{

Automatic Number
Plate Recognition
Aayush David 2K10/EC/003
Abhishek Choudhary 2K10/EC/009
Aman Bansal 2K10/EC/019
Gaurav Keswani 2K10/EC/059
Minor Project
Contents
Introduction
Need for ANPR
Algorithm
Working
Challenges
Future Work
Bibliography


Introduction
Automatic License Plate Recognition (ALPR) is an image-
processing technology used to identify vehicles license
plates. It is an embedded system which has numerous
applications and challenges. Few of the applications being
unattended parking lots, security control of restricted areas,
traffic law enforcement, and automatic toll collection.
Inspiration?

The entire inspiration behind implementing such a system to improve the
efficiency and speed in these processes. Reduce manpower.
ALPR consists of two main steps :

Locating License Plates
In the first stage, license-plate candidates are determined based
on the features of license plates. License plates come with a
wide range of features in shape, symmetry, size, colour, texture
etc.

Recognizing Characters
The second stage involves optical character recognition of the
connected components as taken out from the images and
writing them into text using OCR.





Need for ANPR
Travel Time & Source - Destination Studies
Commercial Vehicle Safety
Revenue & Tax Collection
Tolling Applications
General Law Enforcement
Border Screening
DHS Screening and Interdiction
Transportation
Law Enforcement
Customs and
Immigration
Homeland Security
A Few Examples
Traffic Control & Transport Planning
By using ANPR on this footage it is possible to monitor the travel of individual
vehicles, automatically providing information about the speed and flow of various
routes. These details can highlight problem areas as and when they occur and
helps the centre to make informed incident management decisions.

Drive-through Customer Recognition

Hotel & Car Parking Automation
One of the main applications of ANPR is parking automation and parking
security: ticketless parking fee management, parking access automation, vehicle
location guidance

Access Control
Access control in general is a mechanisms for limiting access to areas and
resources based on users' identities and their membership in various predefined
groups



Algorithm
Capture Pre-Process Localize
Connected
Component
Analysis
Segmentation OCR
CAPTURE

The image of the vehicle is captured using a high resolution photographic camera.
A better choice is an Infrared (IR)camera. The camera may be rolled and pitched
with respect to the license plates.

For lack of resources, we used the 5MP camera of our smartphone for clicking test
pictures.



PRE-PROCESS

Pre-processing is the set algorithms applied on the image to enhance the quality.
For the present system pre-processing involves two processes: Resize The image
size from the camera might be large and can drive the system slow. It is to be
resized to a feasible aspect ratio. Convert Colour Space Images captured using
IR or photographic cameras will be either in raw format or encoded into some
multimedia standards. Normally, these images will be in RGB mode, with three
channels (viz. red, green and blue) Number of channels defines the amount color
information available on the image. The image has to be converted to grayscale.





LOCALIZE

There are two motivations for this operation
1. Highlighting characters and
2. Suppressing background.
Localization is done by an image processing technique called Thresholding. The
pixels of the image are truncated to two values depending upon the value of
threshold. Threshold requires pre-image analysis for identifying the suitable
threshold value. Adaptive thresholding technique determines a local optimal
threshold value for each image pixel so as to avoid the problem originating from
non uniform illumination.


CONNECTED COMPONENT ANALYSIS

In order to eliminate undesired image areas, a connected component algorithm
is first applied to the binarized plate candidate. Connected component analysis
is performed to identify the characters in the image. Basic idea is to traverse
through the image and find the connected pixels. Each of the connected
components (blobs) are labelled and extracted. Fig. 4 shows the filtered blobs

SEGMENTATION

Segmentation is the process of cropping out the labelled blobs. These blobs are expected to be
the required portion of the license number. A special algorithm called Image Scissoring is
introduced here. In this algorithm, the license plate is vertically scanned and scissored at the
row on which there is no white pixel and the scissored area is copied into a new matrix, There
are unwanted blobs even after segmentation. These are classified using special algorithms.


OCR (Optical Character Recognition)

In order to eliminate undesired image areas, a connected component algorithm is
first applied to the binarized plate candidate. Connected component analysis is
performed to identify the characters in the image. Basic idea is to traverse through
the image and find the connected pixels. Each of the connected components (blobs)
are labelled and extracted. Fig. 4 shows the filtered blobs
Process.
Test Image
Pre-processConversion, Noise
Removal
Pre-processDilation, Erosion,
Closing
Pre-processAdjustment, Enhancement
LocalizationFilling,Morphological
Operations..
Connected Component Analysis,
Segmentation & OCR.
Detection of Connected Components using regionprops
function in MATLAB.
Calculation of Bounding boxes and its dimensions.
Finding out the required Boundingboxes using histograms
taking Y-axis coordinates and Y-axis width to the
criterions to met.
Finding out required BoundingBoxes using Takeboxes
and Guess functions as implemented in code.
Template Matching to read and display characters in a text
file.
Output
Challenges
There are a number of possible difficulties that the software must be able to
cope with. The issues can be broadly categorised into two:

Standardization
Image Quality

Standardization
Even though there is a proper standard for licence plates in India, people are neither
worried nor bothered about this, which stands as the greatest challenge faced.
They vary in dimensions, fonts(type and size), colours and position of the plate. We
may also find artworks which make it difficult for recognition.

Image Quality
The image quality depends on the camera resolution and lighting. Undesirable blobs
(like screws and holograms) may also creep in which increases complexity in the
character recognition phase.


Future Work
Depending on the interest of the team, we can look forward to
working and improving on our current project by working on
the following challenges :

Standardization
Plate Orientation
Plate Localization
Improving low quality image processing
Realtime Processing
Bibliography