Abstract: converted into grayscale image. The first step to

Abstract:  Car number plate Recognition is a part of digital image
processing. Template Matching algorithm
of Object Character Recognition methods is 
usedto identify the Number plate.
First the input color image is converted
to gray scale image for easy to handle and simple way to find the location
in the number plate. This system uses blurred
regions and different font style and sizes using the character reorganization.

 

Proposed
Work:This process
contains three steps—

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

1.    
Vehicle number plate extraction

2.    
 character segmentation

3.    
Optical Character Recognition (OCR).

·       
The
purpose of edge detection is significantly reducing the amount of data in an
image.The edge detection is performed on 
the number plate area. Canny edge
detection algorithm produce better output than the other edge detection
algorithms.

·       
The
detected number plate is pre-processed to remove the noise and then the result
is passed to the segmentation part to segment the individually characters from
the extracted number plate.

·       
In
OCR, the characters are recognized using Template matching

·       
Detected
image converted to the gray scale image.

 

Methodology
:

Ø  Acquire Images

Ø  Pre-processing

Ø  Compute  Edge Detection

Ø  Apply Morphological
Operations

Ø  Perform Character
Segmentation

Ø  Perform Image
Enhancement

Ø  Optical Character
Recognition (Using Template Matching)

Ø  Number Plate
Extraction 

A.
Pre-Processing :

RGB to Grayscale Conversion—

        In RGB format, each Pixel has three colourcomponents:
Red, Green, and Blue. In pre-processing step, the colour image is given as an
input and it is converted into grayscale image.

The first
step to digitize a “black and white” image composed of an array of gray shades
is to divide the image into a number of pixels, depending on the required
spatial resolution.

This range
is represented in abstract way as a range from 0 (black) and 1 (white), with
any fractional values.

B.
Edge Detection   

            The edge is a boundary between two
regions with relatively distinct gray level properties.

  In edge detection, many operators are defined
such as sobel, log, canny, prewitt.

The Canny
operator was designed to be an optimal edge detector.

It takes as
input a gray scale image, and produces as output an image showing the positions
of tracked intensity discontinuities.

C.  Morphological operations

  Morphology is a broad set of image processing
operations that process images based on shapes.

Morphological
operations apply a structuring element to an input image, creating an output
image of the same size.

 The most basic morphological operations are dilation and erosion.

Dilation
performed by adding  pixels to the
boundaries of objects for all the pixels in the input pixel’s neighborhood. In
a binary image, if any of the pixels is set to the value 1, the output pixel is
set to 1.

 Dilation is used for the purpose of increasing
thickness of the number plate edges. So we can find the numbers easily.