Super-resolution of license plate images via character-based perceptual loss

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

Abstract

License Plate Recognition (LPR) is an highly influential problem in computer vision. In this paper, we present a super-resolution model specialized for the license plate images, CSRGAN, trained with a novel character-based perceptual loss. Specifically, we focus on the character-level recognizability of the super-resolved images rather than the pixel-level reconstruction. Experimental results validate the benefits of our proposed method in both quantitative and qualitative aspects. In particular, our method achieves a higher character-level recognition accuracy over the state-of-the-art image super-resolution techniques.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020
EditorsWookey Lee, Luonan Chen, Yang-Sae Moon, Julien Bourgeois, Mehdi Bennis, Yu-Feng Li, Young-Guk Ha, Hyuk-Yoon Kwon, Alfredo Cuzzocrea
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages560-563
Number of pages4
ISBN (Electronic)9781728160344
DOIs
StatePublished - Feb 2020
Event2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020 - Busan, Korea, Republic of
Duration: 19 Feb 202022 Feb 2020

Publication series

NameProceedings - 2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020

Conference

Conference2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020
Country/TerritoryKorea, Republic of
CityBusan
Period19/02/2022/02/20

Keywords

  • Generative
  • License plate recognition
  • Super-resolution

Fingerprint

Dive into the research topics of 'Super-resolution of license plate images via character-based perceptual loss'. Together they form a unique fingerprint.

Cite this