Scribd Logo
Upload

Welcome to Scribd!

  • 35 views

    Number Plate Recognition

    Uploaded by

    Krishna Basutkar
    This document describes a MATLAB program for vehicle number plate recognition. The program resizes and converts the input image to grayscale and binary, performs noise reduction, detects characters using bounding boxes, and compares characters to a training dataset to recognize plates with over 40% match. It was tested on 20 images with 90% accuracy for detecting license plate text. Key steps include preprocessing the image, character detection using bounding boxes, recognition by comparing to a dataset, and storing the results.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Number Plate Recognition

    Uploaded by

    Krishna Basutkar
    35 views10 pages
    This document describes a MATLAB program for vehicle number plate recognition. The program resizes and converts the input image to grayscale and binary, performs noise reduction, detects characters using bounding boxes, and compares characters to a training dataset to recognize plates with over 40% match. It was tested on 20 images with 90% accuracy for detecting license plate text. Key steps include preprocessing the image, character detection using bounding boxes, recognition by comparing to a dataset, and storing the results.

    Original Title

    NUMBER PLATE RECOGNITION

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document describes a MATLAB program for vehicle number plate recognition. The program resizes and converts the input image to grayscale and binary, performs noise reduction, detects characters using bounding boxes, and compares characters to a training dataset to recognize plates with over 40% match. It was tested on 20 images with 90% accuracy for detecting license plate text. Key steps include preprocessing the image, character detection using bounding boxes, recognition by comparing to a dataset, and storing the results.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    35 views10 pages

    Number Plate Recognition

    Uploaded by

    Krishna Basutkar
    This document describes a MATLAB program for vehicle number plate recognition. The program resizes and converts the input image to grayscale and binary, performs noise reduction, detects characters using bounding boxes, and compares characters to a training dataset to recognize plates with over 40% match. It was tested on 20 images with 90% accuracy for detecting license plate text. Key steps include preprocessing the image, character detection using bounding boxes, recognition by comparing to a dataset, and storing the results.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    You are on page 1of 10

    NUMBER PLATE

    RECOGNITION
    USING MATLAB
    Table of Contents

    Contents
    Introduction 1
    Executing the program 2-5

    Report on the present investigation 6-7

    Results & Discussions 8

    Summary & Conclusions 8

    Bibliography _8
    Pg. 01

    Introduction

    What it is?
    Vehicle number plate recognition is the process by which the characters on
    a number plate are recognized. This is done using MATLAB

    The need for it?


    There are many people who are violating traffic rules every day and it is a
    quite difficult task for officers to punish these violators. This project gives
    an option for a cheap recognition process. It can be set up in main centers
    of the city and violators can be punished accordingly.

    What it does?
    This system reads the characters on the number plate which is checked
    against the data model. If there is more than a 40% match the
    character will be stored in the final output matrix
    Pg.

    Executing the program

    This section will guide you on how to execute the program.

     When you hit run on the program, the first step is to select an image
    of a number plate

     After selectin the image, the image is resized to 300x500


     The image is converted to grayscale image
     The grayscale image is then converted into binary image using
    IM2BW
     The noise in the image (objects lesser than 50 px) will be removed,
    and a black and white image, with lesser noise is produced
    Pg.
    Pg.

     After reducing noise in the image, the program starts detecting


    the characters

     Each character will be compared and if there is more than 40%


    match with the training dataset, the character will be stored in the
    final_output matrix
    Pg.

     Finally, output is copied in number_plate.txt


    Pg.

    Report on the present investigation

    1. The input of the image is taken into the program and the image
    is resized to 300x500 pixels.

    2. The image taken as input is now converted from RGB to


    grayscale. The image is then converted to binary using IM2BW
    library and noise reduction process is started.
    Pg.

    3. Here the green ‘bounding box’ that you see in the output
    screenshot is created to read the characters one at a time.

    4. A final_output matrix is created and all the characters


    which have been detected gets stored in it

    5. All the characters stored in the final_output matrix is compared


    with the dataset and if there is more than 40% match it detects
    the image as correct
    Pg.

    RESULTS AND DISCUSSIONS

     We can observe that the program executes the desired task


    successfully and recognizes the given number plate

    SUMMARY & CONCLUSIONS

     the text found on the vehicle plates is detected from the input image
    and this requires the localization of number plate area in order to
    identify the characters present on it.

     The algorithm has been tested on 20 samples and is found to extract


    both alphabets and numbers from vehicle license plates images
    with an accuracy of 90% for four-wheeler license plates.

    BIBLIOGRAPHHY

    1. Digital Signal and Image Processing Using MATLAB


    - Gerard Blanchet & Maurice Charbit

    2. www.semanticsscholar.org

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy