Professional Documents
Culture Documents
Manju Ayalli Prof. Vijay Kumar Naik Pawar Prof. (Dr.) Shailendra Aswale
Computer Engineering Shri Rayeshwar Institute of Engineering Shri Rayeshwar Institute of Engineering
Shri Rayeshwar Institute of Engineering Information Technology Information Technology
Information Technology Shiroda, Goa Shiroda, Goa
Shiroda, Goa vijaykumar.pawar@ritgoa.ac.in principal.ritgoa@gmail.com
ayallimanju4@gmail.com
Abstract— Automatic number plate recognition(ANPR) is one extracted number plate contains numbers and alphabets. And
of the smart transportation method that provides a then the various image processing algorithms are used [12] to
safe medium of transportation and monitoring planning used analyze the image and find the numbers, alphabets from the
by many two wheeler vehicles as well as four wheeler vehicles to image. After which second part is recognition, in this case
boost traffic controlling, routing, parking system, toll collection,
after finding the exact number, this number is searched in the
and governance and insuring highway law. There are various
techniques and algorithms has been developed so that we can database for owner information. Thus we can verify whether
identify and recognize Number plates. This paper shows a a user is authenticated or not.
various deep learning approach for recognizing and detecting
number plate. This system is divided into three parts, i.e. The automatic number plate recognition (ANPR) approach
number plate detection, segmentation, and character can be applied depending on different methodologies.
recognition. In our proposed system for number plate detection
Yolo method is used, after that some filters are applied and then Although ANPR uses many algorithms but still it is not
characters are segmented. Finally the Convolutional Neural successful in a state of precision and performance in real
Network is used to recognize all the segmented characters.
time. This can be reduced by applying deep learning
Keywords— Number Plate detection, Number plate recognition techniques. Deep learning is vast area of artificial intelligence
system, Character segmentation, Character recognition, , CNN, (AI) that uses neural network to learn from vast amounts of
Deep Learning, Yolo algorithm. data. This is part of machine learning [4] and uses many
layers to get advanced functionality from raw input. Today,
I. INTRODUCTION deep learning is used in almost every real-time application.
Compared to other algorithms, it is very efficient and has
Rapid road traffic requires a large amount of traffic proven to be as error-free as possible.
monitoring and management skills. In this case, you will not
be able to manually track vehicles moving at high speeds on The methods considered in this project are briefly detailed in
the road. Also, human energy and time is wasted. It is having the sections. Section II gives a literature review of the work.
been operated manually, that will cause a lot of difficulty and Table giving the efficiency of each particular method in
many mistakes. Hence there is a necessary to make an section II. With a diagram that briefs the working of our
automated system that assist in tracking vehicles by tracking project in section IV and ended the paper in section V.
their number plate in a more efficiently.
II. LITERATURE SURVEY
Automatic Number plate recognition (ANPR) became one of
the simplest ways for identifying cars [1]. It can be used in A. Number Plate Detection
many countries for many applications like keeping traffic
administration, vehicle tax, car parking, Toll collection etc. In this phase, we cut out the various boundary boxes that
The ANPR algorithm is divided into four categories: Vehicle could be treated as number plates. However to determine if a
image acquiring, number plate detection, character number plate from various boundary boxes are
segmentation and recognition. acceptable, the deep learning architecture presented in the
CNN model [3] is integrated to filter and identify whether the
First, the camera captures images of a car that contains a number plate is a number plate., The methods are:
number plate. From it, the number plate is detected and the
19
978-1-6654-6756-8/22/$31.00 ©2022 IEEE
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI. Downloaded on December 24,2022 at 17:43:19 UTC from IEEE Xplore. Restrictions apply.
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
20
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI. Downloaded on December 24,2022 at 17:43:19 UTC from IEEE Xplore. Restrictions apply.
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
B. Character Recognition
21
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI. Downloaded on December 24,2022 at 17:43:19 UTC from IEEE Xplore. Restrictions apply.
