A Type-2 Fuzzy Subtractive Clustering Algorithm

摘要

The paper introduces a new approach to subtractive clustering algorithm (SC) with the fuzzifier parameter m which controls the clustering results in SC. And to manage the uncertainty of the parameter m, we have expanded the SC algorithm to interval type-2 fuzzy subtractive clustering algorithms (IT2-SC) using two fuzzifiers parameters m_1 and m_2 which creates a footprint of uncertainty (FOU) for the fuzzifier. The experiments are done based on image segmentation with the statistics show that the depends greatly on the parameter m of SC and stability and accuracy of our IT2-SC.