A Novel Single Fuzzifier Interval Type-2 Fuzzy C-Means Clustering with Local Information for Land-Cover Segmentation

Abstract

In the process of land cover segmentation from remote sensing image, there are some uncertainties such as 'significant difference in class density', 'different objects with same spectrum', and 'same object with different spectra'. Existing fuzzy c-means clustering is not sufficient to describe the high-order fuzzy uncertainties and cannot achieve accurate segmentation. Type-2 fuzzy set is perfect for handling with interclass multiple uncertainties, and clustering algorithm can suppress the noise of remote sensing image effectively by incorporating local information. Therefore, on the basis of integrating local information, this article proposes a robust single fuzzifier interval type-2 fuzzy local C-means clustering based on adaptive interval-valued data for land cover segmentation. First, interval-valued data modeling is performed for remote sensing data, and remote sensing features are represented as interval-valued vectors, and the robust interval-valued distance measure that can maximize the distance between interval-valued numbers is used to generate an interval type-2 fuzzy set through robust fuzzy clustering. Second, this article adopts an efficient type reduction method to seek equivalent type-1 fuzzy set adaptively, and realizes the segmentation of land cover by the principle of maximum type-1 fuzzy membership. The test results of multispectral remote sensing images show that the segmentation performance of this proposed algorithm outperforms existing state of the art adaptive interval type-2 fuzzy clustering algorithms, and it is beneficial to the interpretation of remote sensing image.