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
22
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI. Downloaded on December 24,2022 at 17:43:19 UTC from IEEE Xplore. Restrictions apply.
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
Reference Success
using Methods Rate Types of Categories
Algorithm (%)
ANN(Artificial English letters and
[17] 98.17%
Neural Network ) digit
English letters and
[13] Template matching 96.7%
digit
Chinese letters,
Back Propagation
[21] 93.5% English letters and
Neural Network
digit
Feed Forward Back English letters
[20] 95.69%
propagation and digit
CNN(Convolutional English letters Figure 2: vehicle Image
[8] 92.7%
Neural Network) and digit
DNN (Deep Neural 2. Number Plate Detection
[16] 90.6% English letters
Network)
KNN (K Nearest English letters YOLO method is used for localization of number plate, with
[2] 96.22%
Neighbours) and digit this we can separate number plate from the vehicle. This
[12]
SVM (Support
98.05%
English letters process removes the other complex pre-processing like edge
Vector Machine) and digit and contour detection for number plate detection [7]. The
number plates may be recognized under unexpected or
III. METHODOLOGY inappropriate conditions like the angle of number plate
placement, brightness, etc.
Our main motive is to make a framework which detects and
recognizes number plate in a given image or video. Our
approach is designed to focus on finding and reading number
Plate in tough environments. The proposed approach and it is
divided into different stages as shown in fig.1. In this we
proposes the number plate detection and recognition system
which is based upon the YOLO that works with efficiency
under a variety of conditions. YOLO is system which can be
trained to run a regression task evaluate both objects
bounding the box and an object class. This technique is Figure 3: Number plate detected from vehicle using YOLO
surprisingly fast, it continuously forms an image at 45 frames
per second.
3. Character Segmentation
23
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI. Downloaded on December 24,2022 at 17:43:19 UTC from IEEE Xplore. Restrictions apply.
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
Figure 5: Blurred image with a Gaussian filter of detected number plate REFERENCES
[1] Selmi, Zied; Ben Halima, Mohamed; Alimi, Adel M. (2017). [IEEE
2017 14th IAPR International Conference on Document Analysis and
Recognition (ICDAR) - Kyoto, Japan (2017.11.9-2017.11.15)] 2017
14th IAPR International Conference on Document Analysis and
Recognition (ICDAR) - Deep Learning System for Automatic License
Figure 6: Binary conversion of detected number plate Plate Detection and Recognition.
[2] Varma P, Ravi Kiran; Ganta, Srikanth; B, Hari Krishna; Svsrk, Praveen
(2020). A Novel Method for Indian Vehicle Registration Number Plate
Detection and Recognition using Image Processing Techniques.
Procedia Computer Science.
[3] Xie, Lele; Ahmad, Tasweer; Jin, Lianwen; Liu, Yuliang; Zhang, Sheng
Figure 7: Results of contour detection (2018). A New CNN-Based Method for Multi-Directional Car License
Plate Detection. IEEE Transactions on Intelligent Transportation
Systems.
4. Character Recognition [4] Hossen, M. S., Akter, M., & Saifuddin, K. M. (2021). Automatic Digit
and Alphabet Recognition Based Online Toll Collection System. 2021
The final step in the number plate detection is character International Conference on Information and Communication
Technology for Sustainable Development (ICICT4SD).
recognition. There are currently so many method applied for [5] Jamtsho, Yonten; Riyamongkol, Panomkhawn; Waranusast,
character recognition, which can be the syntactic, statistical Rattapoom (2019). Real-time Bhutanese license plate localization
and neural networks [14][15]. In this we will be using using YOLO. ICT Express.
Convolutional Neural Network (CNN) for recognize the [6] Mondal, Madhusree; Mondal, Parmita; Saha, Nilendu; Chattopadhyay,
Paramita (2017). [IEEE 2017 IEEE Calcutta Conference (CALCON) -
characters on number plate. We separate the characters and Kolkata, India (2017.12.2-2017.12.3)] 2017 IEEE Calcutta Conference
numbers using a CNN model with 37 classes. There are 36 (CALCON) - Automatic number plate recognition using CNN based
entry classes which are classes of digits (0 - 9) and 26 self-synthesized feature learning.
uppercase characters (A - Z) and another non-character class [7] Hashmi, S. N., Kumar, K., Khandelwal, S., Lochan, D., & Mittal, S.
