Impulsive Noise Removal by Adaptive Mathematical Morphology

In this work, an approach to the problem of impulsive noise removal in gray scale images is presented. We describe two models of adaptive mathematical morphology that improve the classical mathematical morphology in the removal of impulsive noise. The proposed method adjust the structuring elements to the local context of the image. The comparison with classical mathematical morphology denoising technique shows that the new approach better removes the salt and pepper noise, while preserves image details.