Watershed is a widely used image segmentation algorithm. Most researchers understand just an idea of this method: a grayscale image is considered as topographic relief, which is flooded from initial basins. However, frequently they are not aware of the options of the algorithm and the peculiarities of its realizations. There are many watershed implementations in software packages and products. Even if these packages are based on the identical algorithm–watershed, by flooding their outcomes, processing speed, and consumed memory, vary greatly. In particular, the difference among various implementations is noticeable for huge volumetric images; for instance, tomographic 3D images, for which low performance and high memory requirements of watershed might be bottlenecks. In our review, we discuss the peculiarities of algorithms with and without waterline generation, the impact of connectivity type and relief quantization level on the result, approaches for parallelization, as well as other method options. We present detailed benchmarking of seven open-source and three commercial software implementations of marker-controlled watershed for semantic or instance segmentation. We compare those software packages for one synthetic and two natural volumetric images. The aim of the review is to provide information and advice for practitioners to select the appropriate version of watershed for their problem solving. In addition, we forecast future directions of software development for 3D image segmentation by watershed.
Image segmentation is a crucial step of almost any Digital Rock workflow. In this paper, we propose an approach for generation of a labelled dataset and investigate an application of three popular convolutional neural networks (CNN) architectures for segmentation of 3D microtomographic images of samples of various rocks. Our dataset contains eight pairs of images of five specimens of sand and sandstones. For each sample, we obtain a single set of microtomographic shadow projections, but run reconstruction twice: one regular high-quality reconstruction, and one using just a quarter of all available shadow projections. Thoughtful manual Indicator Kriging (IK) segmentation of the full-quality image is used as the ground truth for segmentation of images with reduced quality. We assess the generalization capability of CNN by splitting our dataset into training and validation sets by five different manners. In addition, we compare neural networks results with segmentation by IK and thresholding. Segmentation outcomes by 2D and 3D U-nets are comparable to IK, but the deep neural networks operate in automatic mode, and there is big room for improvements in solutions based on CNN. The main difficulties are associated with the segmentation of fine structures that are relatively uncommon in our dataset.
1 March 2021 in Journal of Natural Gas Science and Engineering
We present image processing algorithms for a new technique of ceramic proppant crush resistance characterization. To obtain the images of the proppant material before and after the test we used X-ray microtomography. We propose a watershed-based unsupervised algorithm for segmentation of proppant particles, as well as a set of parameters for the characterization of 3D particle size, shape, and porosity. An effective approach based on central geometric moments is described. The approach is used for calculation of particles’ form factor, compactness, equivalent ellipsoid axes lengths, and lengths of projections to these axes. Obtained grain size distribution and crush resistance fit the results of conventional test measured by sieves. However, our technique has a remarkable advantage over traditional laboratory method since it allows to trace the destruction at the level of individual particles and their fragments; it grants to analyze morphological features of fines. We also provide an example describing how the approach can be used for verification of statistical hypotheses about the correlation between particles’ parameters and their crushing under load.
Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) tomography provides a stack of images that represent serial slices of the sample. These images are displaced relatively to each other, and an alignment procedure is required. Traditional methods for alignment of a 3D image are based on a comparison of two adjacent slices. However, such algorithms are easily confused by anisotropy in the sample structure or even experiment geometry in the case of porous media. This may lead to significant distortions in the pore space geometry, if there are no stable fiducial marks in the frame. In this paper, we propose a new method, which meaningfully extends existing alignment procedures. Our technique allows the correction of random misalignments between slices and, at the same time, preserves the overall geometrical structure of the specimen. We consider displacements produced by existing alignment algorithms as a signal and decompose it into low and high-frequency components. Final transformations exclude slow variations and contain only high frequency variations that represent random shifts that need to be corrected. The proposed algorithm can operate with not only translations but also with arbitrary affine transformations. We demonstrate the performance of our approach on a synthetic dataset and two real FIB-SEM images of natural rock.
The whispering gallery effect in the hard X-ray region (0.15–0.3 nm) has been theoretically and experimentally investigated using a concave spherical mirror with a 25-cm radius of curvature and a...