An Enhancement Method of Underground Noisy Image Based on Dual Domain Decomposition

An underground image technology, applied in the field of image processing, can solve the problems of poor imaging environment, weak performance, low image contrast, etc., and achieve the effect of image contrast improvement

Active Publication Date: 2022-02-22
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the other types of enhancement algorithms mentioned above, the transformation domain image enhancement algorithm has unique advantages in separation and noise suppression. However, the transformation domain image enhancement algorithm has weak performance in improving image contrast and brightness, and the underground imaging environment is poor, and the image contrast is low. Underground image enhancement algorithms must have a strong ability to improve contrast

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
  • An Enhancement Method of Underground Noisy Image Based on Dual Domain Decomposition
  • An Enhancement Method of Underground Noisy Image Based on Dual Domain Decomposition
  • An Enhancement Method of Underground Noisy Image Based on Dual Domain Decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be described in detail below in conjunction with the accompanying drawings and implementation examples.

[0038] A method for enhancing noise-containing images in underground mines by double-domain decomposition, comprising the following steps:

[0039] The first step: input image r, g, b channel layered decomposition

[0040] Such as figure 1 As shown, the Gaussian filter is used to decompose the input image according to three channels of r, g, and b. The Gaussian filter is a spatial smoothing filter. The template size of the Gaussian kernel function of the Gaussian filter is 15×15, and the variance is 3. In the dotted frame of "image r, g, b channel layered decomposition", the base layer r, g, b channel image by the input image f c ,c∈{r,g,b} and Gaussian kernel function It is obtained by convolution, and the r, g, b channel images of the detail layer are obtained by f c ,c∈{r,g,b} minus yields, namely:

[0041]

[0042] Step 2...

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 dual-domain decomposition method for enhancing noise-containing images in underground mines. The method first uses a Gaussian filter in space to decompose the noise-containing images in underground mines in layers to realize the decoupling of image contrast improvement and noise suppression; The maximum bright channel image of the base layer obtained by the layer is used as the illuminance component estimation of the Retinex model. According to the Retinex enhancement principle, the contrast of the base layer is improved; The shearlet transform domain implements hard threshold shrinkage on the decomposition coefficients to achieve noise suppression in the detail layer. The non-subsampled shearlet inverse transform shrinks the decomposition coefficients to obtain the noise suppression detail layer. Using the same enhancement ratio as the base layer, the noise suppression detail layer is achieved. Enhancement; finally, the fusion enhanced image is obtained by fusing the enhanced base layer and the noise-suppressed enhanced detail layer, and Gamma fine-tuning is performed on the fusion-enhanced image to obtain the final noise-suppressed and contrast-enhanced enhanced image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a dual-domain decomposition method for enhancing noise-containing images in underground mines. Background technique [0002] With the acceleration of the development of smart mines, various image recognition technologies continue to extend to underground mines. However, the imaging environment in underground mines is poor and there are many electromagnetic interferences, resulting in low contrast and rich noise in the collected images. Mine image enhancement and noise suppression have become mine images. Identify and apply the top issues that need to be addressed. [0003] At present, commonly used algorithms for image enhancement include: histogram equalization, histogram regulation, image enhancement algorithm based on physical model, image enhancement algorithm based on partial differential equation and variation, and image enhancement algorithm in change ...

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 Patents(China)
IPC IPC(8): G06T5/00G06T5/50G06V10/30
CPCG06T5/007G06T5/002G06T5/50G06T2207/20064G06T2207/20221G06V10/30
Inventor 田子建王满利张向阳
Owner CHINA UNIV OF MINING & TECH (BEIJING)
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