Fuzzy adaptive anisotropic filter for medical images

Demirci, Recep/0000-0002-3278-0078WOS: 000279613000007An adaptive anisotropic diffusion filter for images is proposed in this paper. First, the gradient of an image was calculated by a novel fuzzy-rule-based gradient operator. Accordingly, the centre of gravity of a histogram of the gradient image was estimated and it was assigned as an edge threshold. In conventional anisotropic filters, the conduction coefficients have to be selected by an operator. However, in this study, the centre of gravity of the histogram was assigned as the conduction coefficient of the anisotropic filter. Consequently, an adaptive anisotropic image filter which automatically sets its conduction coefficient without user intervention was developed. The image filter achieved was tested with various medical images