanes wherethere are electronic collection systems. However mostnew highways only have the option of electronic toll col-lection system. The electronic toll collection system com-prises three different structures: ANPR which workswith infrared cameras and reads license plates from ev-ery vehicle Lasers to measure the volumetry of the vehi-cle to confirm whether it is a regular car or if it is a SUVor truck as charges are very different RFID-like to read

smart tags that cars can have installed. When the smarttag is installed, the car is quickly identified and ownersbank account is automatically deducted. This process is

https://en.wikipedia.org/wiki/Taiwanhttps://en.wikipedia.org/wiki/Washington_(state)https://en.wikipedia.org/wiki/Washington_State_Route_167https://en.wikipedia.org/wiki/Seattlehttps://en.wikipedia.org/wiki/Evergreen_Point_Floating_Bridgehttps://en.wikipedia.org/wiki/Aucklandhttps://en.wikipedia.org/wiki/Auckland_Northern_Motorwayhttps://en.wikipedia.org/wiki/Hi-passhttps://en.wikipedia.org/wiki/Dublinhttps://en.wikipedia.org/wiki/M50_motorway_(Ireland)https://en.wikipedia.org/wiki/%C4%B0stanbulhttps://en.wikipedia.org/wiki/Trans_European_Motorwayhttps://en.wikipedia.org/wiki/Trans_European_Motorwayhttps://en.wikipedia.org/wiki/Fatih_Sultan_Mehmet_Bridgehttps://en.wikipedia.org/wiki/Bosphorus_Bridgehttps://en.wikipedia.org/wiki/Bosphorus_Bridgehttps://en.wikipedia.org/wiki/Gwinnett_Countyhttps://en.wikipedia.org/wiki/Oklahomahttps://en.wikipedia.org/wiki/Pike_Passhttps://en.wikipedia.org/wiki/Illinoishttps://en.wikipedia.org/wiki/I-Passhttps://en.wikipedia.org/wiki/TollTaghttps://en.wikipedia.org/wiki/Maryland_Route_200https://en.wikipedia.org/wiki/Smart_Taghttps://en.wikipedia.org/wiki/Smart_Taghttps://en.wikipedia.org/wiki/Virginiahttps://en.wikipedia.org/wiki/Massachusettshttps://en.wikipedia.org/wiki/New_Jerseyhttps://en.wikipedia.org/wiki/E-ZPasshttps://en.wikipedia.org/wiki/Santiago,_Chilehttps://en.wikipedia.org/wiki/List_of_tunnels_and_bridges_in_Hong_Konghttps://en.wikipedia.org/wiki/Highway_6_(Israel)https://en.wikipedia.org/wiki/FasTrakhttps://en.wikipedia.org/wiki/Brisbanehttps://en.wikipedia.org/wiki/Logan_Motorwayhttps://en.wikipedia.org/wiki/Gateway_Motorwayhttps://en.wikipedia.org/wiki/EastLink_(Melbourne)https://en.wikipedia.org/wiki/CityLinkhttps://en.wikipedia.org/wiki/Maple_Ridge,_British_Columbiahttps://en.wikipedia.org/wiki/Langley,_British_Columbia_(city)https://en.wikipedia.org/wiki/Fraser_Riverhttps://en.wikipedia.org/wiki/Golden_Ears_Bridgehttps://en.wikipedia.org/wiki/Saint_John,_New_Brunswickhttps://en.wikipedia.org/wiki/Saint_John_Harbour_Bridgehttps://en.wikipedia.org/wiki/Wake_County,_North_Carolinahttps://en.wikipedia.org/wiki/Wake_County,_North_Carolinahttps://en.wikipedia.org/wiki/Triangle_Expresswayhttps://en.wikipedia.org/wiki/Interstate_540_(North_Carolina)https://en.wikipedia.org/wiki/Interstate_540_(North_Carolina)https://en.wikipedia.org/wiki/NC_Quick_Passhttps://en.wikipedia.org/wiki/Fastrakhttps://en.wikipedia.org/wiki/San_Francisco,_Californiahttps://en.wikipedia.org/wiki/San_Francisco,_Californiahttps://en.wikipedia.org/wiki/Golden_Gate_Bridgehttps://en.wikipedia.org/wiki/RFIDhttps://en.wikipedia.org/wiki/RFIDhttps://en.wikipedia.org/wiki/Electronic_toll_collectionhttps://en.wikipedia.org/wiki/Transponderhttps://en.wikipedia.org/wiki/Orange_County,_Californiahttps://en.wikipedia.org/wiki/FasTrak


11/18

14.4 Sweden 11

realized at any speed up to over 250 km per hour. If thecar does not have the smart tag, the driver is required togo to a pay station to pay the tolls between 3rd and 5thday after with a surplus charge. If he fails to do so, theowner is sent a letter home with a heavy fine. If this isnot paid, it increases five-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 ofmain cities to allow only entry from pre-registered resi-dents. It is planned to be implemented both in more roadsand in city entrance toll collection/access restriction. Theefficacy of the system is considered to be so high that itis almost impossible for the driver to complain.

See also: List of electronic toll collection systems

14.3 Charge zones – the London conges-

tion charge

The London congestion charge scheme uses 230 cameras and ANPR to help monitor vehicles in the charging zone

The London congestion charge is an example of a systemthat chargesmotorists entering a payment area. Transportfor London (TfL) uses ANPR systems and charges mo-torists a daily fee of £10 paid before 10pm if they enter,leave or move around within the congestion charge zonebetween 7 a.m. and 6:00 p.m., Monday to Friday. A re-

duced fee of £9 is paid by vehicle owners who sign upfor the automatic deduction scheme. Fines for travelingwithin the zone without paying the charge are £60 per in-fraction if paid before the deadline, doubling to £120 perinfraction thereafter.

There are currently 1,500 cameras which use automaticnumber plate recognition (ANPR) technology.[66] Thereare also a number of mobile camera units which may bedeployed anywhere in the zone.

