Pareto-based interval type-2 fuzzy c-means with multi-scale JND color histogram for image segmentation

Although the interval type-2 fuzzy c-means clustering algorithm (IT2FCM) can well represent the uncertainty in data, there remain some problems to be solved: how to initialize cluster centers and how to determine fuzzifiers. In order to solve these issues of IT2FCM for color image segmentation, a pareto-based interval type-2 fuzzy c-means with multi-scale just noticeable difference color histogram (PIT2FC-MJND) is proposed in this paper. A multi-scale just noticeable difference (JND) color histogram is firstly constructed by using many distance thresholds and utilized to provide initial cluster centers. Then, a modified type-reduction and de-fuzzification mechanism on this multi-scale JND color histogram is designed for updating membership functions and cluster centers. Moreover, a pareto-based strategy for determining the combination of fuzzifiers is presented by using a global fuzzy compactness function and a fuzzy separation function which are based on the constructed multi-scale JND color histogram. The experimental results on real, Berkeley and Weizmann Images confirm the validity of the proposed approach.