Enhancement method and device for low light image

A low-light, image technology, applied in the field of image processing, can solve problems such as halo generation and noise increase
CN109255756BInactive Publication Date: 2020-12-29PEKING UNIV
8 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Patent Type
Patents(China)
Current Assignee / Owner
PEKING UNIV
Publication Date
2020-12-29
Estimated Expiration
Not applicable ยท inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a low-light image enhancement method and device. The method includes: calculating the enhancement gradient of at least one channel image of the original image; establishing an objective function for solving the brightness component and reflection component of the at least one channel image; The objective function of the image is solved to obtain the brightness component and reflection component of at least one channel image; the enhanced image of at least one channel is calculated based on the brightness component and reflection component of the at least one channel image; the enhanced image of each channel is synthesized, Or the enhanced image of a certain channel is combined with the original image of other channels to form an enhanced low-light image. Since the reflection component and brightness component are not solved in the logarithmic domain in the objective function, the noise in the image is effectively suppressed, and the 1 norm is constrained when constraining the gradient of the brightness component, so it can effectively avoid image enhancement. The phenomenon of haloing in the result.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a method and device for enhancing a low-light image. Background technique

[0002] Low-light images refer to images captured under low-light conditions, which usually contain different degradation phenomena. Examples include poor visibility, low contrast, and high noise. Although professional equipment and advanced photography skills can reduce these degradations to a certain extent, noise in low-light conditions is inevitable and currently cannot be solved at the hardware level. Therefore, for ordinary consumers, it is very critical and practical to enhance low-light images with denoising effects through software means.

[0003] In the prior art, the method based on retinal technology has a better effect for enhancing low-light images. It assumes that the image can be split into two components, reflectance and luminance. The single-retina ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More