Dataset Open Access

Structure Assisted Compressed Sensing Reconstruction of Undersampled AFM Images Dataset

Oxvig, Christian Schou; Arildsen, Thomas; Larsen, Torben

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 (
  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 ( . 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 ( .

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 ( The original images are available at 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. 

Files (8.1 GB)
Name Size
2.1 GB Download
2.1 GB Download
2.1 GB Download
1.6 GB Download
393 Bytes Download
19.0 kB Download
553 Bytes Download


Cite as