Figure 3 - uploaded by Ying Da Wang
Content may be subject to copyright.
Architecture of SegNet, an early example of a semantic segmentation neural network. The encoding and decoding blocks are clearly illustrated. The translation of input is performed by sequentially deeper convolutions, while transformation into output is performed by sequentially shallower convolutions.
Source publication
Segmentation of 3D micro-Computed Tomographic uCT images of rock samples is essential for further Digital Rock Physics (DRP) analysis, however, conventional methods such as thresholding, watershed segmentation, and converging active contours are susceptible to user-bias. Deep Convolutional Neural Networks (CNNs) have produced accurate pixelwise sem...
Context in source publication
Context 1
... this process, an input grey-scale or colour image is transformed into a semantically segmented image, with multiple labelled regions identified. The architecture is illustrated in Figure 3, and shows the structure of each encoder and decoder block. Each encoder block consists of batch-normalised [71], ReLU activated [72] convolutions of increasing filter depth followed by a 2x2 maxpool [73]. ...
Similar publications
Gas identification using seismic data is challenging for tight gas reservoirs with low porosity and permeability due to the complicated poroelastic behaviors of tight sandstone. In this study, the Chapman theory was used to simulate the dispersion and attenuation caused by the squirt flow of fluids in the complex pore spaces, which are assumed to c...
