Automated mineral identification algorithm using optical properties of crystals

A method has been developed to automatically characterize the type of mineral phases by means of digital image analysis using optical properties of crystals. The method relies on microscope automation, digital image acquisition, image processing and analysis. Two hundred series of digital images were taken from 45 standard thin sections using a digital camera mounted on a conventional microscope and then transmitted to a computer.CIELab color space is selected for the processing, in order to effectively employ its well-defined color difference metric for introducing appropriate color-based feature. Seven basic optical properties of minerals (A. color; B. pleochroism; C. interference color; D. birefringence; E. opacity; F. isotropy; G. extinction angle) are redefined. The Local Binary Pattern (LBP) operator and modeling texture is integrated in the Mineral Identification (MI) scheme to identify homogeneous regions in microscopic images of minerals.The accuracy of mineral identification using the method was %99, %98, %96 and %95 for biotite, hornblende, quartz and calcite minerals, respectively. The method is applicable to other minerals and phases for which individual optical properties of crystals do not provide enough discrimination between the relevant phases. On the basis of this research, it can be concluded that if the CIELab color space and the local binary pattern (LBP) are applied, it is possible to recognize the mineral samples with the accuracy of more than 98%. Display Omitted A novel automated mineral identification (MI) scheme is developed.Weighted color and texture features are employed for the MI task.The scheme uses CIELab color space equipped with the well-defined color metric ΔE.A mineral database is developed considering alteration and indicatrix.

[1]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Veerendra Singh,et al.  Application of image processing and radial basis neural network techniques for ore sorting and ore classification , 2005 .

[3]  Mariusz Mlynarczuk,et al.  The application of pattern recognition in the automatic classification of microscopic rock images , 2013, Comput. Geosci..

[4]  R. Marschallinger,et al.  Automatic mineral classification in the macroscopic scale , 1997 .

[5]  Alessandro Fornaciai,et al.  Dissolution/crystallization kinetics recorded in the 2002–2003 lavas of Stromboli (Italy) , 2009 .

[6]  J. Starkey,et al.  Edge detection in petrographic images , 1993 .

[7]  Brian J. Ross,et al.  Machine Vision and Applications Automatic Mineral Identification Using Genetic Programming , 2022 .

[8]  Frank Fueten,et al.  An artificial neural net assisted approach to editing edges in petrographic images collected with the rotating polarizer stage , 2007, Comput. Geosci..

[9]  M. K. Gökay,et al.  Color identification of some Turkish marbles , 2008 .

[10]  F. Fueten,et al.  Mineral identification using artificial neural networks and the rotating polarizer stage , 2001 .

[11]  Dougal A. Jerram,et al.  Quantifying the Building Blocks of Igneous Rocks: Are Clustered Crystal Frameworks the Foundation? , 2003 .

[12]  B. Rigg,et al.  Modification to the JPC79 Colour–difference Formula , 2008 .

[13]  Boguslaw Obara,et al.  Identification of transcrystalline microcracks observed in microscope images of a dolomite structure using image analysis methods based on linear structuring element processing , 2007, Comput. Geosci..

[14]  Harun Artuner,et al.  Application of Decision Tree Algorithm for classification and identification of natural minerals using SEM-EDS , 2015, Comput. Geosci..

[15]  Hisao Ito,et al.  Grain size distributions of fault rocks: A comparison between experimentally and naturally deformed granitoids , 2007 .

[16]  Y. Susilowati,et al.  Digital image processing technique in rock forming minerals identification , 2000, IEEE APCCAS 2000. 2000 IEEE Asia-Pacific Conference on Circuits and Systems. Electronic Communication Systems. (Cat. No.00EX394).

[17]  F. Fueten.  A computer-controlled rotating polarizer stage for the petrographic microscope , 1997 .

[18]  M. Topi,et al.  Robust texture classification by subsets of local binary patterns , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[19]  Matti Pietikäinen,et al.  Robust Texture Classification by Subsets of Local Binary Patterns , 2000, ICPR.

[20]  W. D. Nesse,et al.  Introduction to optical mineralogy , 1986 .

[21]  Ronald Woods,et al.  Raman microprobe mineral identification , 2001 .

[22]  Nurdan Akhan Baykan,et al.  Mineral identification using color spaces and artificial neural networks , 2010, Comput. Geosci..

[23]  Michael Egmont-Petersen,et al.  Image processing with neural networks - a review , 2002, Pattern Recognit..

[24]  Maria Petrou,et al.  Image processing - dealing with texture , 2020 .