Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance Applications
Vehicle license plate images are often low resolution and blurry because of the large distance and relative motion between the vision sensor and vehicle, making license plate identification arduous. The extensive use of expensive, high-quality vision sensors is uneconomical in most cases; thus, imag...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/4/892 |
| _version_ | 1827756682712711168 |
|---|---|
| author | Mohammad Hijji Abbas Khan Mohammed M. Alwakeel Rafika Harrabi Fahad Aradah Faouzi Alaya Cheikh Muhammad Sajjad Khan Muhammad |
| author_facet | Mohammad Hijji Abbas Khan Mohammed M. Alwakeel Rafika Harrabi Fahad Aradah Faouzi Alaya Cheikh Muhammad Sajjad Khan Muhammad |
| author_sort | Mohammad Hijji |
| collection | DOAJ |
| description | Vehicle license plate images are often low resolution and blurry because of the large distance and relative motion between the vision sensor and vehicle, making license plate identification arduous. The extensive use of expensive, high-quality vision sensors is uneconomical in most cases; thus, images are initially captured and then translated from low resolution to high resolution. For this purpose, several traditional techniques such as bilinear, bicubic, super-resolution convolutional neural network, and super-resolution generative adversarial network (SRGAN) have been developed over time to upgrade low-quality images. However, most studies in this area pertain to the conversion of low-resolution images to super-resolution images, and little attention has been paid to motion de-blurring. This work extends SRGAN by adding an intelligent motion-deblurring method (termed SRGAN-LP), which helps to enhance the image resolution and remove motion blur from the given images. A comprehensive and new domain-specific dataset was developed to achieve improved results. Moreover, maintaining higher quantitative and qualitative results in comparison to the ground truth images, this study upscales the provided low-resolution image four times and removes the motion blur to a reasonable extent, making it suitable for surveillance applications. |
| first_indexed | 2024-03-11T08:28:56Z |
| format | Article |
| id | doaj.art-fe2b9df07e8c4235a10a52a62e0cfa03 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T08:28:56Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-fe2b9df07e8c4235a10a52a62e0cfa032023-11-16T21:55:28ZengMDPI AGMathematics2227-73902023-02-0111489210.3390/math11040892Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance ApplicationsMohammad Hijji0Abbas Khan1Mohammed M. Alwakeel2Rafika Harrabi3Fahad Aradah4Faouzi Alaya Cheikh5Muhammad Sajjad6Khan Muhammad7Faculty of Computers and Information Technology, University of Tabuk, Tabuk 47711, Saudi ArabiaDigital Image Processing Laboratory, Department of Computer Science, Islamia College Peshawar, Peshawar 25000, PakistanFaculty of Computers and Information Technology, University of Tabuk, Tabuk 47711, Saudi ArabiaFaculty of Computers and Information Technology, University of Tabuk, Tabuk 47711, Saudi ArabiaFaculty of Computers and Information Technology, University of Tabuk, Tabuk 47711, Saudi ArabiaThe Software, Data and Digital Ecosystems (SDDE) Research Group, Department of Computer Science, Norwegian University of Science and Technology (NTNU), 2815 Gjøvik, NorwayDigital Image Processing Laboratory, Department of Computer Science, Islamia College Peshawar, Peshawar 25000, PakistanVisual Analytics for Knowledge Laboratory (VIS2KNOW Lab), Department of Applied Artificial Intelligence, School of Convergence, College of Computing and Informatics, Sungkyunkwan University, Seoul 03063, Republic of KoreaVehicle license plate images are often low resolution and blurry because of the large distance and relative motion between the vision sensor and vehicle, making license plate identification arduous. The extensive use of expensive, high-quality vision sensors is uneconomical in most cases; thus, images are initially captured and then translated from low resolution to high resolution. For this purpose, several traditional techniques such as bilinear, bicubic, super-resolution convolutional neural network, and super-resolution generative adversarial network (SRGAN) have been developed over time to upgrade low-quality images. However, most studies in this area pertain to the conversion of low-resolution images to super-resolution images, and little attention has been paid to motion de-blurring. This work extends SRGAN by adding an intelligent motion-deblurring method (termed SRGAN-LP), which helps to enhance the image resolution and remove motion blur from the given images. A comprehensive and new domain-specific dataset was developed to achieve improved results. Moreover, maintaining higher quantitative and qualitative results in comparison to the ground truth images, this study upscales the provided low-resolution image four times and removes the motion blur to a reasonable extent, making it suitable for surveillance applications.https://www.mdpi.com/2227-7390/11/4/892AISRGANimage super-resolutiongeneratordiscriminatorgenerative adversarial networks |
| spellingShingle | Mohammad Hijji Abbas Khan Mohammed M. Alwakeel Rafika Harrabi Fahad Aradah Faouzi Alaya Cheikh Muhammad Sajjad Khan Muhammad Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance Applications Mathematics AI SRGAN image super-resolution generator discriminator generative adversarial networks |
| title | Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance Applications |
| title_full | Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance Applications |
| title_fullStr | Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance Applications |
| title_full_unstemmed | Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance Applications |
| title_short | Intelligent Image Super-Resolution for Vehicle License Plate in Surveillance Applications |
| title_sort | intelligent image super resolution for vehicle license plate in surveillance applications |
| topic | AI SRGAN image super-resolution generator discriminator generative adversarial networks |
| url | https://www.mdpi.com/2227-7390/11/4/892 |
| work_keys_str_mv | AT mohammadhijji intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications AT abbaskhan intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications AT mohammedmalwakeel intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications AT rafikaharrabi intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications AT fahadaradah intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications AT faouzialayacheikh intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications AT muhammadsajjad intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications AT khanmuhammad intelligentimagesuperresolutionforvehiclelicenseplateinsurveillanceapplications |