It is estimated that around 98% of vehicles moving withinthe zone are caught on camera. The video streams aretransmitted to a data centre located in central London

where the ANPR software deduces the registration plateof the vehicle. A second data centre provides a backuplocation for image data.

Both front and back number plates are being captured,on vehicles going both in and out – this gives up to fourchances to capture the number plates of a vehicle enter-ing and exiting the zone. This list is then compared witha list of cars whose owners/operators have paid to enterthe zone – those that have not paid are fined. The regis-

tered owner of such a vehicle is looked up in a databaseprovided by the DVLA.[67]

14.4 Sweden

In Stockholm, Sweden, ANPR is used for the Stockholmcongestion tax, owners of cars driving into or out of theinner city must pay a charge, depending on the time ofthe day. From 2013, also for the Gothenburg congestiontax, which also includes vehicles passing the city on themain highways.

15 Usage

Several UK companies and agencies use ANPR sys-tems. These include Vehicle and Operator Ser-vices Agency (VOSA),[68] Driver and Vehicle LicensingAgency (DVLA)[69] and Transport for London.[70]

16 Challenges

16.1 Controversy

The introduction of ANPR systems has led to fearsof misidentification and the furthering of 1984-stylesurveillance.[71] In the United States, some such as GreggEasterbrook oppose what they call “machines that issuespeeding tickets and red-light tickets” as the beginningof a slippery slope towards an automated justice system:

“A machine classifies a person as an offender,and you can't confront your accuser becausethere is no accuser... can it be wise to es-

tablish a principle that when a machine saysyou did something illegal, you are presumedguilty?"[72]

Similar criticisms have been raised in other countries.Easterbrook also argues that this technology is employedto maximize revenue for the state, rather than to pro-mote safety.[72] The electronic surveillance system pro-duces tickets which in the US are often in excess of $100,and are virtually impossible for a citizen to contest incourt without the help of an attorney. The revenues gen-erated by these machines are shared generously with the

private corporation that builds and operates them, creat-ing a strong incentive to tweak the system to generate asmany tickets as possible.

https://en.wikipedia.org/wiki/Slippery_slopehttps://en.wikipedia.org/wiki/Gregg_Easterbrookhttps://en.wikipedia.org/wiki/Gregg_Easterbrookhttps://en.wikipedia.org/wiki/Nineteen_Eighty-Fourhttps://en.wikipedia.org/wiki/Gothenburg_congestion_taxhttps://en.wikipedia.org/wiki/Gothenburg_congestion_taxhttps://en.wikipedia.org/wiki/Stockholm_congestion_taxhttps://en.wikipedia.org/wiki/Stockholm_congestion_taxhttps://en.wikipedia.org/wiki/Stockholmhttps://en.wikipedia.org/wiki/Transport_for_Londonhttps://en.wikipedia.org/wiki/Transport_for_Londonhttps://en.wikipedia.org/wiki/London_congestion_chargehttps://en.wikipedia.org/wiki/London_congestion_chargehttps://en.wikipedia.org/wiki/List_of_electronic_toll_collection_systems


12/18

12 16 CHALLENGES

Older systems had been notably unreliable; in the UK thishas been known to lead to charges being made incorrectlywith the vehicle owner having to pay £10 in order to beissued with proof (or not) of the offense. Improvementsin technology have drastically decreased error rates, butfalse accusations arestill frequent enough to be a problem.

Perhaps the best known incident involving the abuse of anANPR database in North America is the case of Edmon-ton Sun reporter Kerry Diotte in 2004. Diotte wrote anarticle critical of Edmonton police use of traffic camerasfor revenue enhancement, and in retaliation was addedto an ANPR database of “high-risk drivers” in an at-tempt to monitor his habits and create an opportunityto arrest him.[73][74][75] The police chief and several of-ficers were fired as a result, and The Office of the Pri-vacy Commissioner of Canada expressed public concernover the “growing police use of technology to spy onmotorists.”[76]

Other concerns include the storage of information thatcould be used to identify people and store details abouttheir driving habits and daily life, contravening theData Protection Act along with similar legislation (seepersonally identifiable information). The laws in the UKare strict for any system that uses CCTV footage and canidentify individuals.[77][77][78][79][80][81][82][83][84]

Also of concern is the safety of the data once it is mined,following the discovery of police surveillance records lostin a gutter.[85][86]

ThereisalsoacaseintheUKforsayingthatuseofANPR

cameras is against the law under theRegulation of Investi-gatory Powers Act 2000.[87] The breach exists, some say,in the fact that ANPR is used to monitor the activitiesof law-abiding citizens and treats everyone like the sus-pected criminals intended to be surveyed under the act.The police themselves have been known to refer to thesystem of ANPR as a “24/7 traffic movement database”which is a diversion from its intendedpurpose of identify-ing vehicles involved in criminal activities.[88] The oppos-ing viewpoint is that where the plates have been cloned,a 'read' of an innocent motorist’s vehicle will allow theelimination of that vehicle from an investigation by vi-sual examination of the images stored. Likewise, stolenvehicles are read by ANPR systems between the time oftheft and report to the Police, assisting in the investiga-tion.

