SAR image noise reduction processing method based on dictionary learning fusion

Abstract

The present invention provides a SAR image denoising processing method based on dictionary learning fusion, which combines non-subsampling contourlet dictionary learning and K-SVD dictionary learning, and uses translation-invariant non-subsampling contourlet transformation filtering to overcome the contour problem. The defect that wave transformation cannot be translated invariant eliminates the scratch effect of denoising; at the same time, the adaptive K-SVD dictionary learning algorithm is used for denoising, and the dictionary atoms are constantly updated according to the characteristics of the image, which not only suppresses the image well Noise can also better retain important SAR image information such as edges and textures; and further by fusing the two noise reduction effects, the fused image greatly improves the signal-to-noise ratio of the image, and the equivalent of the image The number of views has also been improved to a certain extent, and edge and texture information are also well preserved, without negative effects such as scratches and darkening of image contrast, which significantly improves the overall quality of SAR image noise reduction processing.

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 ...

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

Images