Car Number Plate Detection model Web Portal

Task Description

Step 1: Create a model that will detect a car in a live stream or video and recognize characters on the number plate of the car.

Step 2: It will use the characters of the Number plate and fetch the owner’s information using RTO APIs.

Step 3: Create a Web portal where all this information will be displayed using HTML, CSS, and JS, or any other Technologies.

So, Let's get started with the task.

  1. What is the Autonomous Car Number Plate Detection System?
  2. What are its Usecases in Realife?
  3. Prerequisites for Successfully doing this task.

Autonomous Car Number Plate Detection System

Automatic Number Plate Recognition(ANPR) : ANPR has become part of our lives and promises to stay in the future, integrable with proposed transportation technologies. The concept of Autonomous Vehicles is providing many possibilities for changing fundamental transportation systems. Automatic License Plate Recognition technology is already contributing towards intelligent transportation systems and is eliminating the need for human intervention. It is no longer just the camera on the roadside or at the barricade at the car parking. It has become over the years mobile, first being deployed in vehicles, but now more recently with the advancement of smartphone and Cloud Computing technology, many ANPR systems have become handheld too. Due to lower provisioning costs, this system is often a choice in the toll and parking lot use cases.

Use cases in Real life

  1. Parking: one among the most applications of ANPR is parking automation and parking security: ticketless parking fee management, parking access automation, vehicle location guidance, car theft prevention, “lost ticket” fraud, fraud by changing tickets, simplified, partially, or fully automated payment process, among many others.
  2. Access Control: Access control, generally, may be a mechanism for limiting access to areas and resources that supported users’ identities and their membership in various predefined groups. Access to limited zones, however, can also be managed supported by accessing vehicles alone, or alongside identity. car place recognition brings automation of auto access control management, providing increased security, carpool management for logistics, security guide assistance, event logging, event management, keeping access diary, possibilities for analysis, and data processing.
  3. Motorway Road Tolling: Road Tolling means, that motorists pay directly for the usage of a specific segment of road infrastructures. Tolls are a standard way of funding the improvements of highways, motorways, roads, and bridges: tolls are fees for services. Efficient road tolling increases the extent of related road services by reducing time period overhead, congestion and improve roadways quality. Also, efficient road tolling reduces fraud associated with non-payment, makes charging effective, reduces required manpower to process events of exceptions. car place recognition is usually used as a really efficient enforcement tool, while there are road tolling systems based solely on car place recognition too.
  4. Border Control: Border Control is a longtime state-coordinated effort to realize operational control of the country’s state border with the priority mission of supporting the homeland’s security against terrorism, illegal cross-border traffic, smuggling, and criminal activities. Efficient border control significantly decreases the speed of violent crime and increases society’s security. Automatic number plate recognition adds significant value by event logging, establishing investigate-able databases of border crossings, alarming suspicious passings, at more.
  5. Journey Time Measurement: Journey Time Measurement may be a very efficient and widely usable method of understanding traffic, detecting conspicuous situations and events, etc. A computer vision-based system has its well-known downfalls in Journey Time Measurement, while Automatic Number Plate Recognition has provided its viability: vehicle journey times are often measured reliably by automatic number plate recognition-based systems. Data collected by car place recognition systems are often utilized in some ways after processing: feeding back information to road users to extend traffic security, helping efficient enforcement, optimizing traffic routes, reducing costs and time, etc.
  6. Law Enforcement: ANPR is a perfect technology to be used for enforcement purposes. it’s ready to automatically identify stolen cars supported by the up-to-date blacklist. Other quite common enforcement applications are red-light enforcement and Overspeed charging and traffic lane control.

Prerequisites for this task:

  1. We must need certain Python and Deep Learning Libraries Installed in our Base Operating System. The alternative we can use Google Colab.
  2. We should install a flask package in our system.
  3. We should know the basic knowledge of python, Flask, Javascript, CSS, HTML, Open-CV Image process working.
  4. We need a Video or Image in which we want to detect the car’s plate and retrieve information
  5. We must create an account in any of Open RTO’s API Key providers. In here I am providing a link where they provide the first 10 car plate identification free of cost

Let's Get Started with the Coding Part with a step-by-step workflow So that anyone can easily understand. It's not rocket science we have to spend months to understand the concept in Machine learning, It's all about analyzing concepts where to use and apply that's all.

  1. Detect the Number Plate of a vehicle from a video or an Image.

We will detect our car using the LBPH algorithm.

Local Binary Patterns Histogram algorithm was proposed in 2006. It is based on local binary operator. It is widely used in facial recognition due to its computational simplicity and discriminative power.
The steps involved to achieve this are:

  • creating dataset
  • face acquisition
  • feature extraction
  • classification

Video Demo Work flow

Even though model can predict 85% of score but most of time due to less data set we cant get 100% accuracy.




Aspiring Cloud DevOps MlOps Enthusiast

Recommended from Medium

MMDetection3D:The next generation 3D object detection platform

Introducing What To Label

Gathering Smart Data

Environment setting for deep learning model using Apple m1:

Main Challenges in Image Classification

GAN for unsupervised anomaly detection on X-ray images.

Adversarial robustness

How to get started with machine learning on graphs

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Sathya Narayana

Sathya Narayana

Aspiring Cloud DevOps MlOps Enthusiast

More from Medium


Confusion Matrix for Multi-Class Classification

[Metarrior — Character Introduction Series] Tordil — The Woodland Spearman

Fine tuning XLSR Wav2Vec model for Indian Languages