The Associated Press reported in August 2011 that NewYork Police Department cars and license plate trackingequipment purchased with federal HIDTA (High Inten-sity Drug Trafficking Area) funds were used to spy onMuslims at mosques, and to track the license plate num-bers of worshipers. [89] Police in unmarked cars outfit-ted with electronic license plate readers would drive downthe street and automatically catalog the plates of everyoneparked near the mosque, amassing a covert database thatwould be distributed among officers and used to profileMuslims in public.[90]

In 2013 the American Civil Liberties Union released26,000 pages of data about ANPR systems obtained fromlocal, state, and federal agencies through freedom of in-formation laws. “The documents paint a startling pic-ture of a technology deployed with too few rules that isbecoming a tool for mass routine location tracking and

surveillance” wrote the ACLU. The ACLU reported thatin many locations the devices were being used to store lo-cation information on vehicles which were not suspectedof any particular offense. “Private companies are also us-ing license plate readers and sharing the information theycollect with police with little or no oversight or privacyprotections. A lack of regulation means that policies gov-erning how long our location data is kept vary widely,” theACLU said.[91] In 2012 the ACLU filed suit against theDepartment of Homeland Security, which funds many lo-cal and state ANPR programs through grants, after theagency failed to provide access to records the ACLU had

requested under the Freedom of Information Act aboutthe programs.[92]

16.2 Plate inconsistency and jurisdictional

differences

Many ANPR systems claim accuracy when trained tomatch plates from a single jurisdiction or region, but can

fail when trying to recognize plates from other jurisdic-tions due to variations in format, font, color, layout, andother plate features.[93] Some jurisdictions offer vanity oraffinity plates (particularly in the US), which can createmany variations within a single jurisdiction.[94]

From time to time, US states will make significantchanges in their license plate protocol that will affectOCR accuracy. They may add a character or add a newlicense plate design. ALPR systems must adapt to thesechanges quickly in order to be effective. Another chal-lenge with ALPR systems is that some states have thesame license plate protocol. For example, more than

one state uses the standard three letters followed by fournumbers. So each time the ALPR systems alarms, it isthe user’s responsibility to make sure that the plate whichcaused the alarm matches the state associated with the li-cense plate listed on the in-car computer. For maximumeffectiveness, an ANPR system should be able to recog-nize plates from any jurisdiction, and the jurisdiction towhich they are associated, but these many variables makesuch tasks difficult.

Currently at least one US ANPR provider (PlateSmart)claims their system has been independently reviewedas able to accurately recognize the US state juris-

diction of license plates, and one European ANPRprovider claims their system can differentiate all EU platejurisdictions.[95][96]

https://en.wikipedia.org/wiki/PlateSmarthttps://en.wikipedia.org/wiki/American_Civil_Liberties_Unionhttps://en.wikipedia.org/wiki/HIDTAhttps://en.wikipedia.org/wiki/New_York_Police_Departmenthttps://en.wikipedia.org/wiki/New_York_Police_Departmenthttps://en.wikipedia.org/wiki/Associated_Presshttps://en.wikipedia.org/wiki/Regulation_of_Investigatory_Powers_Act_2000https://en.wikipedia.org/wiki/Regulation_of_Investigatory_Powers_Act_2000https://en.wikipedia.org/wiki/Personally_identifiable_informationhttps://en.wikipedia.org/wiki/Data_Protection_Act_1998https://en.wikipedia.org/wiki/Office_of_the_Privacy_Commissioner_of_Canadahttps://en.wikipedia.org/wiki/Office_of_the_Privacy_Commissioner_of_Canadahttps://en.wikipedia.org/wiki/Kerry_Diotte


13/18

13

16.3 Accuracy and measurement of ANPR

system performance

A 2008 article in Parking Trend International discussed adisparity in claimed vs. experienced license plate recog-nition 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. Earlysystems were reportedly only 60% to 80% reliable.[97]

True system error rate is the product of its subsystem er-ror rates (image capture, license plate image extraction,LP image interpretation); slight increases in subsystemerror rates can produce dramatic reductions of read rates.The effects of real-world interfering factors on read rateare not uniformly specified or tested by manufacturers.The article states “there is a need for the industry to adopta standard performance measurement protocol to enable

potential customers assess the best fit for their particularrequirements.”[97]

17 Other uses

ANPR systems may also be used for/by:

• Section control, to measure average vehicle speedover longer distances.[98]

• Border crossings

• Automobile repossessions[36][99]

• petrol stations to log when a motorist drives awaywithout paying for their fuel.

• A marketing tool to log patterns of use

• Targeted advertising, a-la “Minority Report”-stylebillboards.[100][101]

• Traffic management systems, which determine traf-fic flow using the time it takes vehicles to pass twoANPR sites[102]

• Analyses of travel behaviour (route choice,origin-destination etc.) for transport planningpurposes[103][104]

• Drive Through Customer Recognition, to automat-ically recognize customers based on their licenseplate and offer them the items they ordered the lasttime they used the service.

• To assist visitor management systems in recognizingguest vehicles.

• Police and Auxiliary Police

• Car parking companies

• Hotels

18 Related research society

• IEEE Intelligent Transportation Systems Society

19 See also• AI effect

• Applications of artificial intelligence

• Closed circuit television

• Facial recognition system

• Parking lot

• Road Policing Unit

• SPECS (speed camera)

• Vehicle location data

Lists

• List of emerging technologies

• Outline of artificial intelligence

20 References

[1] “ANPR Tutorial”. ANPR Tutorial. 15 August 2006. Re-trieved 2012-01-24.

[2] “Shan Du ; IntelliView Technol., Inc., Calgary, AB,Canada ; Ibrahim, M. ; Shehata, M. ; Badawy, Wael; Au-tomatic License Plate Recognition (ALPR): A State-of-the-Art Review”. IEEE. 1 Feb 2013. Retrieved 2014-01-09.

[3] “An introduction to ANPR”. Cctv-information.co.uk.Retrieved 2012-01-24.

[4] “CCTV network tracks 'getaway' car”. BBC News. 21November 2005. Retrieved 2013-08-12.

[5] “Plate Recognition”. PhotoCop.com.

[6] “Algorithm for License Plate Recognition”. VISL, Tech-nion. 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 artificialvision system for license plate recognition” (PDF). Dept.of Computer Science, Wayne State University. Retrieved2012-01-24.

