Semantic-guided dark light image enhancement method

An image enhancement and image technology, applied in the field of image processing, can solve the problems that dark light images cannot reveal details, strong imaging noise, and cannot maintain naturalness, etc.

Active Publication Date: 2020-06-16
HEFEI UNIV OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, imperfect brightness conditions are often encountered in everyday life
For example, in cases where weak light sources are insufficient to illuminate the entire scene, the resulting image is usually very dark and may contain strong imaging noise
In this case, the visual quality of low-l

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Semantic-guided dark light image enhancement method
  • Semantic-guided dark light image enhancement method
  • Semantic-guided dark light image enhancement method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] A semantically guided low-light image enhancement method, comprising the following steps:

[0032] S10, converting the original dark-light RGB image into an HSV color space image;

[0033] S20. Using the fusion enhancement model to enhance the brightness of the V channel in the HSV color space image, to obtain the V channel after the image brightness is enhanced;

[0034] The fusion enhancement model is:

[0035] I E =I⊙(1-M)+I ini ⊙ M

[0036] Among them, I E Indicates the enhanced image, ⊙ indicates pixel-by-pixel multiplication, I indicates the original dark-light image, I ini Represents the initial enhanced image, and M represents the fusion weight image that can perceive illumination and specific semantic information at the same time, that is, M is composed of perceptual brightness image M L and perceptual semantic image M s The brightness of the two parts is merged;

[0037] The original enhanced image I ini The steps to obtain are:

[0038] According to...

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

PUM

No PUM Login to view more

Abstract

The invention provides a semantic-guided dark light image enhancement method, which belongs to the technical field of image processing, and comprises the following steps: S10, converting an original dark light RGB image into an HSV color space image, S20, enhancing the brightness of a V channel in the HSV color space image by using a fusion enhancement model to obtain a V channel after image brightness enhancement, and S30, converting the V channel after image brightness enhancement and the H channel and the S channel in the HSV color space image back to a RGB color space to obtain a brightness enhanced RGB image. The semantic-guided dark light image enhancement method can improve the visibility of image contents in a dark light image so as to reveal details hidden in the dark and can maintain the visual naturalness of the image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a semantic-guided dark-light image enhancement method. Background technique [0002] In recent years, with the rapid development of smart phones, satisfactory images can usually be obtained through handheld mobile devices. However, imperfect brightness conditions are often encountered in everyday life. For example, where weak light sources are insufficient to illuminate the entire scene, the resulting image is usually very dark and may contain strong imaging noise. In this case, the visual quality of low-light images is usually unsatisfactory. In particular, dark-light images cannot reveal details hidden in the dark. In the prior art, computer vision and image processing are performed on dark-light images. Although the processed images improve visibility, they cannot maintain visual naturalness. [0003] Therefore, there is an urgent need for a low-light image enhance...

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

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T5/00
CPCG06T5/00G06T2207/10004G06T2207/20221G06T2207/20192G06T2207/20024G06T2207/20084
Inventor 郝世杰郭艳蓉洪日昌汪萌
Owner HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap