Use of Deep Learning for structural analysis of CT-images of soil samples

Ralf Wieland, Chinatsu Ukawa, Monika Joschko, Adrian Krolczyk, Guido Fritsch, Thomas Hildebrandt, Juliane Filser, Olaf Schmidt & Juan J. Jimenez
Soil samples from several European countries were scanned using medical computer tomography (CT) device and are now available as CT images. The analysis of these samples was carried out using deep learning methods. For this purpose, a VGG16 network was trained with the CT-images (X). For the annotation (y) a new method for automated annotation, "surrogate'' learning, was introduced. The generated neural networks (NN) were subjected to a detailed analysis. Among other things, transfer learning...
40 views reported since publication in 2021.

These counts follow the COUNTER Code of Practice, meaning that Internet robots and repeats within a certain time frame are excluded.
What does this mean?