Two-Dimensional Sparse LMS for Image Denoising

摘要

In this paper we propose a new two-dimensional (2D) zero-attracting least-mean-square (ZA-LMS) based adaptive filter by applying the recently proposed ZA-LMS algorithm for image denoising. The proposed algorithm is applied along both horizontal and vertical directions. Two configurations of data reuse are used to compare the performance and the computational complexity of the 2D conventional LMS algorithm with the proposed one. The simulation results have shown that the proposed 2D ZA-LMS algorithm has similar results as those of the 2D LMS algorithm and it has the benefit of lower computational complexity.