Hierarchical Clustering of Hyperspectral Images using Rank-Two Nonnegative Matrix Factorization

In this paper, we use two simple tools, namely, convex geometry and rank-two nonnegative matrix factorizations, to design a hierarchical clustering algorithm for high-resolution hyperspectral images. The proposed method can also be used as an endmember extraction algorithm. The effectiveness of this approach is illustrated on several synthetic and real-world hyperspectral images.