Unlock instant, AI-driven research and patent intelligence for your innovation.

A Supervised Machine Learning-Based Image-Assisted Denoising Method

A machine learning and image technology, applied in kernel methods, image enhancement, image data processing, etc., can solve the problems of low detail reduction, poor denoising effect, long running time, etc., to save running time and good noise reduction ability. , the effect of removing the noise part

Active Publication Date: 2022-08-02
QINGHAI UNIV FOR NATITIES
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the above-mentioned deficiencies in the prior art, the invention provides an image-assisted denoising method based on supervised machine learning, which solves the problems of poor denoising effect, low detail restoration and long running time in traditional methods.

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
  • A Supervised Machine Learning-Based Image-Assisted Denoising Method
  • A Supervised Machine Learning-Based Image-Assisted Denoising Method
  • A Supervised Machine Learning-Based Image-Assisted Denoising Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The specific embodiments of the present invention are described below to facilitate those skilled in the art to understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes Such changes are obvious within the spirit and scope of the present invention as defined and determined by the appended claims, and all inventions and creations utilizing the inventive concept are within the scope of protection.

[0031] like figure 1 As shown, in one embodiment of the present invention, an image-assisted denoising method based on supervised machine learning includes the following steps:

[0032] S1. Perform non-subsampling contourlet transformation on an image containing noise to obtain a high-frequency sub-band factor and a low-frequency sub-band factor;

[0033] S2. Using the quadratic programming method, a least-squares support vector machine i...

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-assisted denoising method based on supervised machine learning. The non-subsampling contourlet transform method is used to transform the noisy image into multi-scale and multi-directional transform subbands in the Shearlet domain. Low-frequency sub-band factors without noise and high-frequency sub-band factors with noise; through the support vector machine algorithm of least squares method under supervised machine learning, classify the high-frequency sub-band factors that need to preserve edges and textures. factor and the factor to be denoised that need to be denoised, and finally remove the noise by the soft threshold method to obtain the final auxiliary denoised image, which not only has good noise reduction ability, effectively removes the noise part, but also filters out the required image in the image layer by layer. The denoised data ensures image details and saves running time, and has high performance in the field of image processing.

Description

technical field [0001] The invention relates to the field of image signal processing, in particular to an image-assisted denoising method based on supervised machine learning. Background technique [0002] During recording, transmission, processing, and compositing, images are affected by noise, blur, etc., resulting in reduced image quality. Therefore, in the image processing process, denoising is the core content of image processing. The noise part of the noise image and the signal details are scattered in the high frequency region and are not easy to distinguish. However, traditional image-assisted denoising methods have problems such as poor denoising effect, little image detail information, and long time-consuming. Therefore, finding a way to effectively denoise and ensure the details of the image is still the focus of current academic research. SUMMARY OF THE INVENTION [0003] Aiming at the above deficiencies in the prior art, the present invention provides an im...

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): G06T5/00G06V10/764G06V10/70G06K9/62G06N20/10
CPCG06N20/10G06F18/2411G06T5/70
Inventor 李凯勇
Owner QINGHAI UNIV FOR NATITIES