Vehicle License Plate (VLP) Recognition System
By German H. Flores and Gurpal Bhoot
Introduction
Goal and Motivation
Image Segmentation
Feature Extraction
Classification
Results/Conclusion
Future Work
Agenda
Introduction
Technological advancements in both software and hardware Better ways to capture, edit and analyze
images
Safety and security of pedestrians and people in motorized vehicles The large number of cars on the roads has
increased the probability of an accident occurring
With a VLP system, the owner of a car can be easily identified and held responsible for their actions
Video
Imag
e Se
gmen
tatio
n • Locate objects and boundaries in images
• Ex: Separate LP from car and background as well as characters from LP
Feat
ure
Extra
ctio
n
• Extract features that can be used for classification
• Ex: Area, Perimeter, Number of Corners, Contains Hole
Patte
rn
Clas
sifica
tion• Take the
features extracted from the image and use them to automatically classify image objects
• Ex: Classify either as letters (A-Z) and/or numbers (0-9)
Object Recognition Process
Process Flow
Ideal lighting Conditions Non-white car License Plate is in the same region License Plates are similar sizes Only California license plates after 1987 License Plates must be white with dark
characters Upper case letter O and 0 are the same
Assumptions
Image Segmentation
Shrink the image Cut out the background Leave only part of the image where
license plate is most likely to appear
Resize Image
Binary Image
Binary Image Convert the original image into a binary
image Threshold was chosen through testing
Windowing Method
Resized Binary Image
Windowing Method used to find the license plate from the binary image Send a window (m X n) through binary
image, pixel by pixel
Image Segmentation
Windowing Method Find the license plate by number of
white pixels Below is the resulting image from
applying the Window Method
Final Binary Image
Image Segmentation
Connected Component Algorithm Used for separating license plate from
the image Finds the different objects
Finds the license plate by size and shape
Extracted License Plate Then used for separating the letters and
numbers Finds each character and extracts them
one by one
Image Segmentation
Image Segmentation
What features are important for a successful pattern classification? Ex: Color, Area, Perimeter, mean,
variance
Character Recognition
Area
Number of Corners in
compressed simple image
Perimeter
Has Hole
Number of Corners in compresse
d full image
Perimeter of Contour
Distance Image
Compressed and
Normalized Character
Image
Feature Extraction
Area Perimeter
Perimeter of ContourSimple Compression
And Normalized Corners Full Compression AndNormalized Corners
Compressed and Normalized
Feature Extraction
(http://www.leewardpro.com/articles/licplatefonts/font-penitentiary.html)
Characters that have holes
Characters that do not have holes
A B D O P Q R 0 6 8 9
C E F G H I J K L M N S T U V W X Y Z 1 2 3 4 5
7
Features:
• Area• Perimeter• Perimeter of Contour• Number of Corners in simple compressed Image• Number of Corners in full compressed Image
• Distance Image• Normalized Character Image
Feature Extraction
Harris Corner Detection
A new Corner Matching Algorithm Based on Gradient. (Yu, Haliyan.,., Ren Cuihua., and Qiao Xiaoling)
A corner can be defined as the intersection of two edges
Feature Extraction
Feature Extraction
1. Compute X and Y derivatives of the grayscale image Gx Gy
2. Compute products of derivatives
3. Define at each pixel (x,y), the matrix
4. Compute the response at each pixel
5. Threshold on Value R
0s or negative numbers are the corners
Feature Extraction
CHARACTER AREA PERIMETER HAS HOLES
PERIMETER OF CONTOUR
Number of Corners in simple compression
Number of Corners in full compression
A 103 74 1 85 63 202B 120 106 1 102 51 262C 95 75 0 70 63 255D 117 99 1 81 43 270E 90 86 0 50 36 438
Character Features Extracted From Image
Character Features from Database
CorrelationCorr2()
Feature Extraction
LICENSE PLATE
LICENSE PLATE CHARACTERS RECOGNIZED
3DDF536 -- D 5 3EZEZBEH E 2 E Z B E3HOS909 H O 9 3 S 9 04HCF116 4 H C F 1 1 62LOX542 2 O X 5 4 24FJF892 4 F F 8 9 2 J3TFB805 T F B 3 8 0 53WVD539 3 3 93GXP106 3 G X P 1 O 64EYB802 4 E Y B 8 0 24DNX245 --- 4 D N X 2 4 54CGS613 --- C G S 6 1 3 ---3XHK859 3 X H X 8 5 93JXK363 X K 6 3
Results
Results
Results
Raw Image
Image Segmentatio
n•License Plate
Letter Segmentatio
n•Characters
Feature Extraction
•Area•Perimeter•Number of Corners
Character Feature
Database
•All the characters (A-Z) and (0-9)
Classification •Correlation
A B D O P Q R 0 6 8
9
C E F G H I J K L M N S T U V W X Y Z 1 2 3 4
5 7
Conclusion/Overview
Bibliography