CNN-based low-illumination image enhancement method with color recovery and edge sharpening effects

A technology for image enhancement and color restoration, applied in the field of image processing, to achieve the effect of improving color distortion and improving detail expression ability

Pending Publication Date: 2021-08-13
ZHEJIANG UNIV OF TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies of the prior art, the present invention proposes a CNN-based low-illuminance image enhancement method with color restoration and edge sharpening effects, in order to compensate and calibrate the contrast details in the enhancement process, and improve the image enhancement. Color distortion, effectively enhance the edge details of the image, and improve the visual effect of the image

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
  • CNN-based low-illumination image enhancement method with color recovery and edge sharpening effects
  • CNN-based low-illumination image enhancement method with color recovery and edge sharpening effects
  • CNN-based low-illumination image enhancement method with color recovery and edge sharpening effects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the purpose, advantages and technical characteristics of the present invention clearer and more thorough, the present invention will be further described below in conjunction with the accompanying drawings.

[0036] refer to Figure 1 ~ Figure 4 , a CNN-based low-light image enhancement method with color restoration and edge sharpening effects, in order to improve the color distortion after image enhancement, effectively enhance the detail information of the image, and improve the visual effect of the image. The method includes The following steps:

[0037] Step 1: Construction of the data set: The n (n takes 485) pairs in the public "low light pairing" data set LOL containing a large number of low / normal light image pairs captured from real scenes and the RAISE data set were selected. m (m takes 1000) original images as the training data set by adjusting the parameters to obtain m pairs of normal images / synthetic low-light images;

[0038] Step 2: Refe...

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

A CNN (Convolutional Neural Network)-based low-illumination image enhancement method with color recovery and edge sharpening effects is improved on the basis of an original RetinexNet algorithm, and comprises the following steps: firstly, inputting a low-illumination image and a normal image which are paired into a decomposition network to obtain respective reflection components and illumination components; and then carrying out denoising processing on the reflection component of the low-illumination image and then carrying out sharpening processing to obtain a final reflection component; introducing a color loss function at the enhancement network, and inputting the illumination component of the low-illumination image to obtain an adjusted illumination component; finally, carrying out element-by-element multiplication on the two adjusted components to obtain an enhancement result of the original low-illumination image. Compared with the original method, the color distortion phenomenon after image enhancement is improved, the detail information of the image is effectively enhanced, and the visual effect of the image is improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a CNN-based low-illuminance image enhancement method with color restoration and edge sharpening effects. Background technique [0002] In recent years, image enhancement has developed rapidly as a basic research work in the field of computer vision. Among them, low-light image enhancement is one of the important research topics in the field of image enhancement. Low-light image enhancement refers to the restoration of degraded images generated by visual sensors in low-light environments through image processing, pattern recognition and other technologies. [0003] The image enhancement method based on Retinex theory is a popular low-light image processing method at present. Among them, Retinex based on the center / surround type has been widely used, mainly including SSR, MSR and MSRCR. Such algorithms are prone to problems such as halo, blurred details, noise amplification, and ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06N3/04G06N3/08G06T7/90
CPCG06T5/005G06T5/003G06T7/90G06N3/08G06T2207/20172G06T2207/10068G06N3/045
Inventor 李胜陈铭何熊熊李静喻东司鹏
Owner ZHEJIANG 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