Low-Resolution Image Enhancement using Generative Adversarial Networks

Melvin Ajuluchukwu, Atef Shalan, Lei Chen, Yiming Ji, Emmanuel Balogun

Research output: Contribution to book or proceedingConference articlepeer-review

Abstract

Enhancing low-resolution (LR) images is crucial in the field of machine vision science. Improving the quality of LR images captured by security cameras is indispensable for forensic analysis and identification in surveillance applications. Generative Adversarial Networks (GANs) have emerged as a powerful deep-learning technique to address the super-resolution (SR) challenge inherent in long-range surveillance photos. The primary aim of this study is to enhance low-quality images of highway security surveillance using GANs architecture to optimize the image quality by generating high-resolution (HR) equivalents of the real HR images. The desired images were reconstructed using a dataset and employing Red-Green-Blue (RGB) guided thermal SR-GANs and GANs, along with perceptual loss function techniques. These approaches enhance image quality while preserving important LR image features, thereby reducing blur and glitches associated with image upscaling.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE Annual Congress on Artificial Intelligence of Things, AIoT 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages213-218
Number of pages6
ISBN (Electronic)9798350392296
DOIs
StatePublished - 2024
Event2024 IEEE Annual Congress on Artificial Intelligence of Things, AIoT 2024 - Melbourne, Australia
Duration: Jul 24 2024Jul 26 2024

Publication series

NameProceedings - 2024 IEEE Annual Congress on Artificial Intelligence of Things, AIoT 2024

Conference

Conference2024 IEEE Annual Congress on Artificial Intelligence of Things, AIoT 2024
Country/TerritoryAustralia
CityMelbourne
Period07/24/2407/26/24

Keywords

  • blur
  • forensic analysis
  • image enhancement
  • low-resolution image
  • Super-Resolution Generative Adversarial Network (SRGAN)

Fingerprint

Dive into the research topics of 'Low-Resolution Image Enhancement using Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this