We present the first attempt to perform short glass fiber semantic segmentation from X-ray computed tomography volumetric datasets at medium (3.9 {\mu}m isotropic) and low (8.3 {\mu}m isotropic) resolution using deep learning architectures. We performed experiments on both synthetic and real CT scans and evaluated deep fully convolutional architectures with both 2D and 3D kernels. Our artificial neural networks outperform existing methods at both medium and low resolution scans.
@article{arxiv.1901.01211,
title = {Fully Convolutional Deep Network Architectures for Automatic Short Glass Fiber Semantic Segmentation from CT scans},
author = {Tomasz Konopczyński and Danish Rathore and Jitendra Rathore and Thorben Kröger and Lei Zheng and Christoph S. Garbe and Simone Carmignato and Jürgen Hesser},
journal= {arXiv preprint arXiv:1901.01211},
year = {2019}
}
Comments
Accepted to 8th Conference on Industrial Computed Tomography, Wels, Austria (iCT 2018)