Scribd
Upload
491 views

Final Propject

The document presents a project on license plate recognition using edge detection algorithms. A team of 4 students submitted the project under the guidance of their professor. The project involves detecting license plates from images using pre-processing techniques like grayscale conversion and edge detection. Character segmentation and recognition is then performed to read the plate numbers. The system could be applied to applications like catching speeders, recovering stolen vehicles, and monitoring traffic. It was implemented in Python and tested on real images to identify vehicles by their license plates.

Uploaded by

Nandita Iyer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
491 views

Final Propject

The document presents a project on license plate recognition using edge detection algorithms. A team of 4 students submitted the project under the guidance of their professor. The project involves detecting license plates from images using pre-processing techniques like grayscale conversion and edge detection. Character segmentation and recognition is then performed to read the plate numbers. The system could be applied to applications like catching speeders, recovering stolen vehicles, and monitoring traffic. It was implemented in Python and tested on real images to identify vehicles by their license plates.

Uploaded by

Nandita Iyer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 26

Rajeev Institute of Technology, Hassan

Project Second Phase Presentation On

“Licence Plate Recognition By Unique Edge Detection


Algorithm’’

Submitted by, Under the Guidance,

Lakshmi Parvathi K P (4RA15CS043) Ms. Pruthvi Pournami Y R

Nandita B R (4RA15CS057) Assistant professor,

Deepika B H (4RA16CS011) Dept. of CSE,

Namratha B M (4RA16CS053) RIT, Hassan


Contents
• Introduction
• Literature Survey
• Problem Statement
• Objectives
• Methodology
• Implementation
• Applications
• Requirement Specification
• Conclusion
• References
Introduction
 Vehicle License Plate Recognition involves identifying vehicles by

their license plates.


 Users OCR on images to read vehicle registration plates.

 Some of its main tasks are:

- Input image
- License plate localization
- Character segmentation
- Identification
- Display
Literature Survey

TITLE AUTHOR IMPORTANT POINTS


1.Vehicle number plate Sang Kyoon Kim •Proposed a method using a
recognition sytem distributed genetic
algorithm to overcome the
difficulties dealing with
degraded number plate.

2. Presented a real-time Clemens Arth •In this system,where


licence plate recognition image fragments are taken
from real-time video and
processed
3.Automatic number Mohammad Tahir • In which uses optical
plate recognition character
recognition(OCR)
Algorithm to extract the
character for license
plate recognition with
each Individual
character recognition.

4.Recognition of vehicles Ankush Roy • He proposed a method to


number plate overcome the difficult to
correctly identify the non-
standard number plate
characters by using a pixel
based segmentation of the
alphanumeric characters in
the license plate
Problem Statement
• Different methods , techniques and algorithms have been
developed for license plate detection and recognitions.
• First it is necessary to locate and extract the license plate
region from a larger scene image.
• Second, having a license plate region to work with, the
alphanumeric characters in the plate need to be extracted from
the background.
• Third, deliver them to an optical character recognition system
for recognition.
• Vehicle is stationary when the image was taken.
• Only one vehicle image is captured at a time.

• Image of the vehicle taken from the fixed distance.


• Image of the vehicle taken from fixed angle.
Objectives

• In our society, traffic needs to be controlled and the


registration of vehicles can suit more than one purpose.
• The main objective is to use different morphological operation
in such a way that the number plate of vehicle can be
identified accurately.
• This is based on various operations such as image
enhancement, morphological transformation, edge detection
and extraction of number plate from vehicle image.
• It is useful in detecting the licence plate and identify the
vehicle details.
• It develop a prototype for the Optical Character Recognition
system and to implement the Template Matching algorithm in
developing the system prototype.
• The number plate allows categorization of vehicles , the
identification of the driver, or the origin of the driver/car.
Methodology
Character
Input Image
Segmentation

Character
Pre- Processing
Recognition

Helmet detection
Character
using cascade
Detection & display
classifier

Remove Noise from image Compare number


using edge detection algm plate with cloud Data

Plate extraction Send alert message


Pre-processing

Fig: Flow chart of Pre-Processing


• Color image to grayscale

Input image of the vehicle Grayscale image


• Grayscale to sobel edge detector

Grayscale image Sobel edge detector image


• Sobel edge detector to Dilated

Sobel edge detector image


Dilated image
Helmet Detection using cascade
classifier algorithm
 Cascade classifier

 2 major stages
- training
- detection

 LBP(Linear Binary Pattern) cascade algorithm


Remove noise from the image using
Edge Detection algorithm
• Technique for finding
boundary
• Very important in LPR(Linear Binary Pattern)
a
cascade algorithm
• By this edge detection very easy to find number
plate on the vehicles

a. color image b. edge image


• Character Segmentation
• Character Recognition

Character Segmentation Character Recognition


Implementation
• Helmet Recognition using cascade
algorithm
• Penalty message when rules violated
Penalty Text
massage to phone

Comparing

All vehicles
details
T1

Datasets
CLOUD
Internet
COMPUTING
Theft Vehicles
Details
Output T2
Storage Area

Comparing

Finding theft
Vehicles
Applications
• Recovering stolen vehicles
• Catching speeders by comparing the average time taken to get
from stationary camera A to stationary camera B.
• Building a comprehensive database of traffic movement.

• Access control
• Tolling
• Border Security
• Raiding Vehicle with out helmet
• Hit and Run
• Airport Parking

• Parking
• Match license plate numbers to a watch-list in less than
500msec.
• Alert notification.

• Tolling
System Requirement Specification

Software Requirement
• Language : python
• Software : spyder
• Version : 3.6
• Operating System : window 7 and above
• Bit : 64 bit
Hardware Requirements:

• Processor : Intel/AMD based 1.1GHz and above

• RAM : 4 GB and above

• Hard Disk : 1 TB

• Display : SVGA/LCD Based displays

• Devices : Standard Keyboard, Mouse


CONCLUSION
• The automatic vehicle identification system plays
an important role in detecting security threat.
• The system use series of image processing
techniques for identifying the vehicle from the
database stored in the PC.
• Performance is tested on real image.
• The system robustness and speed can be
increase if high resolution camera is used.
References
• Sang Kyoon Kim [1] (1996, September). A recognition of vehicle license
plate using a genetic algorithm based segmentation. In Image Processing,
1996. Proceedings. International Conference on (Vol. 2, pp. 661-664).
IEEE.  

• Sercon Ozbay [2] “A Novel approach to extract text from license plate of
vehicle”, Signal & Image Processing: An International Journal (SIPIJ)
Vol.3, No.4, August 2012.  

• Muhammad Tahir [3]”License Plate Recognition Using Image Processing


Techniques & SVM Classifier,” Israel Institute of Technology, Springer
2004. 

• Ankush Roy [4] proposed a method to overcome the difficult to correctly


identify the non-standard number plate characters. 
THANK YOU

You might also like