[10] “License Plate Recognition in Turkey (Plaka Okuma Sis-temi)". Grimedia.com. Retrieved 2012-01-24.

http://www.grimedia.com/http://www.grimedia.com/https://en.wikipedia.org/wiki/Wayne_State_Universityhttp://vortex.cs.wayne.edu/papers/ijns1997.pdfhttp://vortex.cs.wayne.edu/papers/ijns1997.pdfhttps://en.wikipedia.org/wiki/University_of_Calgaryhttp://pages.cpsc.ucalgary.ca/~federl/Publications/licensePlate1996/license-plate-1996.pdfhttp://visl.technion.ac.il/projects/2003w24/http://visl.technion.ac.il/projects/2002w02/http://www.photocop.com/recognition.htmhttp://news.bbc.co.uk/1/hi/england/bradford/4455918.stmhttp://www.cctv-information.co.uk/i/An_Introduction_to_ANPRhttp://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6213519&url=http%253A%252F%252Fieeexplore.ieee.org%252Fstamp%252Fstamp.jsp%253Ftp%253D%2526arnumber%253D6213519http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6213519&url=http%253A%252F%252Fieeexplore.ieee.org%252Fstamp%252Fstamp.jsp%253Ftp%253D%2526arnumber%253D6213519http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6213519&url=http%253A%252F%252Fieeexplore.ieee.org%252Fstamp%252Fstamp.jsp%253Ftp%253D%2526arnumber%253D6213519http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6213519&url=http%253A%252F%252Fieeexplore.ieee.org%252Fstamp%252Fstamp.jsp%253Ftp%253D%2526arnumber%253D6213519http://www.anpr-tutorial.com/https://en.wikipedia.org/wiki/Outline_of_artificial_intelligencehttps://en.wikipedia.org/wiki/List_of_emerging_technologieshttps://en.wikipedia.org/wiki/Vehicle_location_datahttps://en.wikipedia.org/wiki/SPECS_(speed_camera)https://en.wikipedia.org/wiki/Road_Policing_Unithttps://en.wikipedia.org/wiki/Parking_lothttps://en.wikipedia.org/wiki/Facial_recognition_systemhttps://en.wikipedia.org/wiki/Closed_circuit_televisionhttps://en.wikipedia.org/wiki/Applications_of_artificial_intelligencehttps://en.wikipedia.org/wiki/AI_effecthttps://en.wikipedia.org/wiki/IEEE_Intelligent_Transportation_Systems_Societyhttps://en.wikipedia.org/wiki/Visitor_managementhttps://en.wikipedia.org/wiki/Minority_Report_(film)https://en.wikipedia.org/wiki/Filling_station


14/18

14 20 REFERENCES

[11] Kwaśnicka, Halina; Wawrzyniak, Bartosz (2002),“License plate localization and recognition in camerapictures” (PDF), AI-METH 2002 – Artificial IntelligenceMethods November 13–15 (Gliwice, Poland), retrieved2014-01-13

[12] Kahraman, Fatih; Gokmen, Muhittin (2003). “LicensePlate Character Segmentation Based on the Gabor Trans-form and Vector Quantization” (PDF). Archived from theoriginal (PDF) on 2006-05-24. Retrieved 2012-01-24.

[13] Ondrej Martinsky (2007). “Algorithmic and mathemati-cal principles of automatic number plate recognition sys-tems” (PDF). Brno University of Technology. Retrieved2012-01-24.

[14] “A License Plate Recognition algorithm for IntelligentTransportation System applications”. University of theAegean and National Technical University of Athens.2006. Archived from the original on 2008-04-20. Re-trieved 2012-01-24.

[15] “Automatic Number Plate Recognition”. Cctv-information.co.uk. Retrieved 2012-01-24.

[16] Sexton, Steve (3 July 2003). “License-plate spray foilstraffic cameras”. Washington Times. Retrieved 2013-07-02.

[17] Sexton, Steve (3 July 2003). “License-plate spray foilstraffic cameras”. Washington Times. Retrieved 2013-07-02.

[18] Wentworth, Jeff. “Obscured license plate could be mo-torists’ ticket to fine”. Texas State Senate. Archived from

the original on 24 March 2005. Retrieved 5 April 2005.

[19] http://www.sunflexzone.com/product/stealth-anti-tracking-ir-infrared-license-plate-blocker-privacy-frame-alpr-countermeasure#.VVrj2kbEnrg

[20]

[21] “eTendering - Contract Award Notice Detail View -01092010RFT”. Tenders.nsw.gov.au. Retrieved 2014-04-23.

[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 sys-tem nicks drivers”. Illawarra Mercury. Retrieved 2014-04-23.

[24] “ANPR in Mechelen”. Belgium.

[25] “Politiet vil tjekke millioner af danske nummerplader”.Denmark: B.dk.

[26] “Portiques écotaxe. Ils copient la plaqued’immatriculation de Hollande”. OuestFrance. Ouest-France. Retrieved 21 Feb 2014.

[27] “Das Bundesverfassungsgericht” (in German). Bverfg.de.3 November 2008. Retrieved 2009-02-16.

[28] “TraffiCapture”. Jenoptic.com.

[29] “VÉDA Közúti Intelligens Kamerahálózat” (in Hungar-ian). Országos Rendőr-főkapitányság. Retrieved 2015-09-02.

[30] “Matrix Police”. Hungary. Retrieved 2012-01-24.

[31] “Turk Telekom deploys traffic surveillance service in

Ankara”. Telecompaper. 2010-12-09. Retrieved 2012-08-03.

[32] “Video control”. Ukraine: Ollie.com.ua.

[33] “How are Innovations in Technology Transforming Polic-ing?" (PDF). Police Executive Research Forum. January2012.

[34] “Cameras for insurance verification considered”. TulsaWorld . 29 November 2009.

[35] “License Plate Reader Technology Enhances the Identi-fication, Recovery of Stolen Vehicles”. FBI . September

2011.

[36] Belson, Ken (28 February 2010). “The Wired Repo Man:He’s Not ‘As Seen on TV’". New York Times. Retrieved2012-01-24.

[37] “License plate data not just for cops: Private companiesare tracking your car”. NBC News. 19 July 2013.

