Certain analysis of interval type 2 Fuzzy logic for image Processing applications

Abstract

Domain knowledge of real life problems are often uncertain newlineimprecise and vague therefore that creates difficulty in decision making newlinewhile solving by conventional approaches Among the various methods of newlinehandling uncertainties fuzzy image processing has received considerable newlineattention in the literature for several decades Fuzzy logic FL explores newlinehuman reasoning power using linguistic terms which are modeled as Type 1 newlineFuzzy Sets T1FSs and represented by Membership Functions MFs newlineHowever the MFs of T1FSs are crisp and cannot tackle all kinds of newlineUncertainties Introducing Type 2 Fuzzy Logic T2FL an extension of newlineType 1 Fuzzy Logic simplifies the problems where the MFs are themselves newlinefuzzy with three dimensional representations newlineA number of papers that exist in the literature claim that the newlineperformance of Type 2 Fuzzy Logic System T2FLS is better than Type 1 newlineFuzzy Logic System T1FLS under various conditions environments newlineInterval Type 2 Fuzzy Logic IT2FL is the special case of T2FL The newlineresearchers have shown that the computational cost is high in T2FLS Hence newlineIT2FLS is more commonly seen in the literature due to the fact that the newlinecomputations are more manageable In this dissertation the research activities newlineare focused on the IT2FLS Basically image processing encounters newlineuncertainty and imprecision e g to determine whether a pixel is an edgepixel newlineor not or whether a pixel is contaminated with noise or not Another newlineexample concerns similarity measures which measure the degree of similarity newlinebetween two images which are similar to each other newline