We have described an algorithm to perform automatic dip picking on borehole images. One key element of our method is a statistical validation, based on the a contrario theory, which is used to decide whether each candidate dip is to be accepted or not. Our method also uses a randomized Hough transform, which greatly improves the processing speed, allowing for a real-time detection of dips during image visualization. In addition, the same algorithm can be applied at different scales to provide a multiresolution analysis of the structures. Our experiments determine that our algorithm produces reliable dip picking by an evaluation on three manually annotated boreholes: Our method detects from 60% to 90% of the dips annotated by an expert, depending on the complexity of the data.

中文翻译：

---

用于钻孔成像的反向倾斜采摘

我们已经描述了一种对钻孔图像执行自动倾斜拾取的算法。我们方法的一个关键要素是基于逆向理论的统计验证，用于决定是否接受每个候选倾角。我们的方法还使用随机霍夫变换，这大大提高了处理速度，允许在图像可视化过程中实时检测倾角。此外，可以在不同尺度上应用相同的算法以提供结构的多分辨率分析。我们的实验确定我们的算法通过对三个手动注释钻孔的评估产生可靠的倾角拾取：我们的方法检测专家注释的倾角的 60% 到 90%，具体取决于数据的复杂性。