[38] Vehicle registration plates of Saudi Arabia

[39] “Arabic Licence Plate Recognition”. Sourceforge.

[40] “Polisens nya vapen: “Terminator"-teknik”. Sweden: Ex-pressen.se.

[41] “Section Control: 24.000 Raser angezeigt” (in German).Austria: ORF.at. 7 June 2010.

[42] “Flitsers.net”.

[43] “Ecco come funziona il Tutor in autostrada - Notizie brevi- News - Informazione - A.S.A.P.S. Il Portale della Si-curezza Stradale”. Asaps.it. Retrieved 2012-08-03.

[44] “Description of the system” (in Dutch). Dutch AttorneyGeneral. 31 December 2009. Retrieved 2012-01-24.

[45] “Llegan los radares de velocidad media a España” (in

Spanish). Noticias.coches.com. 23 September 2009. Re-trieved 2012-01-24.

[46] “Speeding tickets can potentially be avoided by changinglanes”. The Daily Mail (London). 15 October 2006. Re-trieved 2012-01-24. The Home Office admitted last nightthat drivers can avoid being caught the by hi-tech 'SPECS'cameras which calculate a car’s average speed over a longdistance.

[47] “Frequently Asked Question over Trajectcontrole” (inDutch). Dutch Attorney General. Retrieved 2012-01-24.

[48] “Autostrade S.p.A” (in Italian). Autostrade.it. 2008-05-25. Retrieved 2012-08-03.

[49] “Niemand rijdt meer te hard op de A2” (inDutch). Trouw.18 October 1997. Retrieved 2012-01-24.

http://www.trouw.nl/tr/nl/5009/Archief/archief/article/detail/2557704/1997/10/18/Niemand-rijdt-meer-te-hard-op-de-A2.dhtmlhttp://www.autostrade.it/assistenza-al-traffico/tutor.html?initPosAra=3_4http://www.om.nl/onderwerpen/verkeer/veelgestelde_vragen/trajectcontrole/http://www.dailymail.co.uk/pages/live/articles/news/news.html?in_article_id=410539&in_page_id=1770http://www.dailymail.co.uk/pages/live/articles/news/news.html?in_article_id=410539&in_page_id=1770http://noticias.coches.com/noticias-motor/llegan-los-radares-de-velocidad-media-a-espana/5797http://www.trajectcontrole.nl/http://www.asaps.it/34253-Ecco_come_funziona_il_Tutor_in_autostrada.htmlhttp://www.asaps.it/34253-Ecco_come_funziona_il_Tutor_in_autostrada.htmlhttp://www.asaps.it/34253-Ecco_come_funziona_il_Tutor_in_autostrada.htmlhttp://trajectcontroles.net/http://ooe.orf.at/stories/448174/http://www.expressen.se/kvallsposten/polisens-nya-vapen-terminator-teknik/https://sourceforge.net/projects/arabiclicenceplaterecognition/https://en.wikipedia.org/wiki/Vehicle_registration_plates_of_Saudi_Arabiahttp://investigations.nbcnews.com/_news/2013/07/19/19548772-license-plate-data-not-just-for-cops-private-companies-are-tracking-your-car?litehttp://investigations.nbcnews.com/_news/2013/07/19/19548772-license-plate-data-not-just-for-cops-private-companies-are-tracking-your-car?litehttp://www.nytimes.com/2010/02/28/automobiles/28REPO.htmlhttp://www.nytimes.com/2010/02/28/automobiles/28REPO.htmlhttp://www.fbi.gov/about-us/cjis/cjis-link/september-2011/license-plate-reader-technology-enhances-the-identification-recovery-of-stolen-vehicles/http://www.fbi.gov/about-us/cjis/cjis-link/september-2011/license-plate-reader-technology-enhances-the-identification-recovery-of-stolen-vehicles/https://en.wikipedia.org/wiki/Tulsa_Worldhttps://en.wikipedia.org/wiki/Tulsa_Worldhttp://www.tulsaworld.com/news/article.aspx?subjectid=16&articleid=20091129_16_A20_OKLAHO172449http://policeforum.org/library/critical-issues-in-policing-series/Technology_web2.pdfhttp://policeforum.org/library/critical-issues-in-policing-series/Technology_web2.pdfhttp://ollie.com.ua/eng/content/system-integration-field-search-vehicleshttp://www.telecompaper.com/news/turk-telekom-deploys-traffic-surveillance-service-in-ankarahttp://www.telecompaper.com/news/turk-telekom-deploys-traffic-surveillance-service-in-ankarahttp://www.matrixpolice.hu/matrix/index.php?Rendszamfelismeres:Matrix_Policehttp://www.police.hu/a-rendorsegrol/europai-tamogatasok/operativ-programok/veda-kozuti-intelligens-kamerahalozathttp://www.jenoptik.com/Internet_EN_TraffiCapturehttp://www.bverfg.de/entscheidungen/rs20080311_1bvr207405.htmlhttp://www.ouest-france.fr/portiques-ecotaxe-ils-copient-la-plaque-dimmatriculation-du-president-1948553http://www.ouest-france.fr/portiques-ecotaxe-ils-copient-la-plaque-dimmatriculation-du-president-1948553http://www.b.dk/nationalt/politiet-vil-tjekke-millioner-af-danske-nummerpladerhttp://www.lokalepolitie.be/5358/nieuws/1-latest-news/2175-automatische-nummerplaat-herkenningscameras-een-eerste-balans.htmlhttp://www.illawarramercury.com.au/story/113726/mass-surveillance-system-nicks-drivers/http://www.illawarramercury.com.au/story/113726/mass-surveillance-system-nicks-drivers/http://www.police.nsw.gov.au/__data/assets/pdf_file/0008/184886/Annual_Report_-_Year_in_Review.pdfhttp://www.police.nsw.gov.au/__data/assets/pdf_file/0008/184886/Annual_Report_-_Year_in_Review.pdfhttps://tenders.nsw.gov.au/?event=public.cn.view&CNUUID=F80634CC-A61C-131B-927280D5FB09C2EBhttps://tenders.nsw.gov.au/?event=public.cn.view&CNUUID=F80634CC-A61C-131B-927280D5FB09C2EBhttp://www.sunflexzone.com/product/stealth-anti-tracking-ir-infrared-license-plate-blocker-privacy-frame-alpr-countermeasure#.VVrj2kbEnrghttp://www.sunflexzone.com/product/stealth-anti-tracking-ir-infrared-license-plate-blocker-privacy-frame-alpr-countermeasure#.VVrj2kbEnrghttp://www.sunflexzone.com/product/stealth-anti-tracking-ir-infrared-license-plate-blocker-privacy-frame-alpr-countermeasure#.VVrj2kbEnrghttp://web.archive.org/web/20050324021038/http://www.senate.state.tx.us/75r/Senate/members/dist25/pr03/p092603a.htmhttp://www.senate.state.tx.us/75r/senate/members/dist25/pr03/p092603a.htmhttp://www.senate.state.tx.us/75r/senate/members/dist25/pr03/p092603a.htmhttps://en.wikipedia.org/wiki/Jeff_Wentworthhttp://www.phantomplate.com/print_washingtontimes.htmlhttp://www.phantomplate.com/print_washingtontimes.htmlhttp://www.washingtontimes.com/news/2003/jul/3/20030703-120901-3612r/http://www.washingtontimes.com/news/2003/jul/3/20030703-120901-3612r/http://www.cctv-information.co.uk/constant3/anpr.htmlhttp://www.aegean.gr/culturaltec/canagnostopoulos/cv/new%2520site/journals.htmhttps://en.wikipedia.org/wiki/National_Technical_University_of_Athenshttps://en.wikipedia.org/wiki/University_of_the_Aegeanhttps://en.wikipedia.org/wiki/University_of_the_Aegeanhttp://web.archive.org/web/20080420191357/http://www.aegean.gr/culturaltec/canagnostopoulos/cv/new%2520site/journals.htmhttp://web.archive.org/web/20080420191357/http://www.aegean.gr/culturaltec/canagnostopoulos/cv/new%2520site/journals.htmhttp://javaanpr.sourceforge.net/anpr.pdfhttp://javaanpr.sourceforge.net/anpr.pdfhttp://javaanpr.sourceforge.net/anpr.pdfhttp://www.be.itu.edu.tr/~kahraman/License%2520Plate%2520Character%2520Segmentation%2520Based%2520on%2520the%2520Gabor%2520Transform%2520and%2520Vector%2520Quantization.pdfhttp://www.be.itu.edu.tr/~kahraman/License%2520Plate%2520Character%2520Segmentation%2520Based%2520on%2520the%2520Gabor%2520Transform%2520and%2520Vector%2520Quantization.pdfhttp://web.archive.org/web/20060524182049/http://www.be.itu.edu.tr/~kahraman/License%2520Plate%2520Character%2520Segmentation%2520Based%2520on%2520the%2520Gabor%2520Transform%2520and%2520Vector%2520Quantization.pdfhttp://web.archive.org/web/20060524182049/http://www.be.itu.edu.tr/~kahraman/License%2520Plate%2520Character%2520Segmentation%2520Based%2520on%2520the%2520Gabor%2520Transform%2520and%2520Vector%2520Quantization.pdfhttp://web.archive.org/web/20060524182049/http://www.be.itu.edu.tr/~kahraman/License%2520Plate%2520Character%2520Segmentation%2520Based%2520on%2520the%2520Gabor%2520Transform%2520and%2520Vector%2520Quantization.pdfhttps://www.ii.pwr.edu.pl/~kwasnicka/download/kwasnickawawrzyniak.pdfhttps://www.ii.pwr.edu.pl/~kwasnicka/download/kwasnickawawrzyniak.pdf


