Role of hybrid switching filter in image denoising - a comparative study

A new fast and reliable hybrid switching impulse noise filter is proposed for highly corrupted images, especially biomedical images. A combination of switching mean and median filtering technique is used to remove impulse noise from corrupted images. This efficient filtering technique is implemented as a two stage algorithm: In the first stage, identification of corrupted pixels that are to be filtered are perfectly detected into a flag image using an iterative fixed sized smaller window approach; In the second stage, using the detected flag image, the pixels to be modified are identified and corrected by the proposed hybrid filter. Experimental results have shown that the proposed algorithm performs far more superior than many of the traditional median filtering and mean filtering techniques reported so far. Since biomedical images are having salt and pepper like structures in it, the ability of the proposed filter to distinguish it from actual noise has been checked. The Peak Signal to Noise Ratio (PSNR) of the filtered image using the proposed technique is much higher than that of the filtered images obtained by the existing mean and median filtering techniques.