A HMMF filter for removal of noise from digital images

In recent years, technological development has significantly improved in analyzing digital images. Noise reduction is an important operation in image processing. Removing impulse noise from digital image is a very active research area in digital image processing. This paper proposes a new non linear hybrid filtering technique which is the hybridization of hybrid max filter and hybrid min filter (HMMF) for the removal of impulse noise from digital images. Experimental results show the proposed method is very effective to filter salt-and-pepper noise. The measurement of noise reduction is difficult and there is no unique algorithm available to measure noise reduction of digital images. So the quality of the noise reduction in images is measured by the statistical quantity measures: Root Mean Square Error (RMSE) and Peak Signal-to-Noise Ratio (PSNR). The performance of this filter on images tainted with different noises of various noise levels is compared with Wiener filtering technique.