scholarly journals Clustered multitask non-negative matrix factorization for spectral unmixing of hyperspectral data

2019 ◽  
Vol 13 (02) ◽  
pp. 1 ◽  
Author(s):  
Sara Khoshsokhan ◽  
Roozbeh Rajabi ◽  
Hadi Zayyani
Keyword(s):  
Matrix Factorization ◽  
Hyperspectral Data ◽  
Spectral Unmixing ◽  
Non Negative Matrix Factorization

scholarly journals Using a Panchromatic Image to Improve Hyperspectral Unmixing

2020 ◽  
Vol 12 (17) ◽  
pp. 2834
Author(s):  
Simon Rebeyrol ◽  
Yannick Deville ◽  
Véronique Achard ◽  
Xavier Briottet ◽  
Stephane May
Keyword(s):  
Matrix Factorization ◽  
State Of The Art ◽  
Hyperspectral Data ◽  
Spectral Unmixing ◽  
Endmember Extraction ◽  
Local Approach ◽  
Hyperspectral Unmixing ◽  
Panchromatic Image ◽  
Art Methods ◽  
Non Negative Matrix Factorization

Hyperspectral unmixing is a widely studied field of research aiming at estimating the pure material signatures and their abundance fractions from hyperspectral images. Most spectral unmixing methods are based on prior knowledge and assumptions that induce limitations, such as the existence of at least one pure pixel for each material. This work presents a new approach aiming to overcome some of these limitations by introducing a co-registered panchromatic image in the unmixing process. Our method, called Heterogeneity-Based Endmember Extraction coupled with Local Constrained Non-negative Matrix Factorization (HBEE-LCNMF), has several steps: a first set of endmembers is estimated based on a heterogeneity criterion applied on the panchromatic image followed by a spectral clustering. Then, in order to complete this first endmember set, a local approach using a constrained non-negative matrix factorization strategy, is proposed. The performance of our method, in regards of several criteria, is compared to those of state-of-the-art methods obtained on synthetic and satellite data describing urban and periurban scenes, and considering the French HYPXIM/HYPEX2 mission characteristics. The synthetic images are built with real spectral reflectances and do not contain a pure pixel for each endmember. The satellite images are simulated from airborne acquisition with the spatial and spectral features of the mission. Our method demonstrates the benefit of a panchromatic image to reduce some well-known limitations in unmixing hyperspectral data. On synthetic data, our method reduces the spectral angle between the endmembers and the real material spectra by 46% compared to the Vertex Component Analysis (VCA) and N-finder (N-FINDR) methods. On real data, HBEE-LCNMF and other methods yield equivalent performance, but, the proposed method shows more robustness over the data sets compared to the tested state-of-the-art methods. Moreover, HBEE-LCNMF does not require one to know the number of endmembers.

Empirical Factors Affecting the Quality of Non-Negative Matrix Factorization of Mammalian Cell Raman Spectra

2017 ◽  
Vol 71 (12) ◽  
pp. 2681-2691 ◽  
Author(s):  
H. Georg Schulze ◽  
Stanislav O. Konorov ◽  
James M. Piret ◽  
Michael W. Blades ◽  
Robin F. B. Turner
Keyword(s):  
Raman Spectra ◽  
Mammalian Cell ◽  
Matrix Factorization ◽  
Mammalian Cells ◽  
Hyperspectral Data ◽  
Spectral Unmixing ◽  
Biological Research ◽  
Data Set ◽  
Non Negative Matrix Factorization

Mammalian cells contain various macromolecules that can be investigated non-invasively with Raman spectroscopy. The particular mixture of major macromolecules present in a cell being probed are reflected in the measured Raman spectra. Determining macromolecular identities and estimating their concentrations from these mixture Raman spectra can distinguish cell types and otherwise enable biological research. However, the application of canonical multivariate methods, such as principal component analysis (PCA), to perform spectral unmixing yields mathematical solutions that can be difficult to interpret. Non-negative matrix factorization (NNMF) improves the interpretability of unmixed macromolecular components, but can be difficult to apply because ambiguities produced by overlapping Raman bands permit multiple solutions. Furthermore, theoretically sound methods can be difficult to implement in practice. Here we examined the effects of a number of empirical approaches on the quality of NNMF results. These approaches were evaluated on simulated mammalian cell Raman hyperspectra and the results were used to develop an enhanced procedure for implementing NNMF. We demonstrated the utility of this procedure using a Raman hyperspectral data set measured from human islet cells to recover the spectra of insulin and glucagon. This was compared to the relatively inferior PCA of these data.

A Hyper-Spectral Unmixing Method Based on Improved Non-Negative Matrix Factorization

2016 ◽  
Vol 13 (11) ◽  
pp. 8689-8694
Author(s):  
Hongmin Gao ◽  
Linghui Chen ◽  
Chenming Li ◽  
Hui Zhou ◽  
Shiming Zhang
Keyword(s):  
Matrix Factorization ◽  
Spectral Unmixing ◽  
Hyper Spectral ◽  
Non Negative Matrix Factorization

scholarly journals Efficient Blind Spectral Unmixing of Fluorescently Labeled Samples Using Multi-Layer Non-Negative Matrix Factorization

PLoS ONE ◽  
2013 ◽  
Vol 8 (11) ◽  
pp. e78504 ◽  
Author(s):  
Thomas Pengo ◽  
Arrate Muñoz-Barrutia ◽  
Isabel Zudaire ◽  
Carlos Ortiz-de-Solorzano
Keyword(s):  
Matrix Factorization ◽  
Spectral Unmixing ◽  
Non Negative Matrix Factorization

scholarly journals Spectral Unmixing of Hyperspectral Images in the Presence of Small Targets

2018 ◽  
Vol 7 (1) ◽  
Author(s):  
Sylvain Ravel ◽  
Caroline Fossati ◽  
Salah Bourennane
Keyword(s):  
Matrix Factorization ◽  
Hyperspectral Image ◽  
Spectral Unmixing ◽  
Reflectance Spectra ◽  
Hyperspectral Images ◽  
Real World Data ◽  
Linear Combinations ◽  
Resampling Methods ◽  
Small Targets ◽  
Non Negative Matrix Factorization

Generally, the content of the hyperspectral image pixel is a mixture of the reflectance spectra of the different components in the imaged scene. In this paper, we consider a linear mixing model where the pixels are linear combinations of those reflectance spectra, called endmembers, and linear coefficients corresponding to their abundances. An important issue in hyperspectral imagery consists in unmixing those pixels to retrieve the endmembers and their corresponding abundances. We consider the unmixing issue in the presence of small targets, that is, their endmembers are only contained in few pixels of the image. We introduce a thresholding method relying on Non-negative Matrix Factorization to detect pixels containing rare endmembers. We propose two resampling methods based on bootstrap for spectral unmixing of hyperspectral images to retrieve both the dominant and rare endmembers. Our experimental results on both simulated and real world data demonstrate the efficiency of the proposed method to estimate correctly all the endmembers present in hyperspectral images, in particular the rare endmembers.

Sign in / Sign up

Export Citation Format

Share Document