Abstract
In this paper, a quantitative evaluation of some noise reduction methods is presented. It first classifies the existing local noise reduction techniques by the use of neighbors and statistics and proposes some new filtering techniques. Subsequently, five performance evaluation criteria including processing time, mean distortion, mean busyness, stability, and correct processing ratio are discussed. By using these performance evaluation criteria, an experiment that involves four factors (test image, noise, mask size, and iteration) was designed to evaluate the performance of the local noise reduction methods. The results indicate that some new local noise reduction techniques have performance better than that of the standard existing techniques under certain criteria. © 1992.