Spatially Adaptive Image Restoration Using Fuzzy Punctual Kriging

We present a general formulation based on punctualkriging and fuzzy concepts for image restoration in spatial domain.Gray-level images degraded with Gaussian white noise have beenconsidered. Based on the pixel local neighborhood, fuzzy logic has beenemployed intelligently to avoid unnecessary estimation of a pixel. Theintensity estimation of the selected pixels is then carried out byemploying punctual kriging in conjunction with the method of Lagrangemultipliers and estimates of local semi-variances. Application of sucha hybrid technique performing both selection and intensityestimation of a pixel demonstrates substantial improvement in the imagequality as compared to the adaptive Wiener filter and existingfuzzy-kriging approaches. It has been found that these filters achievenoise reduction without loss of structural detail information, asindicated by their higher structure similarity indices, peak signal tonoise ratios and the new variogram based quality measures.