Develop a Number Plate Scanner using MATLAB

Published on . Written by

Number Plate Scanner using Matlab
In the world of Automation and Artificial Intelligence the image processing is also taking a lead to support these technologies by providing a better picture of the things,

Read more..
(literally a better picture) one of the ways is to provide better solution to the intelligence. Location and extraction of the license plate region from a larger scene image will be the first step and then after having the license plate region to work with, the alphabetical characters present on the plate will be needed to extract from the background. Next step will be to deliver them to the MATLAB system for recognition. Locating the region of interest helps in dramatically reducing both the computational expense and algorithm complexity. ANPR can be used to store the images captured by the cameras as well as the text from the license plate, with some configurable to store a photograph of the driver. Systems commonly use infrared lighting to allow the camera to take the picture at any time of the day.

Project Requirements:


    Skyfi Labs Projects
    Vehicle’s number/license plate Scanner algorithm is based on the very basic technique of Templates matching widely used in image processing. This algorithm takes the input from the image of the number plate which generally should always be dominant in the image, and after filtering the image, it usually performs a region based operations in which it tries to capture the characteristic regions from the processed binary image that in end with the aid of template matching outputs the string of number plate characters.

    The general Number Plate Recognition system has the following key ingredients:

  1. Vehicle Image Capture.
  2. Extraction of the Number Plate.
  3. Segmentation of the Plate Character.
  4. Display the details of the number plate.

Project Implementation:

  1. The image of the vehicle whose details are required is captured from a digital camera.
  2. Once the image is captured the preprocessing will be done apply the minimum filter to the image in order to enhance the dark values in the image by increasing their area. This is mainly done to make the characters and the plate edges bold, and to remove the effect of the light diagonal strips that appear in the characters and edges of the number plate and later the image will be converted to grayscale.
  3. After the image is created the region is detected by using mathematical morphology and Sobel operator to calculate the value of threshold after which we get a clear binary image from the dilated image.
  4. Once the location is detected bounding box is used to measure the image.
  5. After undergoing these steps, the license plate may be skewed because of the angle of the camera while the image acquisition process. And it is very important to de-skew the plate to its original orientation, thus making the plate aligned with the X and Y axes. Then a Gaussian smoothing filter is applied to smooth the image and remove noise.
  6. Segmentation is the step in which we separate the image texts into different segments and all the digits or numbers are recognized by MATLAB and displayed in text format to the user.

Software requirements:

  1. Matlab/Simulink:software that is used to do the image processing using some inbuilt functions.
Kit required to develop Develop a Number Plate Scanner using MATLAB:
Technologies you will learn by working on Develop a Number Plate Scanner using MATLAB:


Any Questions?


Subscribe for more project ideas