Fully Convolutional Deep Network Architectures for Automatic Short Glass Fiber Semantic Segmentation from CT scans
This work addresses the need for automated fiber segmentation in materials science, representing an incremental improvement with domain-specific applications.
The paper tackled the problem of segmenting short glass fibers in CT scans by developing deep fully convolutional networks, achieving superior performance over existing methods at both medium and low resolutions.
We present the first attempt to perform short glass fiber semantic segmentation from X-ray computed tomography volumetric datasets at medium (3.9 μm isotropic) and low (8.3 μm 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.