Character recognition of Malaysian vehicle license plate with deep convolutional neural networks

Classification (of information); Computer networks; Convolution; Intelligent control; Intelligent robots; License plates (automobile); Neural networks; Optical character recognition; Robotics; Smart sensors; Background image; Convolutional networks; Data augmentation; Deep convolutional neural netwo...

Full description

Saved in:
Bibliographic Details
Main Authors: How D.N.T., Sahari K.S.M.
Other Authors: 56942483000
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers Inc. 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-23094
record_format dspace
spelling my.uniten.dspace-230942023-05-29T14:37:44Z Character recognition of Malaysian vehicle license plate with deep convolutional neural networks How D.N.T. Sahari K.S.M. 56942483000 57218170038 Classification (of information); Computer networks; Convolution; Intelligent control; Intelligent robots; License plates (automobile); Neural networks; Optical character recognition; Robotics; Smart sensors; Background image; Convolutional networks; Data augmentation; Deep convolutional neural networks; Learning models; Vehicle license; Vehicle license plate recognition; Vehicle license plates; Deep neural networks This paper presents a vehicle license plate recognition method using deep convolutional neural networks. The focus of this paper is placed on the recognition of segmented characters of vehicle license. The deep convolutional neural network is able to distinguish numbers (0 to 9), alphabets (A to Z) and background image from one another. We show that the neural networks trained on computer fonts and natural images can be used to recognize the characters and non-characters on the vehicle license plates. In our experiments, we compared several models of the deep learning model and measure the performance of each model. We find that deeper models of neural networks yield better recognition results. What also find that the deep convolutional neural network is much more robust at the task of character recognition compared to the deep multilayer perceptron. With approximately equal amount of weights and biases parameters, the deep convolutional neural network outperforms all other models on the same task. Our best model using deep convolutional network, can achieve 95.89% correct classification of real license plate characters when even though the network is only trained on computer fonts (from Chars74K dataset) and natural images (from CIFAR10 dataset). No data augmentation is performed during the training. � 2016 IEEE. Final 2023-05-29T06:37:44Z 2023-05-29T06:37:44Z 2017 Conference Paper 10.1109/IRIS.2016.8066057 2-s2.0-85050190029 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050190029&doi=10.1109%2fIRIS.2016.8066057&partnerID=40&md5=3ebd3c3fd1f0c551d121612513e71e59 https://irepository.uniten.edu.my/handle/123456789/23094 1 5 Institute of Electrical and Electronics Engineers Inc. Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Classification (of information); Computer networks; Convolution; Intelligent control; Intelligent robots; License plates (automobile); Neural networks; Optical character recognition; Robotics; Smart sensors; Background image; Convolutional networks; Data augmentation; Deep convolutional neural networks; Learning models; Vehicle license; Vehicle license plate recognition; Vehicle license plates; Deep neural networks
author2 56942483000
author_facet 56942483000
How D.N.T.
Sahari K.S.M.
format Conference Paper
author How D.N.T.
Sahari K.S.M.
spellingShingle How D.N.T.
Sahari K.S.M.
Character recognition of Malaysian vehicle license plate with deep convolutional neural networks
author_sort How D.N.T.
title Character recognition of Malaysian vehicle license plate with deep convolutional neural networks
title_short Character recognition of Malaysian vehicle license plate with deep convolutional neural networks
title_full Character recognition of Malaysian vehicle license plate with deep convolutional neural networks
title_fullStr Character recognition of Malaysian vehicle license plate with deep convolutional neural networks
title_full_unstemmed Character recognition of Malaysian vehicle license plate with deep convolutional neural networks
title_sort character recognition of malaysian vehicle license plate with deep convolutional neural networks
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2023
_version_ 1806427344213114880
score 13.214268