You are on page 1of 23

A

presentation on
Automatic Characters Recognition From A
Vehicle Number Plate
By

1.M. Ramya(13H71A0430) 2.R. Kalyan


Chakravarthy(13H71A0416)

3.M. Ravi(13H71A0431) 4.P. BhavyaSree(13H71A0404)

Under the Esteemed Guidance of


Mr. V. V. S. Murthy, M.Tech, (Ph.D)
Associate Professor

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
Motivation
Objective
Introduction
Abstract
Block diagram
Flow chart
Pre-Processing The Image
Edge detection
Removing lower connected components
Final positioning and extracting
Advantages
Limitations
Conclusion
Future Scope
References
3/29/2017 DVR&DrHSMICCollegeofTechnology 2
MOTIVATION

Due to the mass integration of information technology in


all aspects of modern life there is a demand for information
systems for data processing in respect of vehicles.
We have learned some fundamental image
processing techniques in our previous semester.By using that
fundamental knowledge we over come the problems in detecting
the vehicle number plate.

08/01/17 DVR&DrHSMICCollegeofTechnology 3
OBJECTIVE
The projects objective is to develop a character
recognition system for a license plate of a car using the
techniques and tools that best suite and allow doing it in easy and
comfortable way.
Find a method with acceptable results for the correct location of
the area of the license plate.
Build a system that given an image region where plate can be
found to determine the character of the plate.
Recognize each character we have extracted above.

08/01/17 DVR&DrHSMICCollegeofTechnology 4
INTRODUCTION

An image is used to convey useful information in a


visible format. An image is nothing but an arrangement of tiny
elements in a 2-D plane. These tiny elements are called pixels a
large number of pixels combine together to form an image.
Using image enhancement and analysis techniques
we can extract the information in an image.

08/01/17 DVR&DrHSMICCollegeofTechnology 5
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.

08/01/17 DVR&DrHSMICCollegeofTechnology 6
BLOCK DIAGRAM

08/01/17 DVR&DrHSMICCollegeofTechnology 7
FLOW CHART

08/01/17 DVR&DrHSMICCollegeofTechnology 8
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.

08/01/17 DVR&DrHSMICCollegeofTechnology 9
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 horizontal edges, and
the second for evaluation of vertical edges.

08/01/17 DVR&DrHSMICCollegeofTechnology 10
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.

08/01/17 DVR&DrHSMICCollegeofTechnology 11
EDGE DETECTION BY SOBEL OPERATOR

Gray Scale image after


image enhancing

After applying Sobel edge


detection method.

08/01/17 DVR&DrHSMICCollegeofTechnology 12
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));

08/01/17 DVR&DrHSMICCollegeofTechnology 13
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.

08/01/17 DVR&DrHSMICCollegeofTechnology 14
Lower Components Removal

Image after removing components


with connectivity less than of the
intensity 100 per pixel.

08/01/17 DVR&DrHSMICCollegeofTechnology 15
Lower Components Removal
Continued
Using Mat lab toolbox function
bwareaopen() that specifies the desired
connectivity.

All components connectivity lower


than the intensity of 100 per pixel are
removed to get the actual location of
the number plate.

08/01/17 DVR&DrHSMICCollegeofTechnology 16
Final Positioning and Extracting
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.

08/01/17 DVR&DrHSMICCollegeofTechnology 17
ADVANTAGES

To detect the vehicle number plate in easy way.


It reduces the time duration in this process.
It is very reliable and inexpensive.

08/01/17 DVR&DrHSMICCollegeofTechnology 18
LIMITATIONS

The number plate should be clear and dominant.


The length of the characters in the number plate should neither
more nor less than 10.
Height of the each character should be same.
The characters should be in single row.

08/01/17 DVR&DrHSMICCollegeofTechnology 19
CONCLUSION
The project was designed keeping in mind the
automation of the number plate detection system for security
reason that could replace the current system of manual entry. This
project was a success in recording the number plate of a vehicle
although it has got its own limitation of image processing and
other hardware requirements. From this project we learn some
image processing tools in MATLAB.The system use series of
image processing techniques for identifying the vehicle number
plate from the database stored in the PC. The system is
implemented in MATLAB and it performance is tested on real
images.

08/01/17 DVR&DrHSMICCollegeofTechnology 20
FUTURE SCOPE

In future by modifying some functions in the code to


make the simulation results shows that the system robustly detect
and recognize the vehicle license plate against different
lightening conditions and can be implemented on the entrance of
a highly restricted areas.

08/01/17 DVR&DrHSMICCollegeofTechnology 21
REFERENCES

Loumos, V.; Kayafas, E.,License plate recognition from still


images and video sequences: A survey IEEE Transactions on
Intelligent.
R.A. Lotufo, A.D. Morgan, and AS. Johnson, Automatic
Number-Plate Recognition, Proceedings of the IEEE
Colloquium on Image.
Otsu, N., A Thresholding Selection Method from Gray Level
Histograms, IEEE Transactions on Systems, Man and
Cybernetics, Vol. 9, pp.62-66, 1979.

08/01/17 DVR&DrHSMICCollegeofTechnology 22
THANKYOU

08/01/17 DVR&DrHSMICCollegeofTechnology 23

You might also like