Work

Fractional-Order Dynamic Illumination Adjustment for Low-Light Enhancement Using Luminance Segmentation

Year: 2026

Type: article

Abstract: Low-light image enhancement is an important problem in image processing. In this paper, we propose a novel adaptive variational model based on fractional-order gradients for low-light image enhancement. Specifically, the low-light part of the low-light image is enhanced, that is, the contrast of the low-light image is enhanced. The core concept of the proposed technique involves partitioning the image domain into low-light and brighter regions by applying an optimal threshold value. Then, a fitting term is further used for the low-light parts, so that the pixels in the low-light area can be enhanced by adjusting the contrast and brightness parameters. The existence of a minimizer is established under the stated assumptions, and the uniqueness of the solution is proved under the corresponding convexity conditions. An efficient split Bregman method is developed to solve the proposed variational model. Experimental results demonstrate the effectiveness of the proposed method for low-light image enhancement.

Source: Fractal and Fractional

DOI: 10.3390/fractalfract10110755

Authors: Bao Chen, Tianlan Xiong, Juanjuan Gao, Yuchao Tang

Institutions: Nanchang Hangkong University, Guangdong University of Foreign Studies, Guangzhou University

Language: English

Topic: Image Enhancement Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,258

Funders: National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province