Towards intuitionistic fuzzy image processing

This paper discusses the issue of applying the theory of intuitionistic fuzzy sets in the field of image processing. In order to carry out this task, we have to find intuitive ways to interpret and describe the inherent ambiguity and vagueness carried by the image itself in terms of the elements of intuitionistic fuzzy sets theory. We consider the problem of constructing the intuitionistic fuzzy set corresponding to a digital image, by exploiting the inherent imprecision or/and imperfection of information originating out of the imaging and acquisition chain. This action involves the definition of suitable membership and non-membership functions, by treating the term "brightness" of a gray level in a "qualitative" rather than a "quantitative" way. To model the hesitancy present in digital images, the notion of fuzzy histogram is used based on fuzzy numbers. Finally, experimental results using real-world images, demonstrate the ability of the proposed scheme to model the indeterminacy associated with image pixels.