The effect of shape and weight towards the performance of Simple Adaptive Median filter in reducing impulse noise level from digital images

Recently, Simple Adaptive Median (SAM) filter has been introduced for the purpose of reducing the impulse noise level in digital images. SAM filter, which uses square filter as its basis, has an ability to change the size of the filter, spatially, based on the approximated local noise level. This paper investigates the effect of shape and weight into the performance of SAM filter in terms of quality improvement, and also execution time. In this work, SAM filter has been compared with its three new derivatives. These three new methods are Circular SAM (CSAM), Weighted SAM (WSAM), and Weighted CSAM (WCSAM). For the purpose of evaluation, fifty test images of size 1600 × 1200 pixels have been used as the test images. The results show that the performance of these methods is almost identical. All methods successfully restore the images corrupted up to 95% of impulse noise. Circular filter and weighting process slightly improve the performance of SAM. However, circular filter dramatically increases the processing time due to its complicated implementation.