e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:04/April-2022 Impact Factor- 6.752 www.irjmets.com
AUTOMATIC NUMBER PLATE RECOGNITION
Shubhra Tonge*1, Bhavisha Hemwani*2, Gulshan Thawani*3,
Sonnal Katara*4, Nikhil Dhanwani*5
*1Lecturer, Department Of Computer Engineering, Vivekanand Education Society’s Polytechnic,
Sindhi Society, Chembur, Mumbai - 400071, India.
*2,3,4,5Final Year Student, Department Of Computer Engineering, Vivekanand Education Society’s
Polytechnic, Sindhi Society, Chembur, Mumbai - 400 071, India.
ABSTRACT
Automatic Number Plate Recognition (ANPR) is a mass surveillance system that captures the image of vehicles
and recognizes their license number. ANPR can be assisted in the detection of stolen vehicles. This paper
presents a recognition method in which the vehicle plate image is obtained by the digital cameras and the
image is processed to get the number plate information. A rear image of a vehicle is captured and processed
using various algorithms. The ANPR is the image processing technique to extract the image of the license plate.
To read and visualize images, we will be using OpenCV with Python. Also, to identify the vehicles using their
number plates we will require Optical Character Recognition (OCR).
Keywords: License Plate, Number Plate, Image Processing, Optical Character Recognition (OCR).
I. INTRODUCTION
Due to the increasing number of vehicles nowadays, the modern city needs to establish effective and efficient
Automatic Number Plate Recognition. Automatic Number Plate Recognition (ANPR) leads to a significant role in
this condition. The ANPR is the image processing technique to extract the image of the license plate. To read
and visualize images, we will be using OpenCV with Python. Also, to identify the vehicles using their number
plates we will require Optical Character Recognition (OCR).
In this project, we are going to create an Automatic Number Plate Recognition which will detect the number
plate and will display the characters of the number plate on the screen. This extraction of characters is done
using Optical Character Recognition (OCR). The number plate detection will be done through some
algorithm/technique with the help of Python language. Open-Source Computer Vision Library is a library of
programming functions that focuses on real-time computer vision. The library is cross-platform. Its main
purpose is real-time image processing. If the native Intel performance primitives are installed on the system
through self-optimized routines, library performance can be improved. This system will detect the number
plate and will give characters of the number plate. The number plate will be detected using contours and then
the number plate will be masked to improve the text extraction.
The system will be capable of extracting characters from the number plate. For extracting the characters, firstly
we will have to read and visualize the image using OpenCV, then filters (e.g.: grayscale) will be applied to the
image, contours will be detected, number plates will be masked to improve the text extraction. Finally, the
characters of the number plate will be extracted using OCR.
II. METHODOLOGY
In paper [1,2,3], The fundamental idea behind this project is to detect the characters of the number plate. Using
traditional Automatic Number Plate Recognition, the processing of images in dark light and low light was not
visible and not clear which could be made better. With the ever-increasing growth in the field of multimedia
and technology, many number plate recognition systems with many such capabilities are being made in today's
globe. Although these capabilities meet the requirements, still it can be made more efficient and user-friendly.
Number Plate Recognition is the ability to detect the location of a number plate in any input or frame. It can
recognize number plates in an image; with the help of these techniques, we can identify faces with greater
accuracy.
Number Plate Recognition systems such as OpenCV, Neural Networks, Canny Edge Detector and others follow a
nearly same procedure. In some projects, they have created a Number Plate Recognition with Python, OpenCV,
Android Studios, and the Canny Edge Detector.
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[269]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:04/April-2022 Impact Factor- 6.752 www.irjmets.com
1. Image Detection
In this module, the image of the number plate from an already in-built camera. After reading and visualizing the
image of the number plate, the image is then sent for further processing where it is applied filters and scaled
along with this it’s also tested using the techniques proposed in the system i.e., OpenCV. OpenCV, Image
Processing algorithm, and Optical Character Recognition (OCR) will be used in our project to detect the number
plate. Following is detailed information about the techniques used in our project.
OpenCV is the huge open-source library for computer vision, image processing, and now in present times, this
library plays a major role in real-time operation which is very important in terms of technology, user –
interface, and also in other such fields. By using it, one can process images and videos to identify objects, faces,
or even handwriting of a human. When integrated with various libraries, such as NumPy, python is capable of
processing the OpenCV array structure for analysis.
2. Image Processing in OpenCV:
Performing certain operations on the image provided is called Image Processing. To extract some useful
features image processing is used which results in giving required information regarding the image. Bringing
back to the basic definition of image processing it says “It is a type of signal processing in which input is an
image and output may be image or characteristics/features associated with that image.”
Image processing basically includes the following three steps:
1) Importing the image
2) Analyzing and manipulating the image
3) Output in which the result can be altered image or report that is based on image analysis.
