You are on page 1of 20

NUMBER PLATE DETECTION

UNDER THE GUIDANCE OF


PREPARED BY:
G.Nirmala P.Abhivarun Reddy(20X31A0482)
Asst.Professor Pulakanti Pooja (20X31A0494)
Uppala Manahor (20X31A04B6)
Narsing Akshith (20X31A0477)
M.SriRam charan (20X31A0465)
CONTENTS:-
 Abstract
 Introduction
 Block diagram
 Methods
 OpenCV
 Software & Hardware
 Advantages & Disadvantages
 Applications
 Result
 Conclusion
 Future scope
 References
ABSTRACT:-

In the field of intelligent transport systems, recent years have witnessed the application of deep
learning techniques to both car plate detection and recognition. the latter stage, known as optical
character recognition (ocr), ismore challenging as it requires an accurate prediction of the entire
license numbers. one of the widely used ocr engines is the tesseract, which uses longshort-term
memory (lstm). however, the drawback of this approach is the time-consuming image
preprocessing techniques. this project aims to design an accurate yet lightweight ocr solution by
exploring the bidirectional lstm, connectionist temporal classification (ctc) and resnet.
INTRODUCTION:-
Developing a parking area monitoring system that can recognise the car
Plate from a database using a DL model is the scope of this project. The
Limitation of this study is the limited processing power of the device used
to train the OCR model. Hence, a strong GPU device is recommended for
training the DL model. It helps in shortening the training time of the model
effectively. On the other hand, google colab can overcome the constraint In
processing power. However, google colab has limited access time for 12
Hours of free GPU usage.
BLOCK DIAGRAM:-
METHODS USED FOR DETECTION:-

 Character segmentation algorithm


 Optical character recognition(OCR)
 Image processing method
Character segmentation algorithm:-

Extract individual characters from the number plate image using techniques such as contour
detection and connected component analysis.

Character segmentation is an operation that seeks to decompose an image of a sequence of


charac- ters into subimages of individual symbols.
Optical character recognition(OCR):-

OCR stands for "Optical Character Recognition." It is a technology


that recognizes text within a digital image. It is commonly used to
recognize text in scanned documents and images. OCR software
can be used to convert a physical paper document, or an image into
an accessible electronic version with text.
Image processing method:-
Enhance image quality through techniques like noise reduction, image
thresholding, and morphological operations.There are many image processing
methods available in Python. Here the one of the most popular:

 OpenCV :- OpenCV is a free, open-source, and cross-platform library that includes


hundreds of computer vision algorithms. It has Python bindings, making it easy to use
in Python code. OpenCV can be used for a variety of image processing tasks,
including object detection, tracking, and recognition, as well as image filtering and
segmentation
OpenCV:-
OpenCV is a great tool for image processing and
performing computer vision tasks. It is an open-source library that
can be used to perform tasks like face detection, objection
tracking, landmark detection, and much more. It supports multiple
languages including python, java C++. Although, For this article,
we will be limiting to python only.

The library is equipped with hundreds of useful


functions and algorithms, which are all freely available to us.
Some of these functions are really common and are used in almost
every computer vision task. Whereas many of the functions are
still unexplored and haven’t received much attention yet
SOFTWARE:-

 Python, opencv, intel distribution of openvino toolkit.

 Apache HTTP server.

 Flask.

 MySql.

 Yolov4 object detection

 Google colaboratory
HARDWARE:-

 Intel NUC 10i7 Mini PC Kit

 Beelink Mini PC BT3 Pro


ADVANTAGES:-

 Monitoring and Surveillance

 Improved Security

 Still and Video Footage

 Faster traffic management

 Enhanced parking management


DISADVANTAGES:-

 Privacy concerns

 False positives and false negatives

 Cost

 Limited accuracy

 Legal and ethical considerations

 Limited to certain types of vehicles

 Maintanence
APPLICATIONS:-
 Automatic toll collection

 Border crossings

 Parking system

 Traffic controls

 Stolen cars tracking

 Maintaining traffic activities

 Law enforcement
RESULT:-

The evaluation of this project utilises the cpu of intel nuc 10i7 mini pc kit and a captured
video dataset which consists of a real scene of cars with 30 psand a duration length of 26 minutes and 43
seconds. the intention of using thisvideo dataset which has environmental constraints such as light
intensity,background complexity and different captured angles as the camera is moving.there are two
major evaluations in this chapter which are on the performance of fps and the performance of ocr
accuracy
CONCLUSION:-
The hardware limitation is a significant issue for industries and businesses as computer vision is
introduced into the iot era. ocr as part of computer vision which is used in an integrated system, is a real-
time performance required in certain applications especially car park monitoring systems in malaysia. for
the sake of improving the accuracy, the conventional ocr is heavily relying on preprocessing and post-
processing which imply a high degree of customisation,less flexibility and the performance is highly
affected by environmental factors.
FUTURE SCOPE:-
This program can be used for variety of works where a license number is the
primary way of recognizing a vehicle. Current application is completely usable for little
uses as parking area or traffic line use. In future we can include face acknowledgment
and connection the entire framework with criminal database and recognize passing
criminal outlaws
REFERENCES:-

Alyahya, H.M., Alharthi, M.K., Alattas, A.M. and Thayananthan, V., 2017. Saudi License Plate Recognition System
Using Artificial Neural Network Classifier. 2017 International Conference on Computer and Applications, ICCA2017,
pp.220–226. https://doi.org/10.1109/COMAPP.2017.8079759.

Anon. 2022a. Parking Revenue Control Systems, Parking System Solutions,On-street Parking Manufacturers and
Suppliers China - Factory Price - Wiicontrol. [online] Available at: <https://www.wiiparking.com/> [Accessed 2
September 2022].
Anon, 2022b. Intel NUC 10 Performance NUC10i7FNH Barebone System Mini PC. [image online] Available at: <
https://www.amazon.com/Intel- Performance-NUC10i7FNH-Barebone-System/dp/B083SJCJSV> [Accessed 10 March
2022].
THANK YOU

You might also like