Multi-Resolution Beta-Divergence NMF for Blind Spectral Unmixing
arXiv:2007.03893 · doi:10.1016/j.sigpro.2021.108428
Abstract
Many datasets are obtained as a resolution trade-off between two adversarial dimensions; for example between the frequency and the temporal resolutions for the spectrogram of an audio signal, and between the number of wavelengths and the spatial resolution for a hyper/multi-spectral image. To perform blind source separation using observations with different resolutions, a standard approach is to use coupled nonnegative matrix factorizations (NMF). Most previous works have focused on the least squares error measure, which is the -divergence for . In this paper, we formulate this multi-resolution NMF problem for any -divergence, and propose an algorithm based on multiplicative updates (MU). We show on numerical experiments that the MU are able to obtain high resolutions in both dimensions on two applications: (1) blind unmixing of audio spectrograms: to the best of our knowledge, this is the first time a coupled NMF model is used in this context, and (2) the fusion of hyperspectral and multispectral images: we show that the MU compete favorable with state-of-the-art algorithms in particular in the presence of non-Gaussian noise.
arXiv commentWe have added numerical experiments for the case beta=0, for the Cuprite data set. Paper accepted in Signal Processing
References in corpus (12)
- A convex formulation for hyperspectral image superresolution via subspace-based regularization
- Hyperspectral and Multispectral Image Fusion based on a Sparse Representation
- Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation
- A Variable Splitting Augmented Lagrangian Approach to Linear Spectral Unmixing
- Multispectral and Hyperspectral Image Fusion Using a 3-D-Convolutional Neural Network
- Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
- Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications
- Nonlinear hyperspectral unmixing with robust nonnegative matrix factorization
- Multi-Band Image Fusion Based on Spectral Unmixing
- Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey
- Blind Audio Source Separation with Minimum-Volume Beta-Divergence NMF
- Estimation with Low-Rank Time-Frequency Synthesis Models