Car Number Plate Recognition Model

Task Description 📄

📌 In this task :

👉Create a model that will detect a car in a live stream or video and recognize characters on number plate of the car .

👉Secondly , it will use the characters and fetch the owners information using RTO API’s .

👉Create a Web portal where all this information will be displayed (using html,css,and js)

Step 1:- Model For Number Plate Detection

To detect the Number Plate of the car , we first required to import cv2 and other libraries. Here we have used Haar Cascade Russian Plate Model to which is pre-trained model used to detect the number plate of the car.

Step 2: Image Processing

Read the image and convert it from BGR to RGB format

Now using haar cascade russian plate model, Detect the number plate, crop , enlarge and save the image by name final_img.jpg

Step 3: Image-Text Recognition Using Amazon Textract

Now we have to extract the text from the image. For that we have used Amazon textract. Amazon Textract is a machine learning service that automatically extracts text, handwriting and data from scanned documents that goes beyond simple optical character recognition (OCR) to identify, understand, and extract data from forms, tables and images.

To use the amazon or AWS services, we have installed and import boto3 module in the jupyter notebook. After that we have firstly uploaded the final_img.jpg image in the Amazon S3 bucket. From S3 bucket, Amazon Textract will take the image, process it and will return the text present in the image.

We have also used the re module which helps to substitute unwanted spaces and characters in the text.

Step 4:- API for Car Information

API is the acronym for Application Programming Interface, which is a software intermediary that allows two applications to talk to each other.

This time we need an API that will go to the website to retrieve car information when the car number is passed. We found a website that provides this service for free for up to 9 uses and then uses paid subscriptions.

Website URL:- http://www.carregistrationapi.in/

This will return all the information of the car.

Step 5:- Creation of Web Page

Finally , We have created the front end web page for the users using HTML, CSS and also integrated flask to route and process the output.

Now use flask run command to run the flask code.

Use the URL to open the localhost webpage of the code. After opening the webpage choose the image you want to upload and click on Submit button.

You will get the car information in the output screen.

Thank you for reading!!!!!

Github URL:- https://github.com/Tanmay-19/Car-Detection-and-Recognition-Model

#worldrecordholder #training #internship #makingindiafutureready #summer #summertraining #python #javascript #ml #dl #rightmentor #deepknowledge #linuxworld #vimaldaga #righteducation