Adaptive Rank-Ordered Mean Filter for Removal of Impulse Noise from Images

This paper presents a new algorithm for detection of fixed-valued and random-valued impulses from images based on locally obtained statistics. By incorporating the rank-conditioned median (RCM) and center-weighted median (CWM) filters into an impulse noise detection framework, an adaptive mechanism is formed for effectively reducing impulse noise while preserving image details. The rank-conditioned mechanism checks whether the central pixel is well-within the ordered data set, while the center-weighted mechanism is to select more appropriate local thresholds. Simulations show that the proposed scheme works well in suppressing both types of impulses at different noise ratios.