基于裂缝平移的岩心CT序列图像裂缝批量提取

Crack Segmentation Core CT Image Sequence Based on Crack Traslation

岩心CT序列图像的裂缝阈值分割是重构三维岩心裂缝数字模型的关键步骤。由于岩心CT序列图存在噪点较多、裂缝细微等特点,常规的阈值分割方法难以做到完整提取裂缝。但是岩心CT序列图像帧间相似度较大,且部分裂缝存在方向性移动趋势,因此本文提出了一种基于裂缝平移的裂缝批量提取方法。具体流程是先在序列图第一帧进行人工标注裂缝区域,之后再根据下一帧裂缝的位置移动并改变裂缝形态达到提取裂缝的目的。实验结果表明,本文的方法存在两个优点:一是去除了二值化提取后噪声的干扰,也使得提取的裂缝更加完整没有断裂,在大批量提取某种类型裂缝的情景下有较好的应用。二是可以选择逐条提取裂缝目标,可以忽略一些较浅裂缝或不明显裂缝,只保留感兴趣区域的裂缝目标,进而可以针对性地重构目标裂缝的三维结构。

Crack threshold segmentation of core CT image sequence is a key step to reconstruct 3D core crack digital model. Because there are many noises and subtle crack in core CT sequence, it is difficult to extract crack completely by conventional threshold segmentation method. However, the similarity between the frames of core CT sequence images is large, and some cracks have the trend of directional movement. Therefore, this paper proposes a batch crack extraction method based on crack translation. The specific process is to manually mark the crack area in the first frame of the sequence diagram, and then move and change the crack shape according to the position of the next frame to achieve the purpose of extracting cracks. The experimental results show that this method has two advantages: one is to remove the noise after binarization segmentation, and also make the extracted cracks more complete without fracture, which has a good application in the situation of mass extraction of certain types of cracks. Secondly, we can choose to extract the crack target one by one, and ignore some shallow cracks or unobvious cracks, only the crack target in the region of interest is reserved,so as to reconstruct the 3D structure of the target cracks.