Rock image classification method based on attention guidance and multi-feature fusion

CN119445544APending Publication Date: 2025-02-14WUHAN SURVEYING GEOTECHN RES INST OF MCC
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411452248.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-17
Publication Date
2025-02-14

AI Technical Summary

Technical Problem

Traditional rock classification methods rely on professional equipment and manual experience, resulting in long-term and low-efficiency processes, and it is difficult to obtain high-quality rock feature representations under small samples.

Method used

Using a rock image classification method based on attention guidance and multi-feature fusion, the remarkable features of rock images are extracted and fused by constructing a residual neural network ResNet-50, combining the space-channel attention module and the multi-feature fusion prediction module.

Benefits of technology

The accuracy and speed of rock image classification are improved, especially under a small sample condition, with an accuracy rate of 97.03%, a recall rate of 96.42% and a F1 score of 96.72%, which significantly improves the efficiency and accuracy of rock classification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119445544A_ABST
    Figure CN119445544A_ABST
Patent Text Reader

Abstract

The invention provides a rock image classification method based on attention guidance and multi-feature fusion, and the method comprises the following steps: (1) constructing a rock data set, carrying out the data enhancement of the data set, and dividing the data set into a training set and a test set; (2) constructing a residual neural network ResNet-50, inputting a prepared training set into a network structure for training, and extracting third-stage features, (3) inputting the third-stage features into a space-channel attention module, and outputting spatial features # imgabs0 # and channel features # imgabs1 #, (4) inputting # imgabs2 # and # imgabs3 # into a multi-feature fusion prediction module for classification, and outputting identified rock type names; (5) verifying by using the test set to obtain a trained rock image classification model; and (6) identifying and classifying the rock image by using the rock image classification model to obtain the name of the rock type. The classification method is high in precision, the precision rate is 97.03%, the recall rate is 96.42%, and the F1 score is 96.72%.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Copper ore / waste ore classification method and system based on multi-energy-spectrum image

    CN119992230A

  • Rock sample crack detection and identification method based on image visual saliency

    CN120126013A

  • Screen mixed content classification method and system oriented to efficient compression

    CN120526239A