Automatic Number Plate Recognition With Sms Reporting System

Post on 25-Dec-2015

15 views 3 download

Tags:

description

Automatic number plate recognition system uses MATLAB for the purpose of recognizing/detecting the numbers on the plate. It is an improvised and effective version of the already existing system which is tedious and time consuming.

Transcript of Automatic Number Plate Recognition With Sms Reporting System

AUTOMATIC NUMBER PLATE RECOGNITION WITH SMS REPORTING SYSTEM

Under the guidance of

V. Priyanka

Project members:

C. Ramya (10071A0472)N. Rithu (10071A0493)P. Sravya (10071A04A3)T. Abhinayee (10071A04A9)

 

Definition :

•Automatic Number Plate Recognition or ANPR is a technology that uses pattern recognition to 'read' vehicle number plates. The digital image is converted into data, which is processed through the ANPR system.

Applications :ANPR is used for •Detecting crime through the use of intelligence monitoring.

•Identifying stolen vehicles. 

•Detecting vehicle document crime electronic toll collection etc.

Block diagram :

We divided the problem in the following four consecutive steps:

1. Find the license plate on the photo (the location phase)

2. Find the “characters bitmaps” on the license plate (the segmentation phase)

3. Clean the character bitmaps, such that only the character remains (the cleaning phase)

4. Determine which character is displayed in the character bitmap (the classification phase)

The Location PhaseIn the location phase, we have as input a grey

scale photo and we want as output the part of the photo on which the license plate is displayed.

The algorithm for the location of the license plate is based on the following

idea: a license plate consists of a row of characters. A character is a

“relatively dark thing on a relatively light background”. So, we can say that

the license plate region is characterised by a row of transitions from dark to

light and vice versa (we call such a transition an edge).

The column profile of the license platearea, created from a grayscale image

The Segmentation PhaseWe can divide the license plate in characters

by cutting it at the columns that are significantly higher than their surroundings. In this way, we obtain a number of small bitmaps, which contain one character each.

The character bitmaps that are found as a result of the segmentation phase.

The Cleaning PhaseNow we have found the character bitmaps,

we have to make sure that the computer can recognize the characters that they represent.

To facilitate this, we first do some preprocessing; we clean the bitmaps.

By this, we mean that we remove all dark pixels from the character bitmap that do not belong to the characters.

The cleaned character bitmaps. All dark pixels that are not part of the character are removed

Input image :

Gray image :

Black and White Image :

Interfacing with GSM : The system is implemented and simulated in

Matlab.

The resulting data is then used to compare with the records on a database so as to come up with the specific information like the vehicle’s owner, place of registration, address, etc. and the fine details are sent to the person's number through SMS by interfacing it through GSM.

THANK YOU