Type-2 fuzzy image enhancement: Fuzzy rule based approach

Abstract

Image enhancement methods are classified as a group of image processing techniques that receive an image as an input and produce a modified image as an output. There is much effort in literature to propose an efficient enhancing method, but as there are many uncertainties in images, there is no general method. Type-2 fuzzy set theory, by providing quantitative tools to empower the machine to mimic human reasoning, is able to provide effective method for this purpose. In this paper, a new enhancement method based on Type-2 fuzzy rule based systems is proposed and its performance in detecting noise pixels and improving image quality is then evaluated using four images corrupted with pre-defined noise types. Four Magnetic Resonance Images are also used to show the ability of the proposed method in real world applications. The results show that the proposed method can efficiently reduce the noise pixels and improve the image quality.