It is more simple: All the necessary elements for the ANPR process
are integrated in the same housing. Only one device is necessary for
each lane to be controlled. The equipment may be connected by
Ethernet or serial communication with the client application
The ANPR process is divided into three steps. The detection of the vehicle,
the capture of the images and the process of recognition. Next, we will
detail step by step how it works and depending on each case what the
advantages and disadvantages are
o Type of cameras:
Examples
In the above example: while the vehicle approaches the gate, the LPR unit
automatically "reads" the license plate registration number, compares to a
predefined list and opens the gate if there is a match.
The system uses illumination (such as Infra-red) and a camera to take the image of
the front or rear of the vehicle, then an image-processing software analyzes the
images and extracts the plate information. This data is used for enforcement, data
collection, and (as in the access-control system featured above) can be used to open
a gate if the car is authorized or keep a time record on the entry or exit for
automatic payment calculations.
The LPR system significant advantage is that the system can keep an image record
of the vehicle which is useful in order to fight crime and fraud ("an image is worth
a thousand words"). An additional camera can focus on the driver face and save the
image for security reasons. Additionally, this technology does not need any
installation per car (such as in all the other technologies that require a transmitter
added on each car or carried by the driver).
The car, with the plate number: W856RKX, is just exiting from the secured area
and is picked up by the LPR system which identifies it as an authorized car and
opens the gate. A welcome display (which includes the vehicle number and driver
name) is displayed in the large outdoor display in the back of the car.
A typical image captured by the Infra-red illumination and camera unit is shown in
the following image (this image is of the same car above). The image information
is read by the LPR unit and is analyzed and recognized automatically. Note that the
image is monochrome since the infra-red spectrum is above the normal color
spectrum.
Since the vehicle plates are based on different Country standards, they usually
different in form, shape and material. Therefore the LPR systems are Country
specific and are adapted to the Country where they are installed and used (in the
above case - a UK installation). You can see a large collection of plates of different
Countries - download some recognition demoes with the link at the bottom of this
page.
Some plates have additional information written or attached to the plate, such as
state identification (as in USA plates in upper smaller row), province initials (such
as in China upper row), plate issue date lable (such as in USA plates), vehicle type
(such as in Korea in an upper row), Country flag (as in Europe on the left side),
and more. For most applications this additional information is not required (and is
usually not identified due to the complexity, variation, quality and resolution).
The vehicle
approached the
secured area,
and starts the
cycle by
stepping over a
magnetic loop
detector (which
is the most
popular vehicle
sensor). The loop
detector senses
the car and its
presence is
signaled to the
LPR unit.
The authorized
vehicle enters
into the secured
area. After
passing the gate
its detector
closes the gate.
Now the system
waits for the
next vehicle to
approach the
secured area.
Other types of applications use the information retrieved from the image for
different purposes. For example, to prepare a speed or red-light violation ticket. All
rely on automatic image understanding process performed by the LPR unit, which
actually mimics the human mind.
Typical applications
LPR applications have a wide range of applications, which use the
extracted plate number and optional images to create automated
solutions for various problems. These include the following sample
applications (for more information, click on the link in the bottom
of the tutorial) :
Access Control - a gate automatically opens for authorized members in a secured area, thus
replacing or assisting the security gaurd. The events are logged on a database and could be
used to search the history of events.
Tolling - the car number is used to calculate the travel fee in a toll-road, or used to double-
check the ticket.
Border Control - the car number is registered in the entry or exits to the Country, and used to
monitor the border crossings. It can short the border crossing turnaround time and cut short
the typical long lines.
Stolen cars - a list of stolen cars or unpaid fines is used to alert on a passing 'hot' cars. The
'black list' can be updated in real time and provide immediate alarm to the police force. The
LPR system is deployed on the roadside, and performs a real-time match between the passing
cars and the list. When a match is found a siren or display is activated and the police officer is
notified with the detected car and the reasons for stopping the car.
Traffic control - the vehicles can be directed to different lanes according to their entry
permits (such as in University complex projects). The system effectively reduces traffic
congestions and the number of attendents.
