Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 26

VEHICLE LICENSE PLATE

RECOGNITION FOR SECURITY


APPLICATIONS

Presented By,
Under The Guidance of :
181FA05048- O. Sri Jagadeesh
Mr. S. Sivaji
(Asst. Professor) 181FA05098- K. Venkatesh

181FA05238- P. Tagore Ravi Teja


CONTENTS:

Objective
Introduction
Literature survey
Proposed Block diagram
LPR Algorithm
Results
Conclusion
OBJECTIVE:
To design an efficient automatic authorized vehicle identification system by
using the vehicle number plate.
To integrate the edge detection, segmentation and OCR techniques for
reliable recognition of number plate.
To simulate the proposed algorithm for real time applications.
INTRODUCTION
• License Plate Recognition is an image-processing technology which is used
to identify vehicles by their number plates using Optical Character
Recognition.
• This technology is used in various security and traffic applications such as
access-control system.
• Accuracy of character recognition will be significantly reduced if the
characters are not properly segmented. Improper segmentation of characters
will result in mis-recognized characters.
LITERATURE SURVEY

AUTHORS JOURNAL AND YEAR METHODOLOGY


A. S. Mohammed Shariff, R. Vehicle Number Plate Detection Using Python and Open CV library along with python
Bhatia, R. Kuma and S. Jha, [1] Open CV, IEEE 2021 language is used for image processing
using py tesseract
A. Menon and B. Omman, [2] Detection and Recognition of Multiple License Sobel filter, morphological operations,
Plate From Still Images,IEEE 2018 contour algorithms, Support Vector
Machine (SVM)
S. Jain, R. Rathi and R. K. Indian Vehicle Number-Plate Recognition using Pre-Processing, Number-Plate
Chaurasiya, [3] Single Shot Detection and OCR, 2021 IEEE Classification, Object Detection,
Characters Extraction
PROPOSED BLOCK DIAGRAM
PROPOSED WORK FLOW
Proposed LPR algorithm 
1: Begin
2: Input: Original Image
3: Output: Characters
4: Method: Canny edge detection
5: LP: License Plate
6: Convert RGB image to Grayscale
7: Filter Morphological Transformation
8: Transforms Grayscale image to binary image
9: Bilateral Filter for denoising image
10: Finding all contours in image
11: Search & recognize all possible character in image
12: Crop part of image with highest candidate LP
13: Crop the LP from original image
14: Apply steps from 6 to 11 again on crop image
15: Print the characters in LP
INPUT IMAGES
PRE-PROCESSING
Bilateral filter  :
APPLICATIONS OF BILATERAL FILTER
CANNY EDGE DETECTION
Canny Edge Detection is a popular edge detection algorithm. It was developed
by John F. Canny.
1. Smooth the image with a Gaussian filter with spread .
2. Compute gradient magnitude and direction at each pixel of the smoothed
image.
3. Zero out any pixel response less than or equal tothe two neighboring pixels
on either side of it, along the direction of the gradient (non-maxima
suppression).
4.Track high-magnitude contours using thresholding (hysteresis thresholding).
5.Keep only pixels along these contours, so weak little segments go away.
It is a multi-stage algorithm and we will go through each stages:
Noise Reduction:

Finding Intensity Gradient of the Image:


Non-maximum Suppression:

Double thresholding:
Hysteresis Thresholding:
CONTOURS
FIND CONTOURS:
Img is treated as binary and used as scratch space
Storage- location for the sequence
First contour- pointer to the head of contour tree
Header size- tells more about allocated objects
Mode-what to compute
Method- how to compute
Returns total number of contours found
DRAW CONTOURS

 To draw the contours, It can also be used to draw any


shape provided you have its boundary points.

 Its first argument is source image,

 second argument is the contours which should be passed


as a Python list,

 third argument is index of contours (useful when


drawing individual contour.

 To draw all contours, pass -1) and remaining arguments


are colour, thickness etc.
OPTICAL CHARACTER RECOGNITION
OCR PROCESS FLOW
STEPS IN OCR
RESULTS
OUTPUT ACCURACY TABLE

Over all accuracy


from table is 82%
PLATE LOCALIZATION
SUCCESSFULLY FAILED TO
TOTAL IMAGES SUCCESS RATE
SEGMENTED LOCATE
100 90 10 90%

CHARACTER SEGMENTATION
CUMULATIVE
TOTAL CHARACTER SUCCESS
FAILED SUCCESS
IMAGES SEGMENTED RATE
RATE

90 82 8 91.1% 82%
CONCLUSION

This study implements an effective approach for detecting automobile licence plates.
The input picture was evaluated using a bilateral filter and prepossessed using several
techniques. The cropped image of the licence plate for the car is automatically saved in
a folder called cropped licence plates photos, where the image text has been
transformed to a string. The result was displayed in the Python output terminal after the
text was read over the image using tesseract.
REFERENCES
[1].A. S. Mohammed Shariff, R. Bhatia, R. Kuma and S. Jha, "Vehicle Number Plate
Detection Using Python and Open CV," 2021 International Conference on Advance
Computing and Innovative Technologies in Engineering (ICACITE), 2021, pp. 525-529,
doi: 10.1109/ICACITE51222.2021.9404556. 
[2] A. Menon and B. Omman, "Detection and Recognition of Multiple License Plate
From Still Images," 2018 International Conference on Circuits and Systems in Digital
Enterprise Technology (ICCSDET), 2018, pp. 1-5, doi:
10.1109/ICCSDET.2018.8821138.
[3] S. Jain, R. Rathi and R. K. Chaurasiya, "Indian Vehicle Number-Plate Recognition
using Single Shot Detection and OCR," 2021 IEEE India Council International
Subsections Conference (INDISCON), 2021, pp. 1-5, doi:
10.1109/INDISCON53343.2021.9582216.

You might also like