Sparse Signal Subspace Decomposition Based on Adaptive Over-complete Dictionary
This is an incremental improvement for image processing, specifically in denoising tasks.
The paper tackles the problem of image denoising by proposing the Sparse Signal Subspace Decomposition (3SD) method, which uses an over-complete dictionary and a novel frequency-based criterion to preserve details and suppress noise, demonstrating high performance in this application.
This paper proposes a subspace decomposition method based on an over-complete dictionary in sparse representation, called "Sparse Signal Subspace Decomposition" (or 3SD) method. This method makes use of a novel criterion based on the occurrence frequency of atoms of the dictionary over the data set. This criterion, well adapted to subspace-decomposition over a dependent basis set, adequately re ects the intrinsic characteristic of regularity of the signal. The 3SD method combines variance, sparsity and component frequency criteria into an unified framework. It takes benefits from using an over-complete dictionary which preserves details and from subspace decomposition which rejects strong noise. The 3SD method is very simple with a linear retrieval operation. It does not require any prior knowledge on distributions or parameters. When applied to image denoising, it demonstrates high performances both at preserving fine details and suppressing strong noise.