Airport Parking - In order to reduce ticket fraud or mistakes, the LPR unit is used to capture
the plate number and image of the cars. The information may be used to calculate the parking
time or provide a proof of parking in case of a lost ticket - a typical problem in airport
parking which have relatively long (and expensive) parking durations.
An object obscuring (part of) the plate, quite often a tow bar, or the plate is broken or
dirt on the plate.
A different font, popular for vanity plates (some countries do not allow such plates,
eliminating the problem).
Lack of coordination between countries or states. Two cars from different countries or
states can have the same number but different design of the plate and different country
code.
To maximize the chances of effective 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. Analize a live
video stream or a picture are really time-consuming operations.
2. Detection:
According to the new idea of additional thresholding entirely black pixel rows appear repeatedly in the image
after pre-processing. The white license plate area is situated somewhere between those black rows. By
finding the longest vertical array of white pixels, it is possible to detect the left and the right edge of the
license plate. When analyzing the image from left to right, the first longest vertical array of white pixels
represents the left edge of the license plate. Accordingly, the last white column of the same size represents
the right edge of the license plate. By finding the longest horizontal array of white pixels, it is possible to detec
the top and the bottom of the license plate. Positions of these license plate edges are sufficient to
detectcoordinates of the license plate.
3. Segmentation:
The next step is segmentation of the license plate area into smaller parts which represent each character of
the license plate. We often apply the adaptive thresholding filter to enhance an area of the plate before
segmentation. The adaptive thresholding is used to separate dark foreground from light background with non-
uniform illumination. Vertical projection of a binary image looks like a set of black hills on a white surface. This
is obtained by counting the number of black pixels in each column. Columns without black pixels represent
the spacing between each character. Coordinates of each character are then determined with alternatively
found left and right hill edge
4. Recognition
The process of character recognition is repeated for each character image obtained in the last step. This
process could be carried out in several steps. The output of this process should be a recognized character.
The set of possible outputs are characters that appear on license plates, which are letters of the alphabet,
numbers from 0 to 9 and special characters like a dash. Algorithms also look for characters of equal color and
equidistance, with similar font structures to break apart each individual character. This sequential congruency
of the characters embodies a characteristic set that is typically uniform, regardless of the type of license
plate. Character Segmentation separates each letter or number where it is subsequently processed by optical
character recognition algorithms. In order to simplify recognition, the initial step is to separate possible
outputs into smaller groups counting the character end points. In some situations when the recognition
mechanism fails, there is a possibility to detect a failure by a syntactical analysis of the recognized plate. If
we have country-specific rules for the plate, we can evaluate the validity of that plate towards these rules.
Automatic syntax-based correction of plate numbers can increase recognition abilities of the whole ANPR
system.
Six Algorithms of License Plate Recognition
1. License Plate Localization
Vehicles are moving objects and their rate of velocity must be accounted
for in the algorithm's design. This speed creates further complexity as a
license plates image is angularly skewed and subjected to refractory
issues from light changes. External hardware components and filters may
be used to control for light fluctuation.(See External Hardware)
Many countries are now adopting license plates that are also
retroreflectors. Essentially, these types of license plates improve the
visual qualities of the image by reflecting light back in the same direction
of the source with minimal scatter. This retroreflective ability improves
reading ability substantially by algorithms.
Components of algorithms that adjust for the angular skew of the license plate image to accurately
sample, correct, and proportionally recalculate to an optimal size.
3. Normalization
Algorithm for regulating the contrast and brightness of the captured license plate image.
4. Character segmentation
Algorithm that locates the separate alpha numeric characters on a license plate.
Algorithms also look for characters of equal color and equidistance, with similar font structures to
break apart each individual character. This sequential congruency of the characters embodies a
characteristic set that is typically uniform, regardless of the type of license plate. Character
Segmentation separates each letter or number where it is subsequently processed by optical
character recognition(OCR) algorithms.
Algorithm for Translating the captured image into an alpha numeric text entry.