A spatially constrained fuzzy hyper-prototype clustering algorithm

We present in this paper a fuzzy clustering algorithm which can handle spatially constraint problems often encountered in pattern recognition. The proposed method is based on the notions of hyperplanes, the fuzzy c-means, and spatial constraints. By adding a spatial regularizer into the fuzzy hyperplane-based objective function, the proposed method can take into account additionally important information of inherently spatial data. Experimental results have demonstrated that the proposed algorithm achieves superior results to some other popular fuzzy clustering models, and has potential for cluster analysis in spatial domain.

► The proposed method addresses how spatially related features can be robustly partitioned. ► The solution is based on the novel combination of the hyperplanes, fuzzy c-means, and spatial constraints. ► A distinct feature is that no prior information is required in the formulation. ► Experimental results have demonstrated the potential of the proposed method.