An adaptive low-light image enhancement method using frequency domain characteristics

By decomposing the low-illumination image into illumination map and reflection map, and using frequency domain characteristics and noise distribution theory for adaptive adjustment and noise suppression, the low-illumination image quality problem is solved, and efficient image enhancement effect is achieved.

CN117196982BActive Publication Date: 2025-08-22XIDIAN UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311160895.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-08
Publication Date
2025-08-22
Estimated Expiration
2043-09-08

Smart Images

  • Figure CN117196982B_ABST
    Figure CN117196982B_ABST
Patent Text Reader

Abstract

The present invention discloses an adaptive low-light image enhancement method utilizing frequency domain characteristics, comprising: decomposing a low-light image into an illumination map and a reflectance map; adaptively adjusting the illumination map using an adaptive illumination adjustment method based on frequency domain characteristics to obtain an adjusted illumination map; performing noise suppression on the adjusted illumination map based on the independence of noise distribution on the image to obtain a noise-suppressed illumination map; performing noise suppression on the reflectance map based on the independence of noise distribution on the image to obtain a noise-suppressed reflectance map; and fusing the noise-suppressed illumination map and the noise-suppressed illumination map to obtain an enhanced low-light image. The method of the present invention realizes adaptive adjustment of image illumination and simultaneously globally enhances image details, thereby improving the overall quality of the enhanced image and achieving an efficient image enhancement effect.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Self-supervision low-illumination image enhancement and denoising method based on deep learning

    CN112308803A

  • Image enhancement and noise adaptive removal method for low-illumination environment in building

    CN112614063A