society surveillance system

Project Title

society surveillance system

Project Area of Specialization Artificial IntelligenceProject Summary

The aim of our project is to design a system, which automatically identifies an approaching vehicles and record vehicles number. Number plate recognition(NPR) integrated automated security surveillance system, that provides real time security and full assistance to the security personals and security room with an eye on the cars passing by, maintaining their record enables to track movement and activities. NPR using optical character Recognition(OCR) helps maintain vehicle ownership and track. This Automated Number plate recognition will be used to detect car number and approval will be obtained from owner before in/out of car using mobile notification. In any mishap or security breach record can be inevitable to deny and evident in catching the culprits behind any such misconduct or crime.  Automatic recognition of car license plate number became a very important in our daily life because of the unlimited increase of cars and transportation systems.

Therefore in order to reduce the human error and to save time. The existing license plate recognition is designed usually for automatic number plate recognition.

The developed system first detects the vehicle and then captures the vehicle image. Vehicle number plate region is extracted using the image segmentation in an image, we have deployed better approach of objection detection through tensorflow(CNN model). Optical character recognition technique is used for the character recognition, here KNN was observed to be the better approach. The resulting data is then used to compare with the records on a database so as to come up with the specific information like the vehicle’s owner name, contact, registration detail, address, etc. Then approval will be obtained from owner through mobile application, on approval vehicle shall be allowed to leave the entrance.

Project Objectives

Develop a system for the purpose of vehicles and owners registration.To develop a program using Python to implement the ANPR(Automated Number Plate Recognition).To enhance the existing technique or algorithms, here we’re trying to combine best of both worlds KNN and CNN to recognize number plate and then it’s characters respectively

Project Implementation Method

To achieve the first goal of recognition, we will using image processing libraries such as OpenCV, Tensorflow, pillow, matplotlib and numpy to implement KNN ( K-Nearest Neighbors)  and CNN (Convolutional Neural Network). We have done web API in C#, it has manage all type of user’s records and deployed upon IIS(Internet Information Services).

Benefits of the Project

This project performs the recognition mechanism of number plates of cars and shows if the car is registered or not. The importance of this project is that it saves time, it manages toll and traffic system. Through this system, everyone can pay their tax of cars easily and if somehow a car gets involved in an accident or gets stolen so it can be tracked down through this system.

And the applications are already defined as above:

• Avoid any mishap or misuse of vehicle.
• Alert to owner through notification.
• Avoid theft.
• Real-time monitoring

Technical Details of Final Deliverable

We have used Python for Lenience Number Plate Recognition and there are some libraries which have been used in this work which are:

• CNN (Convolutional Neural Network)
• Tensorflow
• Keras
• Pandas
• OpenCv
• Numpy
• Matplotlib
• PIL(pillow)
• KNN (  K-Nearest Neighbors) Algorithm
• Numpy
• OpenCv

Android Studio, We have used Android Studio for our mobile app.

• User Interface GUI

C#

• Desktop Interface GUI
• API

SQL

• Database

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Security Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	70000
FHD cameras	Equipment	3	5000	15000
Cuda supported Graphics card	Equipment	1	55000	55000