The application of pattern recognition in the automatic classification of microscopic rock images

The classification of rocks is an inherent part of modern geology. The manual identification of rock samples is a time-consuming process, and-due to the subjective nature of human judgement-burdened with risk. In the course of the study discussed in the present paper, the authors investigated the possibility of automating this process. During the study, nine different rock samples