Image fusion by combining multiwavelet with nonsubsampled direction filter bank

2015 ◽  
Vol 21 (8) ◽  
pp. 1977-1989 ◽  
Author(s):  
Geng Peng ◽  
Zhengyou Wang ◽  
Shuaiqi Liu ◽  
Shanna Zhuang
Author(s):  
Liu Xian-Hong ◽  
Chen Zhi-Bin

Background: A multi-scale multidirectional image fusion method is proposed, which introduces the Nonsubsampled Directional Filter Bank (NSDFB) into the multi-scale edge-preserving decomposition based on the fast guided filter. Methods: The proposed method has the advantages of preserving edges and extracting directional information simultaneously. In order to get better-fused sub-bands coefficients, a Convolutional Sparse Representation (CSR) based approximation sub-bands fusion rule is introduced and a Pulse Coupled Neural Network (PCNN) based detail sub-bands fusion strategy with New Sum of Modified Laplacian (NSML) to be the external input is also presented simultaneously. Results: Experimental results have demonstrated the superiority of the proposed method over conventional methods in terms of visual effects and objective evaluations. Conclusion: In this paper, combining fast guided filter and nonsubsampled directional filter bank, a multi-scale directional edge-preserving filter image fusion method is proposed. The proposed method has the features of edge-preserving and extracting directional information.


2013 ◽  
Vol 694-697 ◽  
pp. 2003-2008
Author(s):  
Ming Hong Dai

The paper introduces Laplace pyramid, Ridgelet and Curvelet principle, structure and methods, and their denoising experimental studies. It also introduces the traditional direction filter of principle, structure and methodology, and the simulation experiments show that its image denoising PSNR is slightly lower than wavelet but denoising image visual quality is better than former. To that end, proposed a new direction filters that uniform direction filter banks and non-uniform direction filters, proved filter passband condition and related design and implementation issues were discussed. nonlinear experiment shows that the new direction filter bank was better than the wavelet.


Sign in / Sign up

Export Citation Format

Share Document