(2019). Real Time License Plate Recognition from Video Streams
are also considered. using Deep Learning. International Journal of Information Retrieval
Research.
[8] Abdullah, Sohaib; Mahedi Hasan, Md; Muhammad Saiful Islam,
Sheikh (2018). [IEEE 2018 International Conference on Bangla Speech
and Language Processing (ICBSLP) - Sylhet, Bangladesh (2018.9.21-
Figure 7: Recognition of the number plate 2018.9.22)] 2018 International Conference on Bangla Speech and
Language Processing (ICBSLP) - YOLO-Based Three-Stage Network
for Bangla License Plate Recognition in Dhaka Metropolitan City.
Final Output in character recognition of the number plate [9] Cheng-Hung Lin, Yong-Sin Lin, and Wei-Chen Liu, An Efficient
shown in Fig.7. License [IEEE International Conference on Applied System Innovation
2018] Plate Recognition System Using Convolution Neural Networks
IV. CONCLUSION [10] Hendry, Chen, Rung-Ching (2019). Automatic License Plate
Recognition Via Sliding-Window Darknet-Yolo Deep Learning. Image
and Vision Computing.
Automatic Number Plate Recognition (ANPR) system is a [11] Gnanaprakash, V., Kanthimathi, N., & Saranya, N. (2021). Automatic
significant execution of artificial intelligence solutions for number plate recognition using deep learning. IOP Conference Series:
numerous aspect. It is generally helpful for security purposes, Materials Science and Engineering.
[12] Hafiz Ahamed , Ishraq Alam , Md. Manirul Islam [International
keeping vehicle record, toll collection, improved traffic Conference on Engineering Research and Education School of Applied
monitoring, better parking system, vehicle tracking, etc. sciences & Technology, SUST, Sylhet 2019] SVM Based Real Time
Many studies have been conducted on automatic number Hand-Written Digit Recognition System.
plate detection as well as character recognition. In reality, a [13] Avinash Bhujbal, Deepak ane [INTERNATIONAL JOURNAL OF
SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 8, ISSUE
variety of researchers have been done on many methods and 12, DECEMBER 2019] A Survey on Deep Learning Approaches for
techniques for this process. From the survey we can Vehicle and Number Plate Detection.
understand that there are different methods and techniques [14] Jiao, Licheng; Zhang, Fan; Liu, Fang; Yang, Shuyuan; Li, Lingling;
used and it has advantages and disadvantages, and the Feng, Zhixi; Qu, Rong (2019). A Survey of Deep Learning-based
Object Detection. IEEE.
effectiveness of technique is different from each other. Each [15] Tian Ying , Lu Xin , Li Wanxiang [ The 30th Chinese Control and
country has its own number plate numbering system, Decision Conference (2018 CCDC)] License Plate Detection and
different number plate sizes and colors, and character Localization in Complex Scenes Based on Deep Learning.
language. The above survey can give you that Valuable [16] Kessentini, Yousri; Besbes, Mohamed Dhia; Ammar, Sourour;
Chabbouh, Achraf (2019). A Two-Stage Deep Neural Network for
understanding and instructions for the approach use. We have Multi-norm License Plate Detection and Recognition. Expert Systems
proposed a deep learning technique represented by the CNN with Applications.
model for both number plate detection and character [17] Hinduja, Desai; Dheebhika, R.; Jacob, T. Prem (2019). [IEEE 2019
International Conference on Communication and Signal Processing
24
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI. Downloaded on December 24,2022 at 17:43:19 UTC from IEEE Xplore. Restrictions apply.
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
25
Authorized licensed use limited to: INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI. Downloaded on December 24,2022 at 17:43:19 UTC from IEEE Xplore. Restrictions apply.