Unlock instant, AI-driven research and patent intelligence for your innovation.

Mineral substance rapid identification method based on deep learning

A deep learning and mineral technology, applied in the field of deep learning, can solve problems such as limiting remote sensing prospecting, and achieve the effect of improving efficiency and accuracy

Inactive Publication Date: 2019-05-24
JINAN INSPUR HIGH TECH TECH DEV CO LTD
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method works well, but must be carried out in the laboratory, and cannot quickly and timely identify the mineral composition
[0005] Therefore, the use of the above methods for mineral identification will greatly limit the efficiency of remote sensing mineral prospecting, remote sensing mineral mapping, and geoscience research that requires a large number of mineral composition identification work (such as: geological drilling, field geological mapping, etc.)

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, not all Embodiments, based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0035] The present invention uses a deep learning algorithm to initially screen the mineral types of the minerals, and then initially determines the possible mineral types in the spectral library.

[0036] The method of the present invention comprises:

[0037] S1. Segment mineral microscope image data into the same pixel size;

[0038] S2. Carry out manual marking, and mark the types of minerals according to expert experien...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a mineral substance rapid identification method based on deep learning, belongs to the technical field of deep learning, and aims to preliminarily screen mineral substance typesof mineral substances by using a deep learning algorithm and preliminarily determine possible mineral substance types in a spectrum library. Compared with the prior art, the mineral substance recognition efficiency and accuracy can be improved, and the types of the mineral substances can be quickly and accurately recognized.

Description

technical field [0001] The invention relates to deep learning technology, in particular to a method for quickly identifying minerals based on deep learning. Background technique [0002] Geology-related work and remote sensing mineral exploration are inseparable from mineral composition identification. There are two relatively mature identification methods in geosciences: [0003] (1) Cut the specimen into thin slices and use the optical difference of minerals for microscopic identification. This method is mature and reliable, and is most widely used in geoscience research. But the work cycle is long and the appraiser must have rich experience in microscopic appraisal. [0004] (2) Pulverize the specimen, and use the X-ray diffractometer to obtain the diffraction pattern of the specimen for analysis. This method works well, but it must be carried out in a laboratory, and cannot quickly and timely identify mineral components. [0005] Therefore, using the above methods f...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04
Inventor 尹青山李锐段强安程治
Owner JINAN INSPUR HIGH TECH TECH DEV CO LTD