Research on low-light image enhancement based on MER-Retinex algorithm

To solve blurring and poor visual effects after enhancement of low-light images by conventional low-light algorithms, this paper proposes a MER-Retinex (multi-scale expansion reconstruction retinex) algorithm that integrates attention mechanism and multi-scale expansion pyramid reconstruction. It in...

Full description

Saved in:
Bibliographic Details
Published in:Signal, image and video processing image and video processing, 2024-02, Vol.18 (1), p.803-811
Main Authors: Zhou, Rongfeng, Wang, Rugang, Wang, Yuanyuan, Zhou, Feng, Guo, Naihong
Format: Article
Language:English
Subjects:
Algorithms
Blurring
Computer Imaging
Computer Science
Decomposition
Illumination
Image enhancement
Image Processing and Computer Vision
Image reconstruction
Modules
Multilayers
Multimedia Information Systems
Original Paper
Pattern Recognition and Graphics
Perception
Pyramids
Reflectance
Retinex (algorithm)
Signal,Image and Speech Processing
Special effects
Vision
Visual effects
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To solve blurring and poor visual effects after enhancement of low-light images by conventional low-light algorithms, this paper proposes a MER-Retinex (multi-scale expansion reconstruction retinex) algorithm that integrates attention mechanism and multi-scale expansion pyramid reconstruction. It includes two parts: decomposition and enhancement module. In the decomposition module, two U-shaped networks are used to decompose the image into reflectance and illumination, then, use multi-layer convolution to expand the field of perception and improve the ability to decompose the image to obtain reflectance and illumination. In the enhancement module, a U-shaped network is used to fuse multi-scale expansion pyramids with a multi-attention mechanism to enrich image information, increase image brightness and fuse the processed global information with local information to enhance the recovered image details. In the enhanced reconstruction section, super-resolution techniques are used to enhance and denoise image feature details. Experimental analysis of the MER-Retinex algorithm was carried out on the LOL dataset. The PSNR of the algorithm in this paper was 25.26 and the NIQE was 3.43. The algorithm in this paper can effectively solve the problems of blurred images and poor visual effects, and has improved in both subjective perception and objective evaluation indexes.
ISSN:1863-1703
1863-1711
DOI:10.1007/s11760-023-02801-x