A New Cutset-type Kernelled Possibilistic C-Means Clustering Segmentation Algorithm Based on SLIC Super-pixels

Abstract

The kernelled possibilistic C-means clustering algorithm (KPCM) can effectively cluster hyper-sphere data with noise and outliers by introducing the kernelled method to the possibilistic C-means clustering (PCM) algorithm. However, the KPCM still suffers from the same coincident clustering problem as the PCM algorithm due to the lack of between-class relationships. Therefore, this paper introduces the cut-set theory into the KPCM and modifies the possibilistic memberships in the iterative process. Then a cutset-type kernelled possibilistic C-means clustering (CKPCM) algorithm is proposed to overcome the coincident clustering problem of the KPCM. Simultaneously a adaptive method of estimating the cut-set threshold is also given by averaging inter-class distances. Additionally, a cutset-type kernelled possibilistic C-means clustering segmentation algorithm based on the SLIC super-pixels (SS-C-KPCM) is also proposed to improve the segmentation quality and efficiency of the color images. Several experimental results on artificial data sets and image segmentation simulation results prove the excellent performance of the proposed algorithms in this paper.