SEGMENTATION OF GRAYSCALE LOW-CONTRAST IMAGES USING FUZZY TRANSFORMS OF TYPE-2

Segmentation of low-contrast grayscale images is a rather complex task due to the lack of a priori information about the location and characteristics of objects of interest that can be compared with noise. To solve this problem, various fuzzy algorithms based on the processing of membership functions to fuzzy sets describing the analyzed properties are currently often used. The paper proposes the algorithm for segmenting halftone images based on the iterative application of type-1 and type-2 fuzzy transformations. The presented algorithm provides sufficient image segmentation for visual analysis, without allowing excessive detailing, and has a small number of control parameters that do not require lengthy tuning. Unlike the fuzzy clustering algorithms, it does not use the fuzzy cluster center matrix, which reduces the computational load. Experimental results are presented on the example of real grayscale medical images segmentation.