Morphological signal adaptive median filter for still image and image sequence filtering

A novel extension of the classical signal-adaptive median filter (SAM) is proposed in this paper, namely the morphological signal-adaptive median filter (MSAM). Three modifications are introduced in the SAM filter aiming at: (1) enhancing the SAM impulse detection mechanism so that it also detects randomly-valued impulses, (2) employing an anisotropic window adaptation based on binary morphological erosions/dilations with predefined structuring sets and (3) extending its design for its application to image sequences as well. Its performance has been tested for noise suppression in both still images and image sequences. Its robustness against a wide variety of noise distributions as well as its superiority to the classical SAM filter are proved judging from both objective (SNR, MAE) and subjective (perceived image quality) criteria.