15/18

15

[50] “Nummerborden lezen op de A13” (in Dutch). Trouw. 6May 2002. Retrieved 2012-01-24.

[51] Kreling, Tom (28 August 2008). “Een duur foutje vande computer” (in Dutch). NRC Handelsblad . Retrieved2012-01-24.

[52] “SPECS - average speed cameras on SPECS”.A77safetygroup.com. 14 July 2005. Retrieved2012-01-24.

[53] “Jeremy Clarkson tilts at windmills – Speed cameraavoid-ance is an urban myth”. The Register . 21 July 2008. Re-trieved 23 January 2012.

[54] base-security-and-investigations/ “US Navy SelectsPlateSmart® Exclusively to Help with Base Securityand Investigations” Check |url= scheme (help). DefenseProcurement News. 4 March 2013.

[55] “After Boston: The pros and cons of surveillance cam-

eras”. CNN Tech. 26 April 2013.

[56] “License Plate Recognition, Tribal Casinos, and BannedPersons” (PDF). Indiangaming.com. February 2011.

[57] “Recognising a new way to keep traffic moving”. Siemen-straffic.com. Retrieved 2012-01-24.

[58] “PIPS supplies Journey Time Measurement Systems toTrafficmaster”. PIPS Technology. Archived from theoriginal on 2009-01-24. Retrieved 2012-01-24.

[59] “BLURA License Plate Recognition Engine”. Blura.com.Retrieved 2012-01-24.

[60] “Trunk Roads – PTFM”. Trafficmaster.co.uk. Retrieved2012-01-24.

[61] Hansen, Megan and Will Jason (27 Mar 2013). “GoldenGate Bridge sees smooth transition to all-electronic tolls”.Marin Independent Journal . Retrieved 17 May 2013.

[62] “HugeDomains.com - SaintjohnHarbourBridge.com is forSale”. 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] "". Fetc.net.tw. 2006-02-10. Retrieved 2014-04-23.

[66] “Met given real time c-charge data”. BBC . 17 July 2007.Archived from the original on 13 September 2007. Re-trieved 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

[71] Mathieson, SA (19 June 2003). “Keeping 1984 in thepast”. The Guardian (UK).

