Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number
Low-resolution images can be reconstructed into high-resolution images using the Super-resolution Convolution Neural Network (SRCNN) algorithm. This study aims to improve the vehicle license plate number's recognition accuracy by generating a high-resolution vehicle image using the SRCNN. The r...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Diponegoro University
2020-10-01
|
Series: | Jurnal Teknologi dan Sistem Komputer |
Subjects: | |
Online Access: | https://jtsiskom.undip.ac.id/index.php/jtsiskom/article/view/13726 |
id |
doaj-e7c1d09efd05449cbda4cfac3c2b4afd |
---|---|
record_format |
Article |
spelling |
doaj-e7c1d09efd05449cbda4cfac3c2b4afd2021-10-02T15:10:50ZengDiponegoro UniversityJurnal Teknologi dan Sistem Komputer2338-04032020-10-018430431010.14710/jtsiskom.2020.1372612840Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate numberWindra Swastika0Ekky Rino Fajar Sakti1Mochamad Subianto2Fakultas Sains dan Teknologi, Universitas Ma Chung, IndonesiaProgram Studi Teknik Informatika, Universitas Ma Chung, IndonesiaFakultas Sains dan Teknologi, Universitas Ma Chung, IndonesiaLow-resolution images can be reconstructed into high-resolution images using the Super-resolution Convolution Neural Network (SRCNN) algorithm. This study aims to improve the vehicle license plate number's recognition accuracy by generating a high-resolution vehicle image using the SRCNN. The recognition is carried out by two types of character recognition methods: Tesseract OCR and SPNet. The training data for SRCNN uses the DIV2K dataset consisting of 900 images, while the training data for character recognition uses the Chars74 dataset. The high-resolution images constructed using SRCNN can increase the average accuracy of vehicle license plate number recognition by 16.9 % using Tesseract and 13.8 % with SPNet.https://jtsiskom.undip.ac.id/index.php/jtsiskom/article/view/13726rekonstruksi citrapengenalan pelat nomorspnetsrcnnsuper resolutiontesseract ocr |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Windra Swastika Ekky Rino Fajar Sakti Mochamad Subianto |
spellingShingle |
Windra Swastika Ekky Rino Fajar Sakti Mochamad Subianto Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number Jurnal Teknologi dan Sistem Komputer rekonstruksi citra pengenalan pelat nomor spnet srcnn super resolution tesseract ocr |
author_facet |
Windra Swastika Ekky Rino Fajar Sakti Mochamad Subianto |
author_sort |
Windra Swastika |
title |
Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number |
title_short |
Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number |
title_full |
Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number |
title_fullStr |
Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number |
title_full_unstemmed |
Vehicle images reconstruction using SRCNN for improving the recognition accuracy of vehicle license plate number |
title_sort |
vehicle images reconstruction using srcnn for improving the recognition accuracy of vehicle license plate number |
publisher |
Diponegoro University |
series |
Jurnal Teknologi dan Sistem Komputer |
issn |
2338-0403 |
publishDate |
2020-10-01 |
description |
Low-resolution images can be reconstructed into high-resolution images using the Super-resolution Convolution Neural Network (SRCNN) algorithm. This study aims to improve the vehicle license plate number's recognition accuracy by generating a high-resolution vehicle image using the SRCNN. The recognition is carried out by two types of character recognition methods: Tesseract OCR and SPNet. The training data for SRCNN uses the DIV2K dataset consisting of 900 images, while the training data for character recognition uses the Chars74 dataset. The high-resolution images constructed using SRCNN can increase the average accuracy of vehicle license plate number recognition by 16.9 % using Tesseract and 13.8 % with SPNet. |
topic |
rekonstruksi citra pengenalan pelat nomor spnet srcnn super resolution tesseract ocr |
url |
https://jtsiskom.undip.ac.id/index.php/jtsiskom/article/view/13726 |
work_keys_str_mv |
AT windraswastika vehicleimagesreconstructionusingsrcnnforimprovingtherecognitionaccuracyofvehiclelicenseplatenumber AT ekkyrinofajarsakti vehicleimagesreconstructionusingsrcnnforimprovingtherecognitionaccuracyofvehiclelicenseplatenumber AT mochamadsubianto vehicleimagesreconstructionusingsrcnnforimprovingtherecognitionaccuracyofvehiclelicenseplatenumber |
_version_ |
1716854382945894400 |