Image fusion method based on sparse dictionary learning and shear waves

Abstract

The invention discloses an image fusion method based on sparse dictionary learning and shear waves. The image fusion method based on sparse dictionary learning and shearing waves comprises the following steps: step 1, shearing wave transformation is carried out on two registered source images to obtain corresponding low-frequency sub-band coefficients and high-frequency sub-band coefficients; step2, the low-frequency sub-band coefficients are subjected to sparse dictionary learning and fused to obtain low-frequency fusion coefficients; step 3, the high-frequency sub-band coefficients are fused by adopting an absolute value and a maximum value method of the directional sub-band under the same scale to obtain the high-frequency fusion coefficients; step 4, shear wave inverse transformationis performed on the low-frequency fusion coefficient and the high-frequency fusion coefficient to obtain a fusion image. The invention can decompose the image into more directional sub-bands, providesmore directional sub-band information for subsequent image fusion processing, can accurately capture the edge information in the image, and finally improves the image fusion quality.

Description

technical field [0001] The present invention relates to the technical field of image fusion, and more specifically relates to an image fusion method based on sparse dictionary learning and shear wave, which is applied in the fields of military reconnaissance, medical diagnosis and remote sensing. Background technique [0002] The development of sensor technology presents the characteristics of diversified imaging mechanisms, complex working environment, diversified working bands and synergistic work of functional modules, which greatly expands the depth and breadth of human understanding of the world. New sensors such as forward-looking infrared, laser imaging radar, synthetic aperture radar, optical coherence tomography, and optical multi-aperture imaging have realized the expression of multiple modes of the natural world, and are widely used in military and civilian fields. [0003] Image fusion can achieve a more comprehensive and accurate expression of the scene content ...

AI Technical Summary

Problems solved by technology

Multi-scale transform decomposition tools include pyramid transform, wavelet transform, curvelet transform, contourlet transform, and non-subsampled contourlet transform. However, the sparse representation ability of the above methods is poor, and the decomposed image orientation subband information is limited.

The sparse dictionary learning fusion method can accurately fit the data, and the sparser the decomposition coefficient, the better it can reflect the inherent characteristics of the signal. It can improve the sparsity of low-frequency sub-bands through sparse representation, thereby improving the fusion effect, but sparse representation cannot accurately represent high-frequency Information, that is, analysis data that cannot be multi-scale and multi-directional. If high-frequency data is fused using sparse representation, there will be a problem of high-frequency information loss.

Images