Introduction:

Automatic Number Plate Recognition (or 'number plate recognition') is a special form
of optical character recognition (OCR).
It enables computer systems to read automatically the registration number (license
number) of vehicles from digital pictures.
Reading automatically the registration number means transforming the pixels of the
digital image into the ASCII text of the number plate.
OCR technology scans paper documents and turns them into electronic, editable files.
Capturing of fast moving vehicles needs special technique to avoid motion blur. To
ensure the right image quality short shutter time is used with high-power illumination.
The best illumination is the IR, because the retro-reflective plates reflect this kind of
light and it is undetectable for the human eye.
This combination works fine during day and night and provides constant good image
quality.
Only dedicated ANPR cameras meet these requirements, which provide flexible
shutter control with built-in IR flash and able to catch the vehicles up to 250km/h
which is suitable for all kind of license plate reading applications.
ANPR has two technological issues:
o The quality of license plate recognition software with its applied recognition
algorithms, and
o The quality of image acquisition technology, the camera and the illumination.
The very key factor is the number plate recognition software.
A sophistication recognition software should have following features
o the highest recognition accuracy
o the fastest processing speed
o the most type of number plates it can handle,
o the widest range of picture quality it can handle,
o the most tolerant against distortions of input data .

Character Recognition:
Image of the vehicle number plate captured from the camera is converted to the
grascaled image.
 Image consisting characterstics from A to Z and numbers from 0 to 9.
Binary image consisting of only 1s and 0s (only black and white).
The essential point for binarization is the thresholding.By thresholding the pixel
values of 0 (black) for all of image with luminance less than threshold Value and
1(white) for all other pixels.
Characters segmentation:
In the segmentation of the plate characters, the vehicle number plate is segmented in
to its constitutes to obtain its characters individually.
Image filtering from unwanted spots and noise.
Dilation of image to separate characters from each others.

Separating the plate characters:

9
It is done by finding starting and end points of characters in horizontal direction.

TSBT
Normalization of characters:
Normalization is to refine the characters into a block containing no extra white space (pixels)
in all four sides of the characters. Sometimes called contrast stretching. Then each character
should be equal in size.

3389
Extraction of Number Plate Location
In this step the number plate is extracted by firstly converting RGB Image i.e., the captured
image to Gray Scale Image. Here mathematical morphology is used to detect the region and
Sobel operators are used to calculate the threshold value. After this we get a dilated image.
Then imfill function is used to fill the holes so that we get a clear binary image.

Segmentation and Recognition of Plate Character

Here bounding box technique is used for segmentation. The bounding box is used to measure
the properties of the image region. The basic step in recognition of vehicle number plate is to
detect the plate size. Here the segmented image is multiplied with gray scale image so that we
only get the number plate of the vehicle.
 Applications:
Intelligent Transportation Systems (ITS),
security systems
motorway toll collection (highway toll collection),
traffic analysis,
police law enforcement,
state border control,
enforcement of traffic regulations,
vehicle theft prevention,
automation and simplification of airport,
harbor and warehouse logistics,
security monitoring of roads and checkpoints
vehicle surveillance