An Effective Adaptive Nonlinear Filter for Removing High Density Impulse Noises in Gray-Scale Images

Digital images are often distorted by Impulse noise during the process of analog-to-digital conversion, transmission and storage in the physical medias. This type of error certainly changes the properties of some of the pixels while some of the other pixels remain unchanged. In order to remove impulse noise and enhance the distorted image quality, we have tested the number of nonlinear filters and their limitations and we have proposed a new efficient adaptive nonlinear filtering algorithm. This method removes or effectively suppresses the impulse noises in the gray-scale images while preserving the image edges information and enhancing the image quality. The proposed method is a spatial domain approach and uses the 3×3 kernel window to filter the signal based on the correct selection of neighbourhood values to obtain the median per window. The method chosen in this work is based on a functional level 2n +1 window that makes the selection of the normal median easier, since the number of elements in the window is odd. The median so obtained is set as the efficient value for filtering. Suppose the median is an impulse, a more representative value is pursued from the neighbourhood values and used as the median value. The performance of the proposed efficient adaptive nonlinear filter has been evaluated using MATLAB, simulations on gray-scale digital images that have been subjected to high density of corruption with impulse noise as high as 90 %. The results reveal the effectiveness of our proposed algorithm when compared with existing vector, standard and adaptive median filtering algorithms.