MULTI-SCALE RETINEX-UNET FOR ENHANCEMENT OF LOW LIGHT WEAK CONTRAST IMAGES

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteur principal: Journal of Theoretical and Applied Information Technology
Format: Recurso digital
Langue:anglais
Publié: Zenodo 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866901900891258880
author Journal of Theoretical and Applied Information Technology
author_facet Journal of Theoretical and Applied Information Technology
contents <p>The enhanced quality of images is crucial in the realm of image processing applications. However, images captured in low-light environments often suffer from poor contrast and noise, leading to a loss of detailed information. To address this challenge, we propose a Multi-Scale RETINEX-UNET (MSR-UNET) model for low-light weak contrast (LLWC) image enhancement. This novel approach integrates a modified U-Net architecture with an improved multi-scale Retinex (IMSR) model, aiming to preserve natural colors while enhancing visual quality. The proposed model is validated using the Renoir dataset, and its effectiveness is measured through PSNR (34.3 dB) and SSIM (99%). Compared to conventional enhancement techniques, our model outperforms existing methods by effectively reducing noise while maintaining structural details. This study advances deep learning-based image enhancement and sets a new benchmark for LLWC image processing<span>.</span></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18109258
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle MULTI-SCALE RETINEX-UNET FOR ENHANCEMENT OF LOW LIGHT WEAK CONTRAST IMAGES
Journal of Theoretical and Applied Information Technology
Image Enhancement, Convolutional Neural Networks, Grey Level Co-occurrence Matrix, U-Net, Multi-Scale Retinex, Deep Learning
<p>The enhanced quality of images is crucial in the realm of image processing applications. However, images captured in low-light environments often suffer from poor contrast and noise, leading to a loss of detailed information. To address this challenge, we propose a Multi-Scale RETINEX-UNET (MSR-UNET) model for low-light weak contrast (LLWC) image enhancement. This novel approach integrates a modified U-Net architecture with an improved multi-scale Retinex (IMSR) model, aiming to preserve natural colors while enhancing visual quality. The proposed model is validated using the Renoir dataset, and its effectiveness is measured through PSNR (34.3 dB) and SSIM (99%). Compared to conventional enhancement techniques, our model outperforms existing methods by effectively reducing noise while maintaining structural details. This study advances deep learning-based image enhancement and sets a new benchmark for LLWC image processing<span>.</span></p>
title MULTI-SCALE RETINEX-UNET FOR ENHANCEMENT OF LOW LIGHT WEAK CONTRAST IMAGES
topic Image Enhancement, Convolutional Neural Networks, Grey Level Co-occurrence Matrix, U-Net, Multi-Scale Retinex, Deep Learning
url https://doi.org/10.5281/zenodo.18109258