Combining Pseudo-median filter and median filter to improve performance

Despite many of the same properties between standard median filter (SM) and Pseudo-median filter (PM), SM can remove impulses completely but PM not. However, PM can be more efficiently calculated which is very important for processing data online in WSN. In order to synthesize the advantages of performance of PM and SM, an improved method combined the advances of PM and SM is proposed in this paper. A soft-switching scheme based on noise detection is developed to select the appropriate filter for each processing. In the noise detection each sample is classified to contained impulse or normal by increment contrasts of latest two outputs and between the current sample and the latest. Then SM and PM are alternatively used to process the impulsive samples and the normal. The simulation results and calculation complexity analysis show the combined algorithm attenuates impulses more efficiently than PM and can be more easily calculated than SM. So it can be seen as an alternative of high efficiency for applications in wireless sensor network.