Clustered Multitask Nonnegative Matrix Factorization for Spectral Unmixing of Hyperspectral Data
This work addresses spectral unmixing for hyperspectral data analysis, which is an incremental improvement in a domain-specific area.
The authors tackled spectral unmixing in hyperspectral imagery by proposing a clustered multitask nonnegative matrix factorization algorithm, which showed advantages over other methods in experiments on synthetic and real datasets using metrics like spectral angle distance and reconstruction error.
In this paper, the new algorithm based on clustered multitask network is proposed to solve spectral unmixing problem in hyperspectral imagery. In the proposed algorithm, the clustered network is employed. Each pixel in the hyperspectral image considered as a node in this network. The nodes in the network are clustered using the fuzzy c-means clustering method. Diffusion least mean square strategy has been used to optimize the proposed cost function. To evaluate the proposed method, experiments are conducted on synthetic and real datasets. Simulation results based on spectral angle distance, abundance angle distance and reconstruction error metrics illustrate the advantage of the proposed algorithm compared with other methods.