Multi-level adaptive switching filters for highly corrupted images

Abstract

The performance of a switching filter is highly dependent on its detection accuracy. Inspired by adaptive median filter methodology, this paper proposes a multi-level adaptive switching filter (MASF) for the recovery of highly corrupted images. In particular, the adaptive technique is employed in all the detective, edge-preserving and restorative stages in order to improve noise discrimination and suppression simultaneously. Most critical design parameters in the proposed algorithm, e.g., the limit of window-expansion size and the noise range, are self-adaptive so as to retain simple implementation and high computational efficiency. Furthermore, several effective modifications on both stages of the MASF, such as the convergence factor, switching initialization and spatial adaptive weighting, are also introduced in order to provide better and more robust results. Monte-Carlo simulations show that the MASF outperforms many existing state-of-the-art algorithms in terms of both visual and quantitative results.