基于聚类算法的岩石CT图像分割及量化方法

A method of rock CT image segmentation and quantification based on clustering algorithm

为研究岩石CT图像分割及量化方法,以识别岩石CT图像中的岩石区、损伤区及背景区为目的,提出了一种聚类算法与数字图像处理技术相结合的方法,该方法根据"物以类聚"的统计原理,按距离相近或相似程度对岩石CT图像中的像素进行标定,从而实现图像分割及量化。结果表明:该方法能够准确地对岩石CT图像中的不同区域进行分割并且实现了对损伤的量化表达;同时,对于结果不确定度影响的初始参数有完全的排异性,从而保证了结果的稳定性;将该算法与阈值分割法进行比较,该算法可避免人为选择阈值导致的误差,从而保证结果的可靠性。

In order to study rock CT image segmentation and quantification,with the purpose of identifying the rock area,damage area and background area in rock CT image,a method combining clustering algorithm with digital image processing techniques was given. The application results show that： The method can accurately segment the different areas of rock CT image and quantify its percentage; Meanwhile,the initial parameters that can influence the result uncertainly have complementarily mutual exclusiveness completely,ensuring the stability of the result; Compared the algorithm with threshold segmentation method,the algorithm can avoid the error caused by human choice threshold,which ensured the reliability of the results.