2022
DOI: 10.1049/ipr2.12650
|View full text |Cite
|
Sign up to set email alerts
|

Optimization algorithm for low‐light image enhancement based on Retinex theory

Abstract: To improve the visual quality of low‐light images and discover hidden details in images, an image enhancement algorithm is proposed, which is based on a fast and robust fuzzy C‐means (FRFCM) clustering algorithm combined with Retinex theory. The algorithm is based on Retinex theory to solve the above problems as followings: Firstly, the initial illumination estimation image is constructed by max‐RGB and segmented by FRFCM algorithm. Secondly, initial illumination estimation image and its segmented image linear… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 47 publications
0
3
0
Order By: Relevance
“…Yang [23] To estimate an initial illuminated image, Retinex theory was combined with a fast and robust fuzzy C-means clustering algorithm, followed by segmentation and fusion to enrich the image details.…”
Section: Methods Advantage Disadvantagementioning
confidence: 99%
See 1 more Smart Citation
“…Yang [23] To estimate an initial illuminated image, Retinex theory was combined with a fast and robust fuzzy C-means clustering algorithm, followed by segmentation and fusion to enrich the image details.…”
Section: Methods Advantage Disadvantagementioning
confidence: 99%
“…Lin et al [ 11 ] used the Retinex theory to divide the input image into reflection and illumination components, and they added edge-holding to the illumination component. Yang et al [ 23 ] used Retinex theory in conjunction with a fast and robust fuzzy C-mean clustering algorithm to estimate the initial illumination image and then performed segmentation and fusion to enrich the image’s details. However, due to the lack of a reflectance constraint, these methods tend to amplify potential dense noise or even artifacts in low-illumination images.…”
Section: Related Workmentioning
confidence: 99%
“…For instance, under weak illumination conditions, such as at night or on cloudy days, the light reflected from the surface of objects is generally weak. This often results in images that are characterized by low brightness, low contrast, color distortion, and high noise, as demonstrated in studies [1][2][3]. In addition, for color low-light images, the pixel values are mainly concentrated in a low range, and the gray scale difference of the corresponding pixels between each channel is also very limited, with only a small difference between the maximum and minimum gray scale of the image, a deviation of the overall color layer, and weak edge information, which leads to the difficulty in distinguishing the details of the image when observed by human beings or processed by computers.…”
Section: Introductionmentioning
confidence: 95%