Abstract | ||
---|---|---|
Blurred image restoration is a longstanding and critical research problem. We addressed this problem using Expectation Maximization (EM) based approach in wavelet domain. The sparsity property of wavelet coefficients is modeled using the class of Gaussian Scale Mixture (GSM), which represents the heavy-tailed statistical distribution, suitable for natural images. The underlying original image and noise parameters are estimated by alternating EM iterations based on available and hidden data sets, where regularization is introduced using an intermediate variable. Although similar formulations have been proposed before but the resulting optimization problems have been computationally demanding, where our formulation is simple to implement and converge in few iterations. Simulation results are presented to demonstrate the quality of our method both visually and in terms of signal to noise ratio improvement. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICIP.2013.6738122 | Image Processing |
Keywords | Field | DocType |
image restoration,optimisation,EM-based hybrid Fourier-wavelet image deconvolution algorithm,Gaussian scale mixture,blurred image restoration,expectation maximization based approach,heavy-tailed statistical distribution,signal to noise ratio,sparsity property,wavelet domain,Blur Restoration,Gaussian Scale Mixture,Image Deconvolution | Pattern recognition,Expectation–maximization algorithm,Computer science,Signal-to-noise ratio,Deconvolution,Algorithm,Fourier transform,Regularization (mathematics),Artificial intelligence,Image restoration,Optimization problem,Wavelet | Conference |
ISSN | Citations | PageRank |
1522-4880 | 1 | 0.35 |
References | Authors | |
18 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Muhammad Hanif | 1 | 207 | 25.54 |
Abd-Krim Seghouane | 2 | 78 | 12.27 |