SPECTRE Dataset

This repository contains the dataset and code for the paper "SPECTRE: A Dataset for Spectral Reconstruction on Chip-Size Spectrometers With a Physics-Informed Augmentation Method". You can find all data files in the Zenodo repository

Contents

• examples/: Contains examples on how to use the dataset.
• src/: Contains the python files of the spectre module.

Requirements

• Python 3.11+
• Dependencies are listed in the pyproject.toml file.

Usage

1. Clone the repository:

   git clone https://github.com/your-repo.git

2. Install the project:

   pip install .

3. Use the example scripts or notebooks:

   python examples/read_data.py

License

• The dataset is available under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.
• The code is available under the Software Copyright License for Academic Use of the Fraunhofer Software, Version 1.0.

Citation

If you use this dataset or code in your work, please cite the corresponding paper:

SPECTRE: A Dataset for Spectral Reconstruction on Chip-Size Spectrometers With a Physics-Informed Augmentation Method

To be published in: Proceedings of IEEE Sensors 2024. Once the paper is online a link to it and the DOI will be added to the bibtex entry

BibTeX entry:

@article{spectre,
  title={SPECTRE: A Dataset for Spectral Reconstruction on Chip-Size Spectrometers With a Physics-Informed Augmentation Method},
  author={Julio Wissing, Teresa Scholz, Stefan Saloman, Lidia Fargueta, Stephan Junger, Alessio Stefani, Wladimir Tschekalinskij, Stephan Scheele3, Ute Schmid},
  journal={IEEE Sensors 2024},
  year={2024},
}