A low-light image enhancement method based on coefficient of variation and structure-preserving
CN114170104BActive Publication Date: 2025-04-04CHONGQING UNIV
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202111505539.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-10
- Publication Date
- 2025-04-04
- Estimated Expiration
- 2041-12-10
AI Technical Summary
Technical Problem
The existing low-light image enhancement algorithms are difficult to effectively retain structural information and smooth lighting information, and local artifacts are prone to occur.
Method used
Using a method based on the coefficient of variation, the structure weight map and texture weight map are adaptively extracted, combined with the P-norm constraint and block coordinate descent method, the image is decomposed into reflection components and illumination components, and gamma correction is performed to obtain an enhanced image.
Benefits of technology
It realizes effective removal of artifacts while maintaining the structure, improves the contrast and brightness of low-light images, and improves the overall quality of the image.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN114170104B_ABST
Abstract
The present invention discloses a low-light image enhancement method based on coefficient of variation and structure preservation, comprising: obtaining a weight map for a low-light image using the coefficient of variation, and adaptively extracting a structure weight map and a texture weight map; utilizing the structure weight map and the texture weight map to enhance the low-light image gradient as a priori of a reflection component; utilizing a priori estimation of a bright channel as a priori of an illumination component; utilizing a P-norm to constrain the smoothness of illumination; utilizing a block coordinate descent method to obtain a reflection component and an illumination component; performing gamma correction on the illumination component, and multiplying the component pixel by pixel with the reflection component to obtain an enhanced image; the dark area of the low-light image can be significantly enhanced, and the edge information of the final image obtained is complete, without redundant noise, and with less color distortion.
Need to check novelty before this filing date? Find Prior Art