A method for extracting pores and fractures from core CT images based on deep learning

Through a deep learning-based method, the codec model and Dice-Loss function are used to solve the problem of insufficient efficiency and accuracy in the pore joint extraction of core CT images, and a more efficient and accurate pore joint extraction effect is achieved.

CN114820479BActive Publication Date: 2025-03-18SOUTHWEST PETROLEUM UNIV
1 Cites 0 Cited by

Patent Information

Application Number
CN202210383809.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-12
Publication Date
2025-03-18
Estimated Expiration
2042-04-12

AI Technical Summary

Technical Problem

The prior art has problems with insufficient efficiency and accuracy in core CT images extraction, especially in the case of uneven samples, it is difficult to effectively extract pore features.

Method used

Using a deep learning-based method, the hole seams of core CT images are extracted by encoding and decoding models and Dice-Loss functions. The method includes data set preparation, model forward inference and loss calculation, and optimizes image data to achieve accurate extraction of hole seams through multiple iterations and image resolution category judgment.

Benefits of technology

The boundary smoothness and center overlap of the pore seam images are significantly improved, the sample imbalance problem is effectively solved, and the accuracy and efficiency of pore seam extraction are improved.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to the field of image processing technology, and to a method for extracting pores and seams from core CT images based on deep learning, which includes the following steps: 1. Data set preparation; 2. Model forward reasoning, passing the CT image into the model to obtain the output of the forward reasoning graph; 3. Loss calculation, the feature graph output by the model and the real data label; 4. Repeating steps 2 and 3, after multiple iterations and judging the real pore and seam categories of the image, and calculating the loss of the image data, optimizing according to the weight of the loss ratio; finally, using the trained model to output the image pore and seam results, thereby realizing the extraction of pores and seams. The overlap degree of the pore and seam image extracted by the method of the present invention and the real image pore and seam on the edge and the accuracy in the middle are greatly improved.
Need to check novelty before this filing date? Find Prior Art