Application of pattern recognition methods to automatic identification of microscopic images of rocks registered under different polarization and lighting conditions
Journal Title: Geology, Geophysics & Environment - Year 2013, Vol 39, Issue 4
Abstract
The paper presents the results of the automatic classification of rock images, taken under an optical microscope under different lighting conditions and with different polarization angles. The classification was conducted with the use of four pattern recognition methods: nearest neighbor, k-nearest neighbors, nearest mode, and optimal spherical neighborhoods on thin sections of five selected rocks. During research the CIELAB color space and the 9D feature space were used. The results indicate that changing both lighting conditions and polarization angles results in worsening the classification outcome, although not substantially. Duduring the automatic classification of rocks photographed under different lighting and polarization conditions, the highest number of correctly classified rocks (97%) is given by the nearest neighbor method. The results show that the automatic classification of rocks is possible within a predefined group of rocks. The results also indicate the optimal spherical neighborhoods method to be the safest method out of those tested, which means that it returns the lowest number of incorrect classifications.
Authors and Affiliations
B. Ślipek, M. Młynarczuk
Keywords
Related Articles
- EP ID EP166011
- DOI 10.7494/geol.2013.39.4.373
- Views 71
- Downloads 0
Examples of applications of geothermal waters for recreation, heating and bottling in selected regions of Hungary
Due to the favourable geothermal conditions in Hungary, where the geothermal gradient is about 1.5 times greater than the world average, the country has numerous centers, which use geothermal waters directly for heating,...
Selected hydrochemical ratios of waters from inflows at level VI in "Wieliczka" Salt Mine
Relationships between major ions, such as Cl- , SO4 2- and Na+ and some microelements, may serve as good indicators of genesis and chemical transformations occurring during groundwater flow. The chemical composition of w...
Metasomatic column with the apobasite listvenites end-member from the Slovinky-Gelnica ore field (Gemeric Superunit, Western Carpathians) and comparison to their type localities from Ural
A metasomatic column (or metasomatic zone pattern) is the complete sequence of metasomatic zones characterising an individual metasomatic facies (Zharikov et al. 2007). The genesis of this column is the result of a serie...
Raster images generalization in the context of research on the structure of landscape and geodiversity
Generalization is one of the most important stages of work on cartographic data. It has a particular importance in the study of landscape structure, especially geodiversity. In raster images, it is based on modifying the...
The application of electromagnetic methods for polymetallic prospecting in mining conditions
The paper presents selected results of geophysical surveys carried out in the copper mine named “Polkowice-Sieroszowice” in Lower Silesia, Poland. The aim of complex geophysical measurements was the analysis of the usefu...