Image thresholding using type-2 fuzzy c-partition entropy and particle swarm optimization algorithm

The imprecision in an image can be expressed in terms of ambiguity of belonging of a pixel in the image or the bottom (if it is black or white), or at the in-definition of the form and the geometry of a region in the image, or the combination of the two previous factors. The fuzzy c-partition entropy approach for threshold selection is one of the best image thresholding techniques, but its complexity increases with the number of thresholds. In this paper, a multi-level thresholding method for image segmentation using type-2 fuzzy c-partition entropy is presented. Type-2 fuzzy sets represent fuzzy sets with fuzzy membership values. The procedure for finding the optimal combination of all the fuzzy parameters is implemented by a particle swarm optimization algorithm. Experimental results reveal that the proposed image thresholding approaches has good performances for images with low contrast and grayscale ambiguity.