Crack detection algorithm for oil rock core industrial CT image
-
摘要: 针对裂缝区域分割的需求和石油岩芯CT图像的特点, 改进了现有的水平集分割算法。首先对图像中值滤波去噪后运用C-V模型对图像进行初分割, 把背景区域和岩芯区域准确分开, 得到岩芯区域的轮廓;然后调整轮廓外区域的灰度值, 使之等于岩芯区域平均灰度值, 增强目标区域;最后再进行RSF模型细分割, 得到最终分割结果。对于高斯噪声污染严重的岩芯图像, 先采用了邻域加窗的非局部均值去噪方法, 再用改进水平集算法分割, 实验结果表明该分割方法是有效的。Abstract: In order to meet the requirement of crack region segmentation, based on the characteristics of oil sedimentary core industrial CT image, the level set segmentation algorithm is improved. Firstly, a median filter is used for denoising, and a C-V model is adopted to get the coarse image segmentation result. The background area and the core area are separated, and the contour of the core is obtained. Secondly, the gray level of the background region is adjusted, so that it is equal to the average gray level of the core area. Finally, the Region-Scalable Fitting (RSF) model is adopted to precisely segment the crack region. For the core image of Gauss noise pollution, the method of non-local mean with the neighborhood window is used, and then the improved level set algorithm is used. The experimental results show that the improved level set algorithm for image segmentation is effective for oil rock core CT image.
-
Key words:
- CT image /
- crack segmentation /
- level set /
- C-V model /
- Region-Scalable Fitting model
点击查看大图
计量
- 文章访问数: 945
- HTML全文浏览量: 198
- PDF下载量: 328
- 被引次数: 0