Skip to content

This repository focuses on spectral super-resolution using sparse-based machine learning, with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization algorithm. Our aim is to reconstruct high-resolution multi- or hyperspectral images from limited spectral observations, leveraging BFGS for enhanced efficiency and accuracy.

Notifications You must be signed in to change notification settings

stperrakis/Sparse_Dictionary_Learning_BFGS

Repository files navigation

Sparse_Dictionary_Learning_BFGS

This repository focuses on spectral super-resolution using sparse-based machine learning, with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization algorithm. Our aim is to reconstruct high-resolution multi- or hyperspectral images from limited spectral observations, leveraging BFGS for enhanced efficiency and accuracy.

Acknowledgments

This project makes use of concepts described in the following paper:

  • K. Fotiadou, G. Tsagkatakis, and P. Tsakalides, "Spectral Super-Resolution of Hyperspectral Images via Coupled Dictionary Learning," IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 5, pp. 2777 - 2797, May 2019, doi:10.1109/TGRS.2018.2877124.

We also utilized the SparseCoupledDictionaryLearning by @spl-icsforth

About

This repository focuses on spectral super-resolution using sparse-based machine learning, with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization algorithm. Our aim is to reconstruct high-resolution multi- or hyperspectral images from limited spectral observations, leveraging BFGS for enhanced efficiency and accuracy.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •