This document describes a project to develop a vehicle license plate recognition system using MATLAB for image and video processing. The system takes images of license plates as input, performs pre-processing like resizing, filtering and thinning, segments the license plate using horizontal and vertical analysis, and recognizes characters using template matching. It is intended to identify stolen vehicles, catch traffic violations, and enable automated toll collection and vehicle authentication. The system was implemented and tested on images and video frames captured in real environments. Future work could improve nighttime performance and avoid multiple matches or overlapped plates.

1. CAR NUMBER PLATE DETECTION USING
MATLAB IMAGE PROCESSING AND VIDEO
PROCESSING
PREPARED BY :
KESAVA KORUKONDA (546/14)
CHAUHAN MANIK RAO (553/14)
(GROUP NO.:- 7)
Guided by:
Shaima Qureshi
Co-guide
Nadeem

2. Introduction
 Vehicle licence plate recognition involves identifying vehicle
by their licence plates.
 It has become a task of prime importance with the increasing
In number of accident and traffic-rule violation.
 A vehicle registration plate is metal are plastic plate
attached to a motor vehicle for official identification purpose
 The registration number is a is numeric or an alpha numeric
code the unique identify the vehicle with in the issuing
regions database

3. Platform details
 The platform we used here is MATLAB.
 Matlab is a modern programming language environment.
 The research work has been developed using the image
processing functionalities of the MATLAB platform.
 The matlab version used here is ‘R2017b’ for developing
different modules.
 MATLAB is used to solve technical computing problems
faster than traditional programming languages such as
C,C++ etc.

4. Project objective
• identification of stolen cars
• Smuggling of cars
• Invalid license plates
• Toll collection
• Application in authentication of car for the security purpose

5. Some important tasks
• Image capture
• Image pre-processing
• Character segmentation
• Character recognition

6. Image pre-processing
Plate localization
Character segmentation
Character recognition
output
Input
image
Block diagram

7. Work flow
 Image was taken from real environment
 Process digital images of license plates using existing techniques.
 Techniques will perform alpha numeric conversions on the captured license
plate images into text entries.
 System would check the extracted entries against a database in real time.
 The entire system is implemented in MATLAB is used for detection and
recognition.

8. Pre-Processing
 Pre-processing is very important for the good performance of character
segmentation.
 Pre-processing consist of several stages.
• Resizing of an image.
• Rgb2gray.
• Median filtering.
• Dilation.
• Erosion.
• Morphological processing.
• Edge brightening.
• Thinning of image.
• Selection of region.

9. Character segmentation
Pre-processing Horizontal and vertical
segmentation
• In this stage we take the pre processed image as input
and we segment it by various methods.
• In this project we considered the bounding boxes
example by using connected components methods.

10. Horizontal and vertical segmentation
• Detect the horizontal lines in the image with a pixel
value of zero
• Converting the image into binary
• Use the simple “for loops” to detect the portions of the
image
• That had connected objects with a pixel value of ‘0’
and hence accordingly, the image was read.

11. Character recognition
Template matching
Template matching is the one
of the most common and easy
classification method for
recognizing the character.

12. Template matching
 The used template are given in the figure below:

13. Results
 In the output we will be getting a result of characters of
the number plate in a notepad.
 We can also create a database for the number plates
and can identify the plates/owner of the plates.

14.  In case of video processing, we are dividing the
video into several number of frames.
 In which we are choosing the best frames randomly
and we are processing the it as an image.

15. Digital
camera
Capture
the
image
Image
processing
Find
plate
region
Plate
extraction
segmentation
recognition
database
register
administrator
(Use case
diagram)

16. Conclusion & Future scope
1. The car number plate recognition using Matlab image
processing and video processing is presented . The
system use image processing techniques for the
identifying the vehicle from the database stored in the
computer . The system is implemented in Mat lab .
2. Can be improved to work for image taken at night time
3. Multiple matches & overlapping should be avoided.
4. Linking the video & image can be implemented by the
training method.

17. References
 OGE MARQUES “practical image and video processing
MATLAB”, Florida Atlantic University.
 MATHWORKS (matlab site)
 AMITH SREEDHAR (you tube channel)
 CODE4U ENTERTINEMENT (YouTube channel)
 www.Wikipedia.com
 www.google.com
 Geeks4geeks (website)
 Stack overflow (website)