Low light image enhancement algorithm based on improved multi-objective grey wolf optimization with detail feature enhancement

This article aims to enhance low-light images by proposing a novel algorithm called MoGDF. It departs from the traditional approach of using deep learning with low-light and normal images as training data. Instead, exposure images at five different exposure scales are generated using a proposed mode...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of King Saud University. Computer and information sciences Ročník 35; číslo 8; s. 101666
Hlavní autoři:	Yanming Hui, Wang Jue, Bo Li, Ying Shi
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Springer 01.09.2023
Témata:	Exposure Prediction Model Feature Extraction Network Low-light Image Enhancement Multi-Objective Grey Wolf Algorithm
ISSN:	1319-1578
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	This article aims to enhance low-light images by proposing a novel algorithm called MoGDF. It departs from the traditional approach of using deep learning with low-light and normal images as training data. Instead, exposure images at five different exposure scales are generated using a proposed model called EIPM, which consists of an improved Gamma function. Then it introduces a feature extraction network called FMEM, which leverages an improved PFPN structure to enhance the fusion of multi-scale information and strengthen the connection between high-level and low-level semantic information. Finally, it optimizes the fusion weights using an improved multiple-objective grey wolf optimization algorithm with comprehensive improvements in the convergence factor updating strategy, adaptive inertia weight strategy, and individual position strategy. The experiments show that the MoGDF outperforms the current state-of-the-art algorithms in terms of color restoration and detail preservation, and has significant advantages in objective and subjective evaluation metrics, with improvements of 5.69%, 2.60%, 1.11%, and 6.67% in PSNR, SSIM, NIQE, and LPIPS, respectively.
ISSN:	1319-1578
DOI:	10.1016/j.jksuci.2023.101666