Feature analysis and classification of typical mineral images based on Fourier transform

Yaqi Guo; Jun Pan; Lijun Jiang; Yehan Sun

doi:10.1117/12.2626910

14 February 2022 Feature analysis and classification of typical mineral images based on Fourier transform

Yaqi Guo, Jun Pan, Lijun Jiang, Yehan Sun

Proceedings Volume 12161, 4th International Conference on Informatics Engineering & Information Science (ICIEIS2021); 121610W (2022) https://doi.org/10.1117/12.2626910
Event: 4th International Conference on Informatics Engineering and Information Science, 2021, Tianjin, China

Abstract

The identification of minerals in rocks from thin section images is a basic task of geoscience. Compared with traditional manual interpretation, machine recognition is widely used in mineral classification for its advantages of speed and objectivity. It is an important scientific issue to choose which mineral feature to use for automatic classification. Based on this, the texture features of thin mineral images were specially studied in frequency domain. Firstly, the primary texture classification variables were obtained by simulating the radial statistical analysis of images and mineral samples; then, the separability was verified by variance analysis, and the variables were combined based on the factor analysis method; lastly, classification verification of mineral samples was carried out by discriminant analysis. The experimental results show that the low frequency information accounts for about 95% of the energy in the sample spectrum, and the classification efficiency is significantly higher than the test threshold. The total classification accuracy of Texture Contour Factor (TCF) and Texture Detail Factor (TDF) is 89.6%, which is obtained by factor analysis. The results show that the frequency features in the thin section mineral images can effectively reflect the changes of mineral texture and have a good effect on the automatic classification of mineral images.

Citation Download Citation

Yaqi Guo, Jun Pan, Lijun Jiang, and Yehan Sun "Feature analysis and classification of typical mineral images based on Fourier transform", Proc. SPIE 12161, 4th International Conference on Informatics Engineering & Information Science (ICIEIS2021), 121610W (14 February 2022); https://doi.org/10.1117/12.2626910

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
14 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Minerals

Image classification

Feldspar

Mica

Statistical analysis

Quartz

Factor analysis

Show All Keywords

Keywords/Phrases

Search In:

Publication Years