Caving Depth Classification by Feature Extraction in Cuttings Images

The estimation of caving depth is of particular interest in the oil industry. During the drilling process, the rock classification problem is studied to analyze the concentration of cuttings at the vibrating shale shakers through the classification of caving images. To date, depth estimation based on caving rock images has not been treated in the literature. This paper presents a new depth caving estimation system based on the classification of caving images through feature extraction. To extract the texture descriptors, the cutting images are first mapped on a common space where they can be easily compared. Then, textural features are obtained by applying a multi-scale and multiorientation approach through the use of Gabor transformations. Two different depth classifiers are developed; the first separates the textural features by using a soft decision based on the Euclidean distance, and the second performs a hard decision classification by applying a thresholding procedure. A detailed mathematical formulation of the developed classifiers is presented. The developed estimation system is verified using real data from rock cutting images in petroleum wells. Several simulations illustrate the performance of the proposed model using real images from a wellbore in a Colombian basin. The correct classification rate of a database containing 17 depth estimates is 91.2%.