Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SAR image noise reduction processing method based on dictionary learning fusion

A dictionary learning and image noise reduction technology, which is applied in image data processing, image enhancement, image analysis, etc., can solve the problem that the effect of SAR image noise reduction is not ideal, and achieve the effect of improving the signal-to-noise ratio.

Active Publication Date: 2018-07-27
苏州深蓝空间遥感技术有限公司 +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the above-mentioned defects existing in the prior art, in order to solve the problem that the effect of SAR image denoising processing in the prior art is not ideal enough, the present invention provides a SAR image denoising processing method based on dictionary learning and fusion, which combines non-downstream Sampling contourlet dictionary learning and K-SVD dictionary learning form a multi-dictionary learning fusion noise reduction process for SAR images, which can greatly improve the signal-to-noise ratio of SAR images, and at the same time preserve the edge and texture information of SAR images well, thus Improving the quality of SAR image noise reduction processing

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
  • SAR image noise reduction processing method based on dictionary learning fusion
  • SAR image noise reduction processing method based on dictionary learning fusion
  • SAR image noise reduction processing method based on dictionary learning fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0099] This embodiment utilizes a given SAR image (such as image 3 shown), first add Gaussian noise, the SAR image after adding Gaussian white noise is as follows Figure 4 As shown, the noise standard deviation σ=25 of the SAR image after the noise addition, the peak signal-to-noise ratio PSNR=20.1891 of the SAR image after the noise addition; The final SAR image is denoised, and the processing flow is: use the non-subsampled contourlet transform algorithm (NSCT) to denoise the noisy SAR image; then, the sparse representation of the noisy SAR image based on the K-SVD dictionary , represent the image as a sparse linear combination of K-SVD atoms, this sparse representation can effectively reflect the characteristics of the SAR image, and then use the Orthogonal Matching Pursuit Algorithm (OMP) for sparse coding, and then continuously update the dictionary atoms to solve the optimization problem Solve and reconstruct the SAR image to achieve the purpose of denoising the SAR 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 provides a fused SAR image noise reduction processing method based on dictionary learning. The method utilizes translation invariant non-subsampled contourlet transform filtering to overcome the defect that non-subsampled contourlet transform cannot realize translation invariance and eliminate the scratch effect for noise reduction by means of combination of the non-subsampled contourlet dictionary learning and K-SVD dictionary learning, and at the same time utilizes an adaptive K-SVD dictionary learning algorithm to perform noise reduction and continuously updates the dictionary atoms according to the characteristics of images, not only being able to restrain the image noise, but also being able to preferably reserve the important SAR image information, such as edges and texture; and the method further fuses the two noise reduction effects, so that the signal to noise ratio of the image is greatly improved after fusion of the images; the equivalent number of looks of the image is also improved; the edge and texture information is preferably reserved; the negative influence, such as scratches and darkening of the image contrast, does not appear; and therefore, the comprehensive quality for SAR image noise reduction processing is significantly improved.

Description

technical field [0001] The invention relates to the technical field of microwave remote sensing image processing, in particular to a SAR image noise reduction processing method based on dictionary learning fusion. Background technique [0002] Synthetic Aperture Radar (SAR) technology is a pulse radar technology that uses mobile radar mounted on satellites or aircraft to obtain radar target images in high-precision geographic areas. Synthetic Aperture Radar Auto Targets Recognition (SAR-ATR) has important application value in many geographic information analysis technology fields. [0003] Coherent speckle noise is an inherent characteristic of SAR images. The coherent speckles scattered randomly in SAR images will be mixed with smaller ground objects, which seriously affects the image quality and makes it difficult for the automatic interpretation of SAR images. Therefore, in SAR image processing, image noise suppression becomes the key, and it is also the technical basis ...

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): G06T5/00
CPCG06T5/002G06T5/50G06T2207/10044G06T2207/20081G06T2207/20221
Inventor 张新征汪勇常云鹤吴奇政
Owner 苏州深蓝空间遥感技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products