A multi-source image fusion algorithm based on gradient regularized convolution sparse representation

Abstract

Image fusion based on the sparse representation (SR)has become the primary research direction of the transform domain method. However, the SR-based image fusion algorithm has the characteristics of high computational complexity and neglecting the local features of an image, resulting in limited image detail retention and a high registration misalignment sensitivity. In order to overcome these shortcomings and the noise existing in the image of the fusion process, this paper proposes a new signal decomposition model, namely the multi-source image fusion algorithm of the gradient regularization convolution SR (CSR). The main innovation of this work is using the sparse optimization function to perform two-scale decomposition of the source image to obtain high-frequency components and low-frequency components. The sparse coefficient is obtained by the gradient regularization CSR model, and the sparse coefficient is taken as the maximum value to get the optimal high frequency component of the fused image. The best low frequency component is obtained by using the fusion strategy of the extreme or the average value. The final fused image is obtained by adding two optimal components. Experimental results demonstrate that this method greatly improves the ability to maintain image details and reduces image registration sensitivity.

Medical Image Fusion for Brain Tumor Diagnosis Using Effective Discrete Wavelet Transform Methods

“…Furthermore, the lack of local image features in SR-based image fusion leads to low detail and registration misalignment sensitivity. To address these issues, a study [25] introduced gradient regularization convolution SR multi-source image fusion. The highand low-frequency image components were separated.…”

A content-aware correlation filter with multi-feature fusion for RGB-T tracking

“…Algorithms related to RGB-T tracking fall into the following three categories [9]: (i) sparse representation model based trackers; (ii) correlation filter (CF) based trackers; (iii) deep learning based trackers. Due to the strong anti-noise and anti-error capabilities, sparse representation models have been successfully applied to many image processing tasks [10], which are extensively used in target tracking to fuse multiple features, such as multiple sparse representation models [11,12], collaborative representation models [13] and collaborative discriminant learning [14].…”

Hybrid double branch image registration algorithm

“…Heterogeneous image fusion is helpful to realize multimodal fusion, but the primary task of fusion is to complete multisource image registration. 8,9 For the work of image registration, there have been many experts and scholars to study, and now we summarize as follows. In 2004, Lowe 10 proposed a scale-invariant feature transformation (SIFT) method to describe local features between images, mainly through constructing feature pyramids for Gaussian blur and iteration.…”

“…At present, there are many research directions of heterogeneous image fusion, such as infrared and visible image fusion, 1 over- and underexposed image fusion, 2 multifocus image fusion, 3 – 5 multispectral image fusion, 6 , 7 etc. Heterogeneous image fusion is helpful to realize multimodal fusion, but the primary task of fusion is to complete multisource image registration 8 , 9 …”