HELMET DETECTION AND

NUMBER PLATE RECOGNITION

USING ARTIFICIAL
INTELLIGENCE
Content
● 1. Introduction
● 2. Existing and Proposed Methods
● 3. Algorithm
● 4. System Architecture
● 5. Hardware and Software Requirements
● 6. Literature Survey
● 7. DFD Diagram
● 8. ER Diagram
● 9. Sample Dataset used in program
● 10. SRS Diagram
Introduction
● In countries like India, Brazil, Thailand, majority of population uses motorcycles for daily commute.
In India, In most of these countries, wearing helmet for motorcyclists is mandatory by law. Also,
considering safety of people using motorcycles, wearing helmet is paramount.
● Currently, in practice, Traffic Police are entrusted with the task of ensuring that motorcycle riders
wear helmet. But, this method of monitoring motorcyclists is inefficient due to insufficient police
force and limitations of human senses.
● Also, all major cities use CCTV surveillance based methods. But, those require human assistance
and are not automated. Due to the increasing number of motorcycles and the concern for human
safety, there has been a growing amount of research in the domain of road transport.
● The system proposed in this paper automates the task of monitoring motorcyclists.
Existing Method
● Bases of observation in the existing system high rate of accidents and rules violation is their. To
avoid this proposed system is very helpful and effective.
Proposed Method
● In India road accidents are increased very rapidly and lots of deaths are occur due to head injuries
because number of peoples not wearing helmets ,so to avoid the system that automatically
detects the peoples who are not wearing helmet and also detect number plates of the
motorcycles to penalize that persons.
Algorithm
OCR Algorithm
● Optical Character Recognition, is a process of recognizing text inside images and converting it
into an electronic form. These images could be of handwritten text, printed text like documents,
receipts, name cards, etc., or even a natural scene photograph.
● OCR has two parts to it. The first part is text detection where the textual part within the image is
determined. This localization of text within the image is important for the second part of
OCR, text recognition, where the text is extracted from the image. Using these techniques
together is how you can extract text from any image.
System Architecture
Hardware and Software Requirements
● Software: Anaconda Navigator
● IDE: Spyder
● Language: Python
● RAM: 8 GB
● Harddisk: 350 GB
● Operating System: Windows 10
 Literature Survey

Sr.No Paper Name Author Name Description

1 Automated Madhuchhanda Automated detection of traffic rule violators is an essential

Helmet Dasgupta, Oishila component of any smart traffic system. In a country like India with
Detection for Bandyopadhyay, high density of population in all big cities, motorcycle is one of the
Multiple Sanjay Chatterji main modes of transport. It is observed that most of the
Motorcycle motorcyclists avoid the use of helmet within the city or even in
Riders using highways.Use of helmet can reduce the risk of head and severe brain
CNN injury of the motorcyclists in most of the motorcycle accident cases

2 Helmet and Fahad A Khan, Helmet not used by the motorcycle rider is one of the major cause.
Number Plate Nitin Nagori, Dr. Currently, one procedure is to physically check use of helmet at the
detection of Ameya Naik pavement junction or through the CCTV footage video, which
Motorcyclist requires human intervention to detect motorcyclists without helmet.
Literature Survey
Sr.
No Paper Name Author Name Description

3 Helmet Detection Using Dikshant Manocha, This paper is about detecting two-wheeler riders without
ML IoT Ankita helmet with the help of machine learning and provide
Purkayastha, Yatin them with a user interface to pay challans.
Chachra

4 Convolutional Neural Y Mohana Roopa, Numerous reasons lead to dangerous accidents. Lack of
Network-based Automatic Sri Harshini Popuri helmet is one of the major reasons for death during
Extraction and accidents. People are negligent regarding helmet usage.
FineGeneration This needs to be controlled by proper surveillance.

5 Improved OCR based Bhavin V Kakani, Significant research and development of algorithms in
Automatic Vehicle Number Divyang Gandhi, intelligent transportation has grabbed more attention in
PlateRecognition Sagar Jani recent years. An automated, fast, accurate
using Features Trained and robust vehicle plate recognition system has become
Neural Network need for traffic control.
DFD Diagrams

● DFD 0

● DFD 1
ER Diagram
Sample Dataset used in the program

● We are going to take Image Dataset from kaggle website which contain helmet or non
helmet images.
 SRS Diagrams

● Use Case Diagram

● Activity Diagram
● Class Diagram
● Sequence Diagram
● Componant Diagram
● Deployment Diagram