A salt & pepper noise fast filtering algorithm for grayscale images based on neighborhood correlation detection

A salt & pepper noise fast filtering algorithm for grayscale images based on neighborhood correlation detection is presented. By utilizing a 4×4 pixel template, the algorithm can discriminate and filter various patterns of salt & pepper noise spots or blocks within 2×2 pixel size range. In contrast with many kinds of median filtering algorithm, which may cause image blurring, it has much higher edge-preserving ability. Furthermore, this algorithm is able to synchronously reflect image quality via amount, location and density statistics of salt & pepper noise spots and make good sense to guide parameter selection for imaging systems.