[72] Easterbrook, Gregg (28 February 2005). “Daily Express- Lights, Camera, Action”. The New Republic Online.Archived from the original on 2005-09-03.(subscriptionrequired)

[73] “Edmonton officer reprimanded for checking up on news-paper columnist”. CBC News. 14 November 2005.

[74] “CBC Edmonton - Features - Edmonton Police”. CBCNews. Archived from the original on 2007-10-23. Re-trieved 2 July 2013.

[75] “Officer faces suspension for Overtime sting”. EdmontonPolice Watch. 6 September 2008. Retrieved 2012-01-24.

[76] “Canada: Privacy Commissioner Concerned Over Li-cense Plate Spying”. Thenewspaper.com. 3 July 2007.Retrieved 2012-01-24.

[77] Lettice, John (21 February 2003). “The London chargezone, 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 Officers) ANPRSteering Group. 17 March 2005. Archived from the orig-inal on 2010-03-31. Retrieved 2012-01-24.

[79] “Driving crime down” (PDF). London: UK GovernmentHome Office. 22 October 2004. Archived from the orig-inal (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 March2005.

[81] Hofman, Yoram. “License Plate Recognition – A Tuto-rial”. Archived from the original on 24 March 2005. Re-trieved 28 March 2005.

[82] Lucena, Raul (24 August 2006). “Automatic NumberPlate 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. Retrieved28 March 2005.

[84] “Recognizing a new way to keep traffic moving”. SiemensTraffic. Archived from the original on 17 April 2005. Re-trieved 3 April 2005.

[85] “UK: Traffic Camera Data Dropped in Gutter”. thenews-paper.com. Retrieved 2012-01-24.

[86] Clements, Jon (11 March 2008). “A police memory stickcontaining secret data is found in gutter”. The Mirror (UK). Retrieved 2013-07-02.

[87] “Regulation of Investigatory Powers Act 2000”. legisla-tion.gov.uk . The National Archives. 2000. Retrieved2012-01-24.

[88] “Police number plate cameras may breach RIPA - Com-missioner”. TheRegister.com. 17 July 2006. Retrieved2012-01-24.

http://www.theregister.co.uk/2006/07/17/anpr_ripa_breach/http://www.theregister.co.uk/2006/07/17/anpr_ripa_breach/http://www.legislation.gov.uk/ukpga/2000/23/contentshttp://www.mirror.co.uk/news/top-stories/2008/03/11/memory-loss-115875-20347364/http://www.mirror.co.uk/news/top-stories/2008/03/11/memory-loss-115875-20347364/http://www.thenewspaper.com/news/22/2265.asphttp://web.archive.org/web/20050417235558/http://www.siemenstraffic.com/customcontent/case_studies/anpr/anpr.htmlhttp://www.siemenstraffic.com/customcontent/case_studies/anpr/anpr.htmlhttp://web.archive.org/web/20050328030712/http://www.theregister.co.uk/2005/03/24/anpr_national_system/http://www.theregister.co.uk/2005/03/24/anpr_national_system/http://www.theregister.co.uk/2005/03/24/anpr_national_system/http://www.anpr-tutorial.com/http://www.anpr-tutorial.com/http://web.archive.org/web/20050324015141/http://licenseplaterecognition.com/http://www.licenseplaterecognition.com/http://www.licenseplaterecognition.com/http://web.archive.org/web/20050321183720/http://www.cctv-information.co.uk/constant3/anpr.htmlhttp://www.cctv-information.co.uk/constant3/anpr.htmlhttp://police.homeoffice.gov.uk/news-and-publications/publication/operational-policing/Driving_Crime_Down_-_Denyin1.pdf?view=Binaryhttp://police.homeoffice.gov.uk/news-and-publications/publication/operational-policing/Driving_Crime_Down_-_Denyin1.pdf?view=Binaryhttp://web.archive.org/web/20070108130446/http://police.homeoffice.gov.uk/news-and-publications/publication/operational-policing/Driving_Crime_Down_-_Denyin1.pdfhttp://www.acpo.police.uk/asp/policies/Data/anpr_strat_2005-08_march05_12x04x05.dochttp://www.acpo.police.uk/asp/policies/Data/anpr_strat_2005-08_march05_12x04x05.dochttp://web.archive.org/web/20100331060419/http://www.acpo.police.uk/asp/policies/Data/anpr_strat_2005-08_march05_12x04x05.dochttp://www.theregister.co.uk/2003/02/21/the_london_charge_zone/http://www.theregister.co.uk/2003/02/21/the_london_charge_zone/http://www.thenewspaper.com/news/29/2933.asphttp://www.thenewspaper.com/news/29/2933.asphttp://www.edmontonpolicewatch.org/?p=325http://www.cbc.ca/edmonton/features/policehttp://web.archive.org/web/20071023000706/http://www.cbc.ca/edmonton/features/police/http://www.cbc.ca/news/canada/story/2005/11/14/edmonton-police-051114.htmlhttp://www.cbc.ca/news/canada/story/2005/11/14/edmonton-police-051114.htmlhttps://ssl.tnr.com/p/docsub.mhtml?i=w050228&s=easterbrook022805http://web.archive.org/web/20050903045944/https://ssl.tnr.com/p/docsub.mhtml?i=w050228&s=easterbrook022805http://web.archive.org/web/20050903045944/https://ssl.tnr.com/p/docsub.mhtml?i=w050228&s=easterbrook022805http://www.guardian.co.uk/technology/2003/jun/19/newmedia.mediahttp://www.guardian.co.uk/technology/2003/jun/19/newmedia.mediahttp://www.cclondon.com/https://www.gov.uk/government/organisations/driver-and-vehicle-licensing-agencyhttps://www.gov.uk/government/organisations/driver-and-vehicle-licensing-agencyhttp://www.vosa.gov.uk/http://www.cclondon.com/http://web.archive.org/web/20070913102002/http://news.bbc.co.uk/1/hi/uk_politics/6902543.stmhttps://en.wikipedia.org/wiki/BBChttp://news.bbc.co.uk/1/hi/uk_politics/6902543.stmhttp://www.fetc.net.tw/externalFETC/english/en_01.htmlhttp://www.autopistacentral.cl/http://www.translink.ca/en/Driving/Golden-Ears-Bridge.aspxhttp://www.translink.ca/en/Driving/Golden-Ears-Bridge.aspxhttp://www.saintjohnharbourbridge.com/request.htmhttp://www.saintjohnharbourbridge.com/request.htmhttps://en.wikipedia.org/wiki/Marin_Independent_Journalhttp://www.marinij.com/ci_22880388/last-toll-taker-leaves-golden-gate-bridge-switchhttp://www.marinij.com/ci_22880388/last-toll-taker-leaves-golden-gate-bridge-switchhttp://www.trafficmaster.co.uk/page.cfm?key=network_ptfm-networkhttp://www.blura.com/http://www.pipstechnology.co.uk/script/download_document.php?file_id=9http://www.pipstechnology.co.uk/script/download_document.php?file_id=9http://web.archive.org/web/20090124162912/http://www.pipstechnology.co.uk/script/download_document.php?file_id=9http://web.archive.org/web/20090124162912/http://www.pipstechnology.co.uk/script/download_document.php?file_id=9http://www.siemenstraffic.com/customcontent/case_studies/anpr/anpr.htmlhttp://www.indiangaming.com/istore/Feb11_Wanser.pdfhttp://www.indiangaming.com/istore/Feb11_Wanser.pdfhttp://www.cnn.com/2013/04/26/tech/innovation/security-cameras-boston-bombings/index.htmlhttp://www.cnn.com/2013/04/26/tech/innovation/security-cameras-boston-bombings/index.htmlhttps://en.wikipedia.org/wiki/Help:CS1_errors#bad_urlhttp://www.defenseprocurementnews.com/2013/03/04/us-navy-selects-platesmart-exclusively-to-help-with-http://www.defenseprocurementnews.com/2013/03/04/us-navy-selects-platesmart-exclusively-to-help-with-http://www.defenseprocurementnews.com/2013/03/04/us-navy-selects-platesmart-exclusively-to-help-with-http://www.theregister.co.uk/2008/07/21/speed_camera_myth/http://www.theregister.co.uk/2008/07/21/speed_camera_myth/http://www.a77safetygroup.com/index.cfm/page/40http://archief.nrc.nl/index.php/2008/Augustus/28/Economie/14/Een+duur+foutje+van+de+computer/check=Yhttp://archief.nrc.nl/index.php/2008/Augustus/28/Economie/14/Een+duur+foutje+van+de+computer/check=Yhttp://www.trouw.nl/tr/nl/5009/Archief/archief/article/detail/2791819/2002/05/06/Nummerborden-lezen-op-de-A13.dhtml


