Non-negative Einstein tensor factorization for unmixing hyperspectral images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hachimi, Anas El, Jbilou, Khalide, Ratnani, Ahmed
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929388105236480
author Hachimi, Anas El
Jbilou, Khalide
Ratnani, Ahmed
author_facet Hachimi, Anas El
Jbilou, Khalide
Ratnani, Ahmed
contents In this manuscript, we introduce a tensor-based approach to Non-Negative Tensor Factorization (NTF). The method entails tensor dimension reduction through the utilization of the Einstein product. To maintain the regularity and sparsity of the data, certain constraints are imposed. Additionally, we present an optimization algorithm in the form of a tensor multiplicative updates method, which relies on the Einstein product. To guarantee a minimum number of iterations for the convergence of the proposed algorithm, we employ the Reduced Rank Extrapolation (RRE) and the Topological Extrapolation Transformation Algorithm (TEA). The efficacy of the proposed model is demonstrated through tests conducted on Hyperspectral Images (HI) for denoising, as well as for Hyperspectral Image Linear Unmixing. Numerical experiments are provided to substantiate the effectiveness of the proposed model for both synthetic and real data.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11471
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Non-negative Einstein tensor factorization for unmixing hyperspectral images
Hachimi, Anas El
Jbilou, Khalide
Ratnani, Ahmed
Numerical Analysis
In this manuscript, we introduce a tensor-based approach to Non-Negative Tensor Factorization (NTF). The method entails tensor dimension reduction through the utilization of the Einstein product. To maintain the regularity and sparsity of the data, certain constraints are imposed. Additionally, we present an optimization algorithm in the form of a tensor multiplicative updates method, which relies on the Einstein product. To guarantee a minimum number of iterations for the convergence of the proposed algorithm, we employ the Reduced Rank Extrapolation (RRE) and the Topological Extrapolation Transformation Algorithm (TEA). The efficacy of the proposed model is demonstrated through tests conducted on Hyperspectral Images (HI) for denoising, as well as for Hyperspectral Image Linear Unmixing. Numerical experiments are provided to substantiate the effectiveness of the proposed model for both synthetic and real data.
title Non-negative Einstein tensor factorization for unmixing hyperspectral images
topic Numerical Analysis
url https://arxiv.org/abs/2406.11471