3. Character Recognition
Optical Character Recognition (OCR) is the electronic or mechanical conversion of images of typed, handwritten
or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-
photo or from subtitle text superimposed on an image. In more simple way, OCR is a process of extracting text
from images. You may have already seen many of its real-world applications like text extraction from
documents, collecting data from Invoices, passport documents, bank statements, computerized receipts,
business cards, mail, characters from number plate, printouts of static-data, or any suitable documentation. It is
a common way of digitizing printed texts so that they can be electronically edited, searched, stored more
compactly, displayed on-line, and used in machine processes.
III. MODELING AND ANALYSIS
A. OVERVIEW
According to fig. 1, it depicts the abstract view of the system, showing all the modules.
The proposed system consists of five modules. The Automatic Number Plate Recognition module firstly reads
and visualizes the image from the system. After this the image is then filters are applied onto the image and
contours are detected using the OpenCV technique. After this, masking is applied onto the image to improve the
text extraction; lastly, the text/characters of the number plate are extracted using the Optical Character
Recognition (OCR) technique.
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[270]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:04/April-2022 Impact Factor- 6.752 www.irjmets.com
Figure 1: Iterative Design Diagram Of Automatic Number Plate Recognition
After this, masking is applied onto the image to improve the text extraction; lastly, the text/characters of the
number plate are extracted using the Optical Character Recognition (OCR) technique.
Figure 2: DFD Level 0 Diagram of the system
According to fig. 2, it depicts the abstract view of the system, showing the relationship with the external entities
which is the user and the system Level 0 is also called a Context Diagram. It's a basic overview of the whole
system or process being analyzed or modeled. It's designed to be an at-a-glance view, showing the system as a
single high-level process, with its relationship to external entities.
Figure 3: DFD Level 1 Diagram of the system
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[271]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:04/April-2022 Impact Factor- 6.752 www.irjmets.com
According to fig. 3, it expresses what are the main functions our system provides.
Activity Diagram For Our System:
Figure 4: Activity Diagram For Our System
Fig 4 shows the Activity diagram of the system, which explains how the actor i.e., the user interacts with the
system and how the system accepts the request from the user and internally handles all the functions and
provides the accurate results to the user. In short it checks the behavior of the system and checks how it
responds to the user.
IV. RESULTS AND DISCUSSION
Step 1: Original Image Step 2: Reading and visualizing images.
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[272]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:04/April-2022 Impact Factor- 6.752 www.irjmets.com
Step 3: Applying Filters Step 4: Finding Contours
Step 5: Use OCR To Extract Text And Render Result
V. CONCLUSION
An Automatic Number Plate Recognition approach would basically extract the text/characters of the number
plate. For achieving this approach, we will be using techniques such as OpenCV, Image Processing, Optical
Character Recognition (OCR). Also, Automatic Number Plate Recognition systems would work fine in the dark
and low light environment.
VI. FUTURE SCOPE
Our future plans for this system are to implement this system to scale up to various users and make the entire
system and the entire process of detecting images in a more efficient way also make it smooth. We would like to
use this system in a real-life problem and accordingly customize it for the needs of the company/user. Also,
we’ve thought of implementing this system wherever there is any need for ANPR systems such as highways, car
tolls, etc.
VII. REFERENCES
[1] P. Kulkarni, A. Khatri, P. Banga and K. Shah, "Automatic Number Plate Recognition (ANPR) system for
Indian conditions," 2009 19th International Conference Radioelektronika, 2009, pp. 111-114,
doi: 10.1109/RADIOELEK.2009.5158763.
[2] A. Beibut, K. Magzhan and K. Chingiz, "Effective algorithms and methods for automatic number plate
recognition," 2014 IEEE 8th International Conference on Application of Information and
Communication Technologies (AICT), 2014, pp. 1-4, doi: 10.1109/ICAICT.2014.7035951.
[3] B. Pechiammal and J. A. Renjith, "An efficient approach for automatic license plate recognition
system," 2017 Third International Conference on Science Technology Engineering & Management
(ICONSTEM), 2017, pp. 121-129, doi: 10.1109/ICONSTEM.2017.8261267.
[4] B. V. Kakani, D. Gandhi and S. Jani, "Improved OCR based automatic vehicle number plate recognition
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[273]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:04/April-2022 Impact Factor- 6.752 www.irjmets.com
using features trained neural network," 2017 8th International Conference on Computing,
Communication and Networking Technologies (ICCCNT), 2017, pp. 1-6,
doi: 10.1109/ICCCNT.2017.8203916.
[5] F. Fajas, F. Yousuf, P. R. Remya, A. P. Pavanan, S. Ambadiyil and V. Swaminathan, "Automatic Number
Plate Recognition for Indian standard number plates," 2012 IV International Congress on Ultra Modern
Telecommunications and Control Systems, 2012, pp. 1026-1028, doi: 10.1109/ICUMT.2012.6459645.
[6] M. T. Qadri and M. Asif, "Automatic Number Plate Recognition System for Vehicle Identification Using
Optical Character Recognition," 2009 International Conference on Education Technology and
Computer, 2009, pp. 335-338, doi: 10.1109/ICETC.2009.54.
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[274]
