AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION (Paper id 17)

By:-
Kuntal Bhowmick, Subhojit Roy,
Deepak Kumar Jha1

Contents
 Introduction
 The Architecture
 Workflow
 Steps for License Plate Detection
 Image Plate Pre-Processing
 Edge Detection-By SOBEL Operator
 Experimental Results
 Future Works
 Reference
Automatic License Plate Recognition System For Indian Vehicle Identification
2

Introduction
What is ANPR?
Automatic Number Plate Recognition (ANPR) is a practical application
of image processing which uses number (license) plate is used to
identify the vehicle.
Applications
Identification of stolen cars.
Smuggling of Cars.
Invalid license plates.
Usage of cars in terrorist attacks/illegal activities.
Applications in traffic systems (highway electronic toll collection, red light
violation enforcement, border and customs checkpoints, etc.).
3

Introduction continued…
 A vehicle registration plate is a metal or plastic plate attached
to a motor vehicle or a trailer for Official Identification
purposes.
 The registration number is a numeric or an alphanumeric code
that uniquely identifies the vehicle within the issuing region’s
database.
 ANPR Cameras are specialized types of CCTV camera that
has software built into it to help ID and capture license plates
on still and moving vehicles.
4

The Architecture
Input image
The approach do handles the entire ANPR module addressing each of the
steps but the novelty lies in the segmentation scheme adopted.
Sofware part
Pre-Processor Analyze
r
Recognize
r
Segmentation
Unit
Output
Percentage
Accuracy
Software part
5

Workflow
Images of Rear License plate is taken from real
environment .
Pre-Process Digital Images of License Plates by Grey-
scale conversion, Noise Reduction and Contrast
enhancement using histogram equalization.
Application of the proposed method for
localization/segmentation of the license plate.
6

Steps for License Plate Detection
Step 1:-Collection of different
Vehicle’s Image.
Step 2:- RGB to Grey Scale
Image Conversion.
Step 3:- Edge detection of the
processed image.
Step 4:- Area detection of
Number Plate.
Step 5: Segmentation of the
plate.
7

Image Plate Pre-Processing
8

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.
9

Applying the Sobel operator- Examples
All edges in the image have been detected and can be
nicely separated from the background using a threshold of
220.
10

11 Edge Detection-By SOBEL Operator
Grey Scale image after image
enhancing.
After applying Sobel edge detection
method.

12 Removing Lower Connected Componets
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));

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.

14 Lower Components Removal
Image after removing components with
connectivity less than 1200 pixel.

15 Lower Components Removal… Continued
Using Matlab toolbox function
bwareaopen() that specifies the desired
connectivity.
All components connectivity lower than
1200 pixel are removed to get the actual
location of the number plate.

16 Final Positioning and Cropping
We output the four vertexes coordinates of
the last selected region after morphological
filtering and extract the number plate.
The final positioning of the number plate after
cropping.

17 Experimental Results
We have run our proposed method on desktop computer with Core2 due processor
2.26 MHz with 2 GB of RAM under MATLAB 7.14.0.739 R2012a 32-bit(win32)
environment. Several vehicle images are captured using 3.2 mega pixel camera as
well as 13 mega pixel cameras. In the experiments, we test our proposed method
on the different type car image to identify the location accurately.

Future Works
 Recognition of Segmented Character.
 Working with rotated Number Plates.
 Adding some new features to the algorithm.
18

References
1. “Matlab Documentation Website,”. [Online]. Available:
http://www.mathworks.in/help/vision/.
2. Thota Sridevi, Chilukuri Sindhu, Pendyala Naga Praveen
Kumar,Perupogu.Sagar, “Morphology based Number Plate Local
ization for Vehicular Surveillance System”, IJMER, vol.2, issue.2,
2012, pp 334 -337.
3. Feng Yang, Zheng Ma “Vehicle License Plate location Based
on Histogramming and Mathematical Morphology “, 2005.
4. Park, S. H., Kim, K. I., Jung, K., and Kim, H. J., (2009), “Locating ca
r license plates using neural network,” IEE Electronics Letters, .35,
17, pp. 1475-1477.
5. CheokMan, Kengchung “A High Accurate Macau License Plate
Recognition System”, 2008
6. R. C. Gonzalez, and R. E. Woods and S.I.Eddins Digital Image
Processing using MATLAB.Pearson Education, 2008
19

20

AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION (Paper id 17)

More Related Content

What's hot

Viewers also liked

Similar to AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION (Paper id 17)

More from Kuntal Bhowmick

Recently uploaded

AUTOMATIC LICENSE PLATE RECOGNITION SYSTEM FOR INDIAN VEHICLE IDENTIFICATION (Paper id 17)