Sandstone pore detection method based on multi-layer multi-kernel learning and region merging

Abstract

The invention relates to a sandstone pore detection method based on multi-layer multi-kernel learning and region merging, and the method comprises the steps of obtaining an original pore image, carrying out the denoising and enhancement processing of the image, and carrying out the SLIC superpixel segmentation of the image; constructing an RAG region adjacency graph, and marking an adjacent relation between the regions; performing manual annotation after superpixel segmentation, and performing binary classification to obtain a pore region and a non-pore region; extracting artificial features from the training set images to obtain feature vectors of multi-feature fusion, and constructing a multi-layer multi-kernel model; extracting multi-feature vectors from the test set images, and inputting the multi-feature vectors into the stored model; outputting a probability that the current region is a pore, and taking the probability as a region similarity measurement value; calculating the similarity degree of each adjacent region in the graph; carrying out region merging; and outputting the pore detection area. The multi-layer multi-kernel learning algorithm is utilized to further improve the accuracy of region recognition, the target region and the background region of the image can be better distinguished, and the detection precision is improved.

Description

technical field [0001] The invention relates to the technical field of rock pore detection methods, in particular to a sandstone pore detection method based on multi-layer multi-core learning and region merging. Background technique [0002] With the continuous consumption of conventional oil and gas resources in the world, unconventional oil and gas resources are getting more and more attention from countries all over the world. Tight oil is an easy-to-exploit part of unconventional oil and gas. As an important oil replacement resource, it has become a highlight of global oil exploration and development. field. Since tight oil mainly exists in low-porosity sandstone reservoirs, the study of microscopic pore structure is of great significance. The traditional pore detection method adopts direct observation method or image processing technology for gray scale binarization. However, the sandstone CT image contains a variety of mineral components, and there are gaps and vario...

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a sandstone pore detection method based on multi-layer multi-core learning and region merging to overcome the poor interpretability and poor interpretability caused by using deep learning methods and traditional image processing methods in the prior art to detect pores in images. Poor stickiness, low detection accuracy and other defects

Images