A New Image Enhancement and Super Resolution technique for license plate recognition

License Plate Recognition (LPR) is an important implemented application of Artificial Intelligence (AI) and deep learning in the past decades. However, due to the low image quality caused by the fast movement of vehicles and low-quality analogue cameras, many plate numbers cannot be recognised accur...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Abdelsalam Hamdi, Yee Kit Chan, Voon Chet Koo
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
LPR
Acceso en línea:https://doaj.org/article/6de844c58d7e4adb8067be9895a5ca05
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:6de844c58d7e4adb8067be9895a5ca05
record_format dspace
spelling oai:doaj.org-article:6de844c58d7e4adb8067be9895a5ca052021-12-02T05:02:45ZA New Image Enhancement and Super Resolution technique for license plate recognition2405-844010.1016/j.heliyon.2021.e08341https://doaj.org/article/6de844c58d7e4adb8067be9895a5ca052021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2405844021024440https://doaj.org/toc/2405-8440License Plate Recognition (LPR) is an important implemented application of Artificial Intelligence (AI) and deep learning in the past decades. However, due to the low image quality caused by the fast movement of vehicles and low-quality analogue cameras, many plate numbers cannot be recognised accurately by LPR models. To solve this issue, we propose a new deep learning architecture called D_GAN_ESR (Double Generative Adversarial Networks for Image Enhancement and Super Resolution) used for effective image denoising and super-resolution for license plate images. In this paper, we show the limitation of the existing networks for image enhancement and image super-resolution. Furthermore, a feature-based evaluation metric called Peak Signal to Noise Ratio Features (PSNR-F) is used to evaluate and compare performance between different methods. It is shown that the use of PSNR-F has a better performance indicator than the classical PSNR-pixel-to-pixel (PSNR-pixel) evaluation metric. The results show that using D_GAN_ESR to enhance the license plate images increases the LPR accuracy from 30% to 78% when blur images are used and increases the accuracy from 59% to 74.5% when low-quality images are used.Abdelsalam HamdiYee Kit ChanVoon Chet KooElsevierarticleImage Super ResolutionImage EnhancementLPRScience (General)Q1-390Social sciences (General)H1-99ENHeliyon, Vol 7, Iss 11, Pp e08341- (2021)
institution DOAJ
collection DOAJ
language EN
topic Image Super Resolution
Image Enhancement
LPR
Science (General)
Q1-390
Social sciences (General)
H1-99
spellingShingle Image Super Resolution
Image Enhancement
LPR
Science (General)
Q1-390
Social sciences (General)
H1-99
Abdelsalam Hamdi
Yee Kit Chan
Voon Chet Koo
A New Image Enhancement and Super Resolution technique for license plate recognition
description License Plate Recognition (LPR) is an important implemented application of Artificial Intelligence (AI) and deep learning in the past decades. However, due to the low image quality caused by the fast movement of vehicles and low-quality analogue cameras, many plate numbers cannot be recognised accurately by LPR models. To solve this issue, we propose a new deep learning architecture called D_GAN_ESR (Double Generative Adversarial Networks for Image Enhancement and Super Resolution) used for effective image denoising and super-resolution for license plate images. In this paper, we show the limitation of the existing networks for image enhancement and image super-resolution. Furthermore, a feature-based evaluation metric called Peak Signal to Noise Ratio Features (PSNR-F) is used to evaluate and compare performance between different methods. It is shown that the use of PSNR-F has a better performance indicator than the classical PSNR-pixel-to-pixel (PSNR-pixel) evaluation metric. The results show that using D_GAN_ESR to enhance the license plate images increases the LPR accuracy from 30% to 78% when blur images are used and increases the accuracy from 59% to 74.5% when low-quality images are used.
format article
author Abdelsalam Hamdi
Yee Kit Chan
Voon Chet Koo
author_facet Abdelsalam Hamdi
Yee Kit Chan
Voon Chet Koo
author_sort Abdelsalam Hamdi
title A New Image Enhancement and Super Resolution technique for license plate recognition
title_short A New Image Enhancement and Super Resolution technique for license plate recognition
title_full A New Image Enhancement and Super Resolution technique for license plate recognition
title_fullStr A New Image Enhancement and Super Resolution technique for license plate recognition
title_full_unstemmed A New Image Enhancement and Super Resolution technique for license plate recognition
title_sort new image enhancement and super resolution technique for license plate recognition
publisher Elsevier
publishDate 2021
url https://doaj.org/article/6de844c58d7e4adb8067be9895a5ca05
work_keys_str_mv AT abdelsalamhamdi anewimageenhancementandsuperresolutiontechniqueforlicenseplaterecognition
AT yeekitchan anewimageenhancementandsuperresolutiontechniqueforlicenseplaterecognition
AT voonchetkoo anewimageenhancementandsuperresolutiontechniqueforlicenseplaterecognition
AT abdelsalamhamdi newimageenhancementandsuperresolutiontechniqueforlicenseplaterecognition
AT yeekitchan newimageenhancementandsuperresolutiontechniqueforlicenseplaterecognition
AT voonchetkoo newimageenhancementandsuperresolutiontechniqueforlicenseplaterecognition
_version_ 1718400715612749824