DMCA
A Dictionary Learning Approach for Poisson Image Deblurring (2013)
Cached
Download Links
| Citations: | 5 - 0 self |
BibTeX
@MISC{Ma13adictionary,
author = {Liyan Ma and Lionel Moisan and Jian Yu and Tieyong Zeng},
title = { A Dictionary Learning Approach for Poisson Image Deblurring},
year = {2013}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The restoration of images corrupted by blur and Poisson noise is a key issue in medical and biological image processing. While most existing methods are based on variational models, generally derived from a Maximum A Posteriori (MAP) formulation, recently sparse representations of images have shown to be efficient approaches for image recovery. Following this idea, we propose in this paper a model containing three terms: a patch-based sparse representation prior over a learned dictionary, the pixel-based total variation regularization term and a data-fidelity term capturing the statistics of Poisson noise. The resulting optimization problem can be solved by an alternating minimization technique combined with variable splitting. Extensive experimental results suggest that in terms of visual quality, PSNR value and the method noise, the proposed algorithm outperforms state-of-the-art methods.
Keyphrases
dictionary learning approach poisson image deblurring poisson noise maximum posteriori visual quality pixel-based total variation regularization term data-fidelity term patch-based sparse representation biological image processing method noise key issue optimization problem state-of-the-art method variational model extensive experimental result efficient approach variable splitting image recovery alternating minimization technique sparse representation learned dictionary psnr value
