A sparse representation based compression of fused images using WDR coding

In this paper, a sparse representation based compression of fused images is proposed using MultiResolution Singular Value Decomposition (MSVD). The main idea of this work is to identify significant and less significant details using MSVD. The core information is fused using the absolute maximum rule while the less significant information is fused using sparse representation. The fused significant information is compressed using wavelet difference reduction coding. On the flip side, the fused less significant information is compressed using quantization and Huffman encoding. On the receiver side, the proposed recovery algorithm can be used to obtain the fused image. The superiority of the proposed technique can be analyzed from the comparison of the proposed work with some related work.(c) 2022 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

This paper proposes a sparse representation based compression method for fused images using MultiResolution Singular Value Decomposition (MSVD), which can identify significant and less significant details. The significant information is fused using the absolute maximum rule, while the less significant information is fused using sparse representation. The fused images are compressed using different coding techniques. The proposed technique is superior to some related work, as demonstrated by comparisons.