Structure Assisted Compressed Sensing Reconstruction of Undersampled AFM Images Dataset

This deposition contains the results from a simulation of reconstructions of undersampled atomic force microscopy (AFM) images. The reconstructions were obtained using weighted iterative thresholding compressed sensing algorithms.

The deposition consists of:

1. An  HDF5 database containing the results from simulations of reconstructions of undersampled atomic force microscopy images (weighted_it_reconstructions.hdf5).
2. The Python script which was used to create the database (weighted_it_reconstructions.py).
3. MD5 and SHA256 checksums of the database and Python script files (weighted_it_reconstructions.MD5SUMS / weighted_it_reconstructions.SHA256SUMS).

The HDF5 database is licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/) . Since the CC BY 4.0 license is not well suited for source code, the Python script is licensed under the BSD 2-Clause license (http://opensource.org/licenses/BSD-2-Clause) .

The files are provided as-is with no warranty as detailed in the above mentioned licenses.

The database is split into four parts:

1. weighted_it_reconstructions.hdf5.tar.xz.part-00
2. weighted_it_reconstructions.hdf5.tar.xz.part-01
3. weighted_it_reconstructions.hdf5.tar.xz.part-02
4. weighted_it_reconstructions.hdf5.tar.xz.part-03

These four parts must be concatenated before the database can be extracted from the tar.xz archive. On Unix-like systems this may be done using:

cat weighted_it_reconstructions.hdf5.tar.xz.part-* > weighted_it_reconstructions.hdf5.tar.xz

after which the archive may be extracted, e.g., using:

tar xfJ weighted_it_reconstructions.hdf5.tar.xz

WARNING: The extracted HDF5 database has a size of 70 GiB.

The simulation results in the database are based on "Atomic Force Microscopy Images of Cell Specimens" by Christian Rankl licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). The original images are available at http://dx.doi.org/10.5281/zenodo.17573. The original images are provided as-is without warranty of any kind. Both the original images as well as adapted images are part of the dataset.