Order-Statistic Filters in Dynamic Image Sequences
L. Macekova, S. Marchevsky, Cs. Stupak, R. Lukáč · Brno University of Technology Digital Library (Brno University of Technology) · 2000
This paper is concerned with filtering methods in dynamic imagesequences corrupted by impulsive noise. Spatial filters based on orderstatistics are well known. However, image sequences can be consideredas spatiotemporal data that is a time sequence of two-dimensional (2D)images. Thus, in many applications temporal or spatiotemporal filtersachieve well performance of noise suppression. Impulse detector canimprove the obtained results. Two new spatiotemporal structures of SDVdetector are introduced. The analysis of various filtering methods ispresented. The performance of the proposed methods is evaluated throughsubjective and objective criteria, and a new objective criterion wasdeveloped.