A Design Of License Plate Recognition System Using Convolutional Neural Network
This paper proposes an improved Convolutional Neural Network (CNN) algorithm approach for license plate recognition system. The main contribution of this work is on the methodology to determine the best model for four-layered CNN architecture that has been used as the recognition method. This is ach...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute Of Advanced Engineering And Science (IAES)
2019
|
Subjects: | |
Online Access: | http://eprints.utem.edu.my/id/eprint/24052/1/A%20Design%20Of%20License%20Plate%20Recognition%20System%20Using%20Convolutional%20Neural%20Network.pdf http://eprints.utem.edu.my/id/eprint/24052/ http://ijece.iaescore.com/index.php/IJECE/article/view/17273/12839 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utem.eprints.24052 |
---|---|
record_format |
eprints |
spelling |
my.utem.eprints.240522020-03-05T12:14:50Z http://eprints.utem.edu.my/id/eprint/24052/ A Design Of License Plate Recognition System Using Convolutional Neural Network Ahmad Radzi, Syafeeza Piramli, Muhamad Marzuki Wong, Yan Chiew Abdul Hamid, Norihan Ali, Nur Alisa Mat Ibrahim, Masrullizam T Technology (General) TK Electrical engineering. Electronics Nuclear engineering This paper proposes an improved Convolutional Neural Network (CNN) algorithm approach for license plate recognition system. The main contribution of this work is on the methodology to determine the best model for four-layered CNN architecture that has been used as the recognition method. This is achieved by validating the best parameters of the enhanced Stochastic Diagonal Levenberg Marquardt (SDLM) learning algorithm and network size of CNN. Several preprocessing algorithms such as Sobel operator edge detection, morphological operation and connected component analysis have been used to localize the license plate, isolate and segment the characters respectively before feeding the input to CNN. It is found that the proposed model is superior when subjected to multi-scaling and variations of input patterns. As a result, the license plate preprocessing stage achieved 74.7% accuracy and CNN recognition stage achieved 94.6% accuracy. Institute Of Advanced Engineering And Science (IAES) 2019-06 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/24052/1/A%20Design%20Of%20License%20Plate%20Recognition%20System%20Using%20Convolutional%20Neural%20Network.pdf Ahmad Radzi, Syafeeza and Piramli, Muhamad Marzuki and Wong, Yan Chiew and Abdul Hamid, Norihan and Ali, Nur Alisa and Mat Ibrahim, Masrullizam (2019) A Design Of License Plate Recognition System Using Convolutional Neural Network. International Journal Of Electrical And Computer Engineering (IJECE), 9 (3). pp. 2196-2204. ISSN 2088-8708 http://ijece.iaescore.com/index.php/IJECE/article/view/17273/12839 10.11591/ijece.v9i3.pp2196-2204 |
institution |
Universiti Teknikal Malaysia Melaka |
building |
UTEM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknikal Malaysia Melaka |
content_source |
UTEM Institutional Repository |
url_provider |
http://eprints.utem.edu.my/ |
language |
English |
topic |
T Technology (General) TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
T Technology (General) TK Electrical engineering. Electronics Nuclear engineering Ahmad Radzi, Syafeeza Piramli, Muhamad Marzuki Wong, Yan Chiew Abdul Hamid, Norihan Ali, Nur Alisa Mat Ibrahim, Masrullizam A Design Of License Plate Recognition System Using Convolutional Neural Network |
description |
This paper proposes an improved Convolutional Neural Network (CNN) algorithm approach for license plate recognition system. The main contribution of this work is on the methodology to determine the best model for four-layered CNN architecture that has been used as the recognition method. This is achieved by validating the best parameters of the enhanced Stochastic Diagonal Levenberg Marquardt (SDLM) learning algorithm and network size of CNN. Several preprocessing algorithms such as Sobel operator edge detection, morphological operation and connected component analysis have been used to localize the license plate, isolate and segment the characters respectively before feeding the input to CNN. It is found that the proposed model is superior when subjected to multi-scaling and variations of input patterns. As a result, the license plate preprocessing stage achieved 74.7% accuracy and CNN recognition stage achieved 94.6% accuracy. |
format |
Article |
author |
Ahmad Radzi, Syafeeza Piramli, Muhamad Marzuki Wong, Yan Chiew Abdul Hamid, Norihan Ali, Nur Alisa Mat Ibrahim, Masrullizam |
author_facet |
Ahmad Radzi, Syafeeza Piramli, Muhamad Marzuki Wong, Yan Chiew Abdul Hamid, Norihan Ali, Nur Alisa Mat Ibrahim, Masrullizam |
author_sort |
Ahmad Radzi, Syafeeza |
title |
A Design Of License Plate Recognition System Using Convolutional Neural Network |
title_short |
A Design Of License Plate Recognition System Using Convolutional Neural Network |
title_full |
A Design Of License Plate Recognition System Using Convolutional Neural Network |
title_fullStr |
A Design Of License Plate Recognition System Using Convolutional Neural Network |
title_full_unstemmed |
A Design Of License Plate Recognition System Using Convolutional Neural Network |
title_sort |
design of license plate recognition system using convolutional neural network |
publisher |
Institute Of Advanced Engineering And Science (IAES) |
publishDate |
2019 |
url |
http://eprints.utem.edu.my/id/eprint/24052/1/A%20Design%20Of%20License%20Plate%20Recognition%20System%20Using%20Convolutional%20Neural%20Network.pdf http://eprints.utem.edu.my/id/eprint/24052/ http://ijece.iaescore.com/index.php/IJECE/article/view/17273/12839 |
_version_ |
1665905883281883136 |
score |
13.18916 |