You are on page 1of 14

A

Paper Presentation on
Characters Recognition In An Image Using
Matlab

By
Ramya Muppala
&
Kalyan Chakravarthy

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING


Devineni Venkata Ramana & Dr. Hima Sekhar

MIC College of Technology


Kanchikacherla-521180, Krishna Dist., A.P, India.

ACADEMIC YEAR: 2016-2017


CONTENTS

Abstract
Flow Chart
Pre-Processing The Image
Edge detection
Removal lower Connected Components
Filling the holes
Final postioning and cropping

09/01/2016 DVR & Dr HS MIC College of Technology 2


Abstract
The vehicle number plate recognition automatically controls
access to a secured area for authorized members. We tested
our method for number plate recognition which includes five
main testimonials first is pre-processing of the input image,
then cropping the preprocessed image that follows by the
image edge extraction operated on the cropped image after
this the character segmentation process algorithm and then
finally to the character recognition which gives the improved
results that shows our method has the average precision that
can be put into practice.

8/2/2017 DVR & Dr HS MIC College of Technology 3


Flow Chart

8/2/2017 DVR & Dr HS MIC College of Technology 4


Pre-Processing
Pre-Processing is very important for the good performance of
algorithm
Pre-Processing consists of :

Resizing of image.
RGB to Gray.
Contrast enhancement using histogram equalization.

8/2/2017 DVR & Dr HS MIC College of Technology 5


Edge Detection By SOBEL operator
The Sobel operator is one of most commonly used edge
detectors.
The Sobel edge detector uses a pair of 3x3 convolution
matrices.
The first is dedicated for evaluation of vertical edges, and
the second for evaluation of horizontal edges.

8/2/2017 DVR & Dr HS MIC College of Technology 6


Applying the Sobel Operator-Example

All edges in the image have been detected and can be nicely separated
from the background using a threshold of 220.

8/2/2017 DVR & Dr HS MIC College of Technology 7


Edge detection by Sobel Operator

Grey Scale image after


image enhancing

After applying Sobel


edge detection method.

8/2/2017 DVR & Dr HS MIC College of Technology 8


Removing lower connected components
After edge detection removes all
connected components that have lower
than p(eight pixel in our method)
pixels. Thus it will produce another binary
image.

Steps:-
1. Determine the connected components.
L= bwlabeln(BW,conn);

2. Compute the area of each component.


S= regionprops(L,Area);

3. Remove small objects


Bw2 = ismember(L,find([S.Area] >= p));

8/2/2017 DVR & Dr HS MIC College of Technology 9


Filling The Holes

The set of background pixels are known as hole that cannot be reached
by filling the background from the edge of the image.

The holes in the binarized image are filled.

8/2/2017 DVR & Dr HS MIC College of Technology 10


Lower Components Removal

Image after removing


components with connectivity
less than of the intensity 1200
per pixel.

8/2/2017 DVR & Dr HS MIC College of Technology 11


Lower Components Removal
Continued

Using Matlab toolbox function


bwareaopen() that specifies the
desired connectivity.

All components connectivity lower


than the intensity of 1200 per pixel
are removed to get the actual
location of the number plate.

8/2/2017 DVR & Dr HS MIC College of Technology 12


Final Positioning and Cropping

We output the four vertices coordinates of the


last selected region after morphological
filtering and extract the number plate.

The final positioning of the number plate after


cropping.

8/2/2017 DVR & Dr HS MIC College of Technology 13


THANK YOU

8/2/2017 DVR & Dr HS MIC College of Technology 14

You might also like