The document outlines the development of a MATLAB-based system for automatic detection and recognition of car number plates through image processing techniques. It describes the workflow starting from image capture to character recognition and saving the recognized number, while also addressing potential challenges such as image quality and character similarity. Future enhancements include applications in intelligent transportation systems, security, and vehicle theft prevention.

1. AUTOMATIC CAR NUMBER PLATE DETECTION AND
RECOGNITION USING MATLAB
Group Members:
Ankita (0815002817, ECE-2)
Himanshi (02215002817, ECE-2)
Project Supervisor:
Dr. Shaifali M.Arora

2. We intended to develop a system in
MATLAB which can perform
detection as well as recognition of Car
Number plate.
This system is based on the image
processing system.
AIM
BASIS
o License Plate Recognition
o Car Registration System
o Intelligent Transport System
Various Name’s

3. Start
End
Convert into Grayscale
Recognition of segmented characters
Localize number plate
Save the recognized characters of number plate
Start it’s segmentation
Import image
ALGORITHM
Edge Enhancement in the image
Morphological Operation
Filling Holes in the Image

4. WORK FLOW PROCESS
 Capture of Image: The image is captured by electronic device and stored in JPEG format.
 RGB to GRAY scale: We will be converting that image into grey scale using MATLAB.
 Detect Number plate from image: We will be detecting the number plate from the morphological
image using the MATLAB function.
 Character segmentation from number plate: We will split each character of the number plate
which is being detected, to find the number from number plate.
 Character Recognition: We will be detecting each and single character using Optical Character
Recognition technique.
 Display & Save Vehicle Number: We will be displaying that number on the screen and save it.

5. Basic Module of the System
o Input image:
This is the first phase deals with acquiring an image.
o Extraction of number plate:
In this step the number plate is extracted by firstly
• converting RGB Image i.e., the captured image to GrayScale
Image.
• Here mathematical morphology is used to detect the region
and Sobel operator are used.
• After this we get a dilated image.
• Then fill the holes so that we get a clear image.

6. o Segmentation and Recognition of Plate
Character:
• Here bounding box technique is used for
segmentation.
• The bounding box is used to measure the
properties of the image region.
• The basic step in recognition of vehicle
number plate is to detect the plate size.
o Display and Save Vehicle Number:
After undergoing the above steps the number
plate is displayed in MATLAB window and Save
in the Excel File.

7. OUTPUT

11. Some of Possible Difficulties
 Broken Number Plate.
 Blurry Image
 Number plate not within the legal specification.
 Low resolution of the characters.
 Poor maintenance of the vehicle plate.
 Similarity between certain characters, namely, O and D; 5
and S; 8 and B, E; O and 0, etc.

12. FUTURE ENHANCEMENT
 Intelligent Transportation System (ITS).
 Security systems
 Highway toll collection
 Traffic analysis
 State border control
 Vehicle theft prevention
 Automation and simplification of airport
 Security monitoring of roads and checkpoints.

13. THANK YOU