Image denoising via weight regression

The core of image denoising is making a trade-off between removing noise and preserving details of noised image. To remove noise, the denoising algorithm based on K-SVD is employed in this paper. Though the power of such denoising algorithm has been verified by a mount of experiments, many meaningful details of noised image cannot be well maintained. To preserve details of noised image, therefore, local structure information of noised image which is described by the steering kernel is considered in image denoising. In fact, a weighted regression method where the weights are defined by the steering kernel is used to recover the meaningful details of noised image. Experimental results have shown that more meaningful details of noised image are preserved by the proposed algorithm.