The long journey to the training of a deep neural network for segmenting pores and fibers

Abstract

Even though it is a crucial step for achieving suitable results, the preprocessing of data before it is used as input to deep neural networks is often only described as a side note. This work elaborates on the required steps in this preprocessing procedure. Specifically, we provide insights into the selection of appropriate segmentation algorithms to generate reference volumes from X-ray computed tomography (XCT) scans as training data. Furthermore, this work evaluates the criteria for the selection of an appropriate deep learning network architecture, and a quantitative comparison between networks based on U-Net and V-Net.