Fully Convolutional Deep Network Architectures for Automatic Short Glass Fiber Semantic Segmentation from CT scans

Autor:	Konopczyński, Tomasz, Rathore, Danish, Rathore, Jitendra, Kröger, Thorben, Zheng, Lei, Garbe, Christoph S., Carmignato, Simone, Hesser, Jürgen
Rok vydání:	2019
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted to 8th Conference on Industrial Computed Tomography, Wels, Austria (iCT 2018)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1901.01211 Zobrazit plný text záznamu View this record from Arxiv