Fuzzy Filters for Noise Reduction in Images

Efficient impulse noise detection method with ANFIS for accurate image restoration

“…For comparison, the corrupted test images are also filtered by using several conventional and state-of-the-art IN removal operators including CWM [4], TSM [5], LUM [6], FSB [15] (fuzzy similarity filter), IFCF [16], MIFCF [16], EIFCF [16], SFCF [17], FIRE [18], PWLFIRE [19], FMF [20,21] (fuzzy median filter), AWFM [22,23], and ATMAV [24]. In order to show performance of the ANFIS with respect to the neural network [31], the NFDMF results are also compared with the neural network detector median filter (NNDMF) results.…”

“…In [22], adaptive weighted fuzzy mean (AWFM) filter which is capable of removing high density Gaussian impulse noise in polluted images was presented. Asymmetrical triangular fuzzy filter with moving average center (ATMAV) was presented in [24]. In a given neighborhood, the ATMAV filter takes into account the deviation of the pixel value with the mean value and replaces the noisy pixel with a fitting output based on triangular membership function.…”

“…Over the last few years, artificial intelligence-based nonlinear techniques such as neural networks and fuzzy systems have been attractive alternatives to classical noise detection and reduction techniques [15][16][17][18][19][20][21][22][23][24][25][26][27][28]. In [16] iterative fuzzy control-based filtering (IFCF) method was presented.…”

Adaptive speckle reduction in ultrasound images using fuzzy logic on Coefficient of Variation

“…s(x, y) = exp − r 2 + s 2 (2K + 1) 2 (16) where R (x, y) and R (x + r, y + s) are center pixel and its neighbouring pixel respectively in a local window of size (2K + 1) × (2K + 1) and r, s ∈ [− K to K]. ı = C ˆ n is an important parameter that distinguishes noisy and edge pixels.…”

“…Nevertheless, calculation of parameters for image fuzzification at every iteration is the limitation of this scheme. Kwan et al [16,17] proposed symmetrical and asymmetrical triangle fuzzy filters based on median and average filters. However, the fuzzy based median or average filters tend to smoothen the fine details causing poor edge preservation.…”