Low-light-level image enhancement method based on MSR theory and exposure fusion

A low-light image and image technology, applied in the field of image processing, can solve the problems of structure destruction, preservation, inability to measure the richness of local details, etc., and achieve the effect of high contrast

Active Publication Date: 2019-11-08
XIDIAN UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The shortcomings of this system are: in its local processor, the weight of the Gaussian kernel cannot be adjusted according to the richness of local details, and in the global processor, the overall structure is greatly damaged
The disadvantage of this method is that the structural processing is not considered in the process of detail processing, resulting in serious structural damage
The shortcomings of this method are: it is mainly used to extract the defect features of the real defect topography map of integrated circuits, and its application range is relatively narrow. The weight of the Gaussian kernel can be adjusted by the degree of richness, and the overall structure of the image and the brightness of the image cannot be maintained during the detail enhancement process at the same time.
[0006]In short, in the process of image enhancement for low-light images in the prior art, the maintenance of the overall structure cannot be taken into account in the implementation of the detail processing method

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
  • Low-light-level image enhancement method based on MSR theory and exposure fusion
  • Low-light-level image enhancement method based on MSR theory and exposure fusion
  • Low-light-level image enhancement method based on MSR theory and exposure fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] The importance of images in modern society is becoming more and more important, and the requirements for the clarity of images in modern society are also increasing. However, due to the low-light environment is a relatively common shooting environment, photos taken at night or in rainy days, or even in backlight environments have low-light specialty. Low-light images have problems such as indistinct details, low contrast, severe color distortion, and are easily disturbed by noise. In image applications, low-light image enhancement must be used to improve image quality, so the research results of low-light image enhancement will have broad applications in computer and vision applications such as surveillance systems, aerial photography, military monitoring, remote sensing imaging systems, and intelligent transportation systems. prospect.

[0027] In the existing technology, the overall structure is greatly damaged during the implementation process. In its local processo...

Embodiment 2

[0037] The low-light image enhancement method based on MSR and exposure fusion is the same as that in Embodiment 1. The local detail processing operator based on the MSR theory described in step 2 of the present invention is used to process the original image to obtain the detail processing image, which specifically includes the following steps:

[0038] 2.1 Convert the original image from the daily three primary color RGB space to the HSV space, and propose the original image V component I V , the V component is the brightness component, which contains all the details of the original image.

[0039] 2.2 Divide the V component of the original image into N blocks, where N is the total number of blocks, and N is any positive integer. In this example, N=6.

[0040] 2.3 The present invention defines a concept to measure the richness of detail of each block, that is, the richness of regional details r, and calculates the richness of regional details r of the i-th block of the V com...

Embodiment 3

[0057] The low-light image enhancement method based on MSR and exposure fusion is the same as in Embodiment 1-2. For an image, it can be divided into detail-rich areas and detail-unrich areas according to local characteristics. In detail-rich areas, there are more details and higher information entropy. High, there are many edges, the difference between pixels is very large, the change is drastic, and it is difficult to observe the noise. In the non-detailed area, the details are less, and it is easier to observe the difference between small pixel values, and the visibility of noise is higher. In order to accurately distinguish the detail-rich area from the detail-unrich area, the present invention adopts the calculation formula of area detail richness to distinguish the detail-rich area from the non-detail area.

[0058] The formula for calculating the richness of regional details described in step 2.3b:

[0059]

[0060] Among them, r i is the regional detail richness o...

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 discloses a low-light-level image enhancement method based on an MSR theory and exposure fusion, and solves the problems of damage to the overall structure of an image, excessive enhancement and the like in low-light-level image enhancement. The method comprises the steps of inputting an original image and extracting a V component of the original image; processing the V component byusing a local detail processing operator to obtain a detail processing graph; processing the V component by using an integral structure preserving operator to obtain a structure processing graph; defining the V component of the original image as a correction processing image; combining the three processing images by adopting an exposure fusion method to obtain an enhanced result image; and transferring from the HSV space to the RGB space for display to obtain an enhanced result graph. According to the invention, the regional detail richness based on the information entropy is used for accurately measuring the detail richness of the image, three different Gaussian kernel weights are adaptively calculated according to the regional detail richness, and three processing images are merged by combining an exposure fusion method. According to the method, image detail enhancement and structure and brightness maintenance are considered while the low-light-level image is enhanced. The method canbe applied to the fields of remote sensing, military, industry and medicine.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to image enhancement in the technical field of low-light image processing, in particular to a low-light image enhancement method based on MSR (Multi-scale Retinex, multi-scale Retinex) theory and exposure fusion. The invention can perform contrast enhancement processing on the low-light images obtained in the fields of remote sensing, military affairs, industry, medicine and the like. Background technique [0002] With the continuous development of information technology, digital images have become an important means for human beings to obtain information, and are widely used in communication, military, medical and other fields. The low-light environment is a relatively common shooting environment. Photos taken at night or on a rainy day, or even in a backlit environment, have low-light characteristics. Using MSR theory can effectively solve the problems of loss of d...

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): G06T5/50G06T5/20G06T5/00
CPCG06T5/50G06T5/20G06T5/007G06T5/002G06T2207/20221G06T2207/20016
Inventor 王俊平张宏杰赵璐璐李栋凯张亚琼周勇魏旗暴婉婷李艳波魏书蕾李金山
Owner XIDIAN UNIV
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