Abstract
In this paper, we propose a framework for CT image segmentation of oil rock core. According to the characteristics of CT image of oil rock core, the existing level set segmentation algorithm is improved. Firstly, an algorithm of Chan-Vese (C-V) model is carried out to segment rock core from image background. Secondly the gray level of image background region is replaced by the average gray level of rock core, so that image background does not affect the binary segmentation. Next, median filtering processing is carried out. Finally, an algorithm of local binary fitting (LBF) model is executed to obtain the crack region. The proposed algorithm has been applied to oil rock core CT images with promising results.
Highlights
There are a large number of irregular and different scales of crack in the rock, which affect the macroscopic physical properties of the rock in varying degrees
computed tomography (CT) images may be polluted by noise, which makes many problems in CT image segmentation, making some widely used methods unable to identify the target area [2]
It should be emphasized that all parameters of C-V and Local Binary Fitting (LBF) models are optimized empirically in the test
Summary
There are a large number of irregular and different scales of crack in the rock, which affect the macroscopic physical properties of the rock in varying degrees. Gao et al proposed a novel statistical active contours method for using an arbitrary number of level set functions to segment the image into regions of the corresponding amount [6]. Wang et al [19] presented a new region-based active contour model in a variational level set formulation for image segmentation. They defined a local energy to characterize the fitting of the local Gaussian distribution. Based on the previous works [17,18,19], we propose a new 3D segmentation model for CT images of rock cores. Comparative analysis of examples of different methods shows that our method is more accurate than the well-known level set models
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have