Abstract
In this letter, we propose a new despeckling method based on two-step sparse decomposition. First, the grouping by block matching method identifies similar image patches and stacks them into a group, so that the group of similar patches are mostly homogeneous, which is suitable for the followed sparse decomposition method. And then, the proposed two-step sparse decompositions are applied to each group. The first sparse decomposition is a classical sparse representation to obtain an overcomplete dictionary and the sparse coefficients. The second sparse decomposition is a subspace decomposition over the dictionary. We proposed a measurement from the sparse coefficients as the criterion to identify a principal signal subdictionary. Finally, the image is reconstructed by the linear combination of the atoms of the principal subdictionary. The proposed method takes benefits from learned overcomplete dictionary, which fully explores details and from the principal subdictionary, which reduces strong noises. Experimental results demonstrate the efficiency of the proposed method to denoise synthetic aperture radar images. Our method can achieve high performances in terms of both structure details preservation and speckle noise reduction.
| Original language | English |
|---|---|
| Pages (from-to) | 1263-1267 |
| Number of pages | 5 |
| Journal | IEEE Geoscience and Remote Sensing Letters |
| Volume | 14 |
| Issue number | 8 |
| DOIs | |
| State | Published - Aug 2017 |
Funding
This work was supported by the National Natural Science Foundation of China under Grant 60872131.
Keywords
- Despeckling
- overcomplete dictionary
- sparse decomposition
- subspace decomposition
- synthetic aperture radar (SAR) images
Indexed by
- EI
- Scopus
- SCIE
Fingerprint
Dive into the research topics of 'Two-Step Sparse Decomposition for SAR Image Despeckling'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver