Image noise reduction method and computer readable storage medium

An image noise reduction and image technology, applied in the field of image processing, can solve problems such as unfavorable diagnosis, poor filtering performance, and smear, and achieve the effects of convenient diagnosis, suppression of smear, and suppression of noise

Active Publication Date: 2022-03-15
SHENZHEN ANGELL TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Common X-ray fluoroscopy filters include NLM, BM3D, and bilateral filters. In low-dose cases, the filtering performance is not good.
[0005] Ordinary X-ray fluoroscopy recursive filtering noise reduction method (TilAach.Noise Reduction and ImageEnhancementAlgorithms for Low-Dose X-Ray Fluoroscopy) will have serious smearing problems at low frame rates (<20fps), that is, the previous frame The texture will be superimposed on the current frame, which is not good for diagnosis

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
  • Image noise reduction method and computer readable storage medium
  • Image noise reduction method and computer readable storage medium
  • Image noise reduction method and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Please refer to Figure 2-11 , Embodiment 1 of the present invention is: an image noise reduction method, based on time-domain recursive filtering, which can be applied to noise reduction of X-ray fluoroscopy images, such as figure 2 shown, including the following steps:

[0064] S1: Setting the parameters of the image of the first frame, including setting the output image of the first frame and the filter gain of the first frame.

[0065] Specifically, the input image of the first frame (that is, the image of the first frame) can be directly used as the output image of the first frame, that is, x(1,n)=y(1,n); x(t,n ) represents the output image of the t-th frame, y(t,n) represents the input image of the t-th frame, t represents the serial number of the frame, and n represents the pixel index in the image. For the convenience of expression, n can be omitted.

[0066] It is also possible to use other non-recursive methods to perform special processing on the image of ...

Embodiment 2

[0097] This embodiment is a computer-readable storage medium corresponding to the above-mentioned embodiments, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented:

[0098] Obtain the input image of the current frame and the output image of the previous frame, the input image of the current frame is the image of the current frame;

[0099] calculating the inter-frame grayscale difference between the input image of the current frame and the output image of the previous frame;

[0100] performing truncation processing on the inter-frame grayscale difference according to a preset suppression value and a truncation value;

[0101] Generate the continuity probability curve corresponding to the current frame according to the truncated inter-frame grayscale difference and the preset curve parameters;

[0102] calculating the filter gain of the current frame according to the filter gain of the previous frame and ...

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 an image noise reduction method and a computer-readable storage medium. The method includes: acquiring an input image of a current frame and an output image of a previous frame; calculating the input image of the current frame and the output image of the previous frame The inter-frame grayscale difference of the image; according to the preset suppression value and cut-off value, the inter-frame grayscale difference is truncated; according to the inter-frame grayscale difference after the truncation process and the preset curve parameter, Generate the continuity probability curve corresponding to the current frame; calculate the filter gain of the current frame according to the filter gain of the previous frame and the continuity probability curve corresponding to the current frame; according to the input image of the current frame, the previous frame The output image of the current frame and the filter gain of the current frame are calculated, and the output image of the current frame is calculated to obtain the denoised image of the current frame. The present invention can better suppress the noise in the image without producing obvious smear.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image noise reduction method and a computer-readable storage medium. Background technique [0002] X-Ray fluoroscopy (X-Ray fluoroscopy) images have more and more important values ​​in clinical diagnosis because of their real-time performance. However, the noise of the image is a Poisson distribution noise, and the noise and the signal are related, so many classical algorithms based on the additive Gaussian noise model cannot remove the noise well. [0003] Under the current industry background that requires lower and lower fluoroscopy dose, the noise level of the image will inevitably increase if the fluoroscopy dose is reduced. This is determined by the physical characteristics of X-rays. Therefore, it is more and more urgent to better filter out the noise of low-dose fluoroscopy. [0004] X-ray fluoroscopy filters are more common such as NLM, BM3D and bi...

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): G06T5/00G16H30/20
CPCG06T5/002G16H30/20G06T2207/10116
Inventor 荣繁壮叶超易浩平杨杰
Owner SHENZHEN ANGELL 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