Fuzzy anisotropic diffusion for speckle filtering

Abstract

An anisotropic diffusion filter contoled by fuzzy rules is presented. The proposed filter is based in the Perona-Malik technique, using a fuzzy reasoning to calculate de diffusion coefficient which controls the whole diffusion. The method has the advantage that it can be used for both smoothing and noise cleaning, as well as edge enhancement. This new aproach also allows ut to model the diffusion process through a rule base to have a better performance. Some examples are given to ilustrate the effectiveness of the proposed technique.

Image reconstruction for positron emission tomography using fuzzy nonlinear anisotropic diffusion penalty

“…n Àx uþ1;v j 2 ; 1 2 jx uþ1;vþ1 À x uþ1;v j 2 g: The purpose for us to define the variable D2 using such a strategy is that we prefer consider the contribution of all pixels gray levels rather than that of some pixels gray levels as proposed in [2]. Similar calculations are made for west, north, and south directions.…”

“…Table 1 shows this fuzzy AD decision table: if ... and ... then rules. The content of the decision table can be modified according to the characteristic of noise [2]. If FP-EM reconstructed images are characterized by a high level of noise, a larger diffusion coefficient is applied that emphasizes the smoothing inside the regions of the image.…”

“…Aja et al [2] thought that these diffusion coefficients could be replaced by some fuzzy variables. The input parameters are the linguistic variables D1 and D2, and the output parameter is diffusion coefficient C F (F 2{W,N,S,E}).…”

Fuzzy based diffusion coefficient function in anisotropic diffusion for impulse noise removal

“…Various fuzzy logic based methods [11][12] have also been efficiently applied for removal of impulsive noise. Fuzzy rules have also been used as a powerful tool in image enhancement and de-noising through anisotropic diffusion [11][12][13]. Aja et al [13] introduced an anisotropic diffusion filter by calculating diffusion coefficients with the help of fuzzy inference rule instead of using edge stopping function.…”

“…Fuzzy rules have also been used as a powerful tool in image enhancement and de-noising through anisotropic diffusion [11][12][13]. Aja et al [13] introduced an anisotropic diffusion filter by calculating diffusion coefficients with the help of fuzzy inference rule instead of using edge stopping function. The intensity difference of each pixel with its eight neighboring pixels was calculated and the output diffusion coefficients were mapped as a membership function of the intensity difference from 0 to 1.…”