Rock image pore type identification method based on semantic segmentation

Abstract

The invention discloses a rock image pore type identification method based on semantic segmentation. The method comprises the following steps: S1, establishing an initial deep learning network model;S2, acquiring an original rock image, and performing image cutting and image enhancement to obtain preprocessed image data; S3, acquiring an original image of the rock, and performing manual marking of pore positions and shapes to obtain marked label image data; S4, carrying out One-Hot encoding on the labeled label image data to obtain coded label data; S5, training the initial deep learning network model by taking the preprocessed image data and the encoded tag data as training samples to obtain a trained model; and S6, identifying the to-be-identified image by using the trained model. The method has the advantages that the noise resistance is high, the generalization capability is realized, the pore recognition precision can be improved, and the pore category recognition is realized.

Description

technical field [0001] The invention relates to the field of rock pore recognition, in particular to a method for recognizing rock image pore types based on semantic segmentation. Background technique [0002] Rock porosity is an index to measure its ability to retain fluid. Different types of rock pores have different characteristics. For example, shale has intergranular pores, intragranular pores, organic pores, and cracks. The difference in pore characteristics can eventually lead to huge differences in the development effect controlled by the permeability, so the pore type largely determines the oil recovery efficiency. In recent years, with the development of digital image processing technology, a commonly used method to identify pore types is to use drilling core samples to grind casting thin sections, take thin section images under scanning electron microscope and process the images to extract rock pore images features to classify them. [0003] Traditional image se...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned deficiencies in the prior art, a method for identifying pore types in rock images based on semantic segmentation provided by the present invention solves the problem of difficult identification of existing rock pores

Images