Detecting micro fractures: A comprehensive comparison of conventional and machine-learning based segmentation methods
This work addresses the challenge of accurately and efficiently identifying micro fractures in porous rock materials, which is important for geoscience and engineering applications, but it is incremental as it compares existing methods on a specific dataset.
The study compared three conventional and two machine-learning segmentation methods for detecting micro fractures in XRCT images of Carrara marble, finding that a 2D U-net model achieved the best performance in terms of segmentation quality and processing time.
Studying porous rock materials with X-Ray Computed Tomography (XRCT) has been established as a standard procedure for the non-destructive visualization of flow and transport in opaque porous media. Despite the recent advances in the field of XRCT, some challenges still remain due to the inherent noise and imaging artefacts in the produced data. These issues become even more profound when the objective is the identification of fractures, and/or fracture networks. The challenge is the limited contrast between the regions of interest and the neighboring areas. This limited contrast can mostly be attributed to the minute aperture of the fractures. In order to overcome this challenge, it has been a common approach to apply digital image processing, such as filtering, to enhance the signal-to-noise ratio. Additionally, segmentation methods based on threshold-/morphology schemes can be employed to obtain enhanced information from the features of interest. However, this workflow needs a skillful operator to fine-tune its input parameters, and the required computation time significantly increases due to the complexity of the available methods, and the large volume of the data-set. In this study, based on a data-set produced by the successful visualization of a fracture network in Carrara marble with XRCT, we present the segmentation results from a number of segmentation methods. Three conventional and two machine-learning-based methods are evaluated. The segmentation results from all five methods are compared to each other in terms of segmentation quality and time efficiency. Due to memory limitations, and in order to accomplish a fair comparison, all the methods are employed in a 2D scheme. The output of the 2D U-net model, which is one of the adopted machine-learning-based segmentation methods, shows the best performance regarding the quality of segmentation and the required processing time.