Published November 17, 2022
| Version 1.0
Dataset
Open
Simulated industrial CT dataset for deep learning with dual-energy tomograms and ground truth material maps for copper and iron
Description
We use this dataset for training and evaluation of a deep learning model to discriminate multi-material systems with X-ray CT.
The dataset consists of:
- inputs: dual-energy tomograms as binary files without a header (tensor shape for numpy: 2x128x128 @float32)
- simulated spectra are 250kVp and 450kVp both prefiltered using 2mmCuSn
- outputs: the material maps a.k.a. ground truths for the training (same shape as inputs)
- sampled with a delaunay algorithm and randomly filled with iron and copper fractions
The dataset is normalized to [0, 1], so you have to multiply by the mass densities of copper and iron to obtain effective fractions in g/cm^3.
Files
quant_FeCu_250_450kV.zip
Files
(3.0 GB)
Name | Size | Download all |
---|---|---|
md5:854a04dd144ae823e5dcad250799ac01
|
3.0 GB | Preview Download |