A switching median–mean filter for removal of high-density impulse noise from digital images

A new, efficient switching median–mean filter is proposed to remove high density impulse noise from digital images. The proposed method consists of detection and filtering stages. The pixels that are labeled noise-free in the detection stage remain unchanged and the noisy-pixels are replaced by the reference image based the proposed filter with 3 × 3 window. The simulation results show that the proposed filter outperforms some existing methods, both in vision and quantitative measurements. Moreover, our method is not only efficient to remove high density impulse noise and preserve the details in the image, but also possess a short processing time.