Local activity indicators for hard-switching adaptive filtering of images with mixed noise

We present a quantitative analysis of several local activity indicator properties and provide comparisons between them: We illustrate that the considered local activity indicators can be applied as adaptation parameters to locally adaptive hard-switching processing (filtering) of images. The cases where images are corrupted with additive or multiplicative noise having different probability density functions and, possibly, spikes are considered. The advantages of the designed adaptive hard-switching filtering algorithms are discussed and demonstrated for simulated data. Recommendations concerning the selection of local activity indicators and threshold values are given. (C) 2001 society of Photo-Optical Instrumentation Engineers.