16/18

16 20 REFERENCES

[89] “Money for nothing: the drug war and the war on Mus-lims”.

[90] Green, Jonah (24 February 2012). “NYPD Defends Tac-tics Over Mosque Spying; Records Reveal New DetailsOn Muslim Surveillance”. Huffington Post .

[91] “ACLU raises privacy concerns about police technologytracking drivers - CNN.com”. CNN . 18 July 2013.

[92] Klein, Allison (26 September 2012). “ACLU files suitover info on license plate readers”. The Washington Post .

[93] “Automated License Plate Recognition Systems: Policyand Operational Guidance for Law Enforcement” (PDF).U.S. Department of Justice, National Institute of Justice.2012.

[94] “New Developments In ALPR”. Police Technology Mag-azine. 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). ParkingTrend International . June 2008. Retrieved 2012-01-24.

[98] “Section control”. Verkeershandhaving Dossiers.Archived from the original on 2006-05-12. Retrieved2012-01-24.

[99] “High-Tech System Helps Repo ManFind Cars”. WFTV.November 11, 2009.

[100] “UK Billboards Equipped with License Plate Spy Cam-eras”. TheNewspaper.com. 25 September 2009. Re-trieved 2013-07-02.

[101] “UK Billboards Equipped with License Plate Spy Cam-eras”. 25 September 2009. Retrieved 2013-07-02.

[102] “Extreme CCTV Announces Contract for StockholmTraffic Cameras” (PDF). Extremecctv.com. 22 April2004. 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 ob-

servance of travel behavior”. Universität Stuttgart Institutfür Straßen und Verkehrswesen. Retrieved 2013-07-02.

[104] Friedrich, Markus; Jehlicka, Prokop; Schlaich, Johannes(2008). “Automatic number plate recognition for the ob-servanceof travel behavior” (PDF). 8th International Con-

ference on Survey Methods in Transport: Harmonisationand DataComparability, May 2008, Annecy, France. Uni-versität Stuttgart Institut für Straßen und Verkehrswesen.Retrieved 2013-07-02.

http://www.isv.uni-stuttgart.de/vuv/publication/downloads/200805_Fr_PJ_JS-ANPR.pdfhttp://www.isv.uni-stuttgart.de/vuv/publication/downloads/200805_Fr_PJ_JS-ANPR.pdfhttp://www.mendeley.com/research/automatic-number-plate-recognition-observance-travel-behaviorhttp://www.mendeley.com/research/automatic-number-plate-recognition-observance-travel-behaviorhttp://www.extremecctv.com/pdf/productnews/CN040422-Extreme-CCTV-Announces-Contract-for-Stockholm-Traffic-Cameras.pdfhttp://web.archive.org/web/20080409035619/http://www.extremecctv.com/pdf/productnews/CN040422-Extreme-CCTV-Announces-Contract-for-Stockholm-Traffic-Cameras.pdfhttp://web.archive.org/web/20080409035619/http://www.extremecctv.com/pdf/product

automatic number plate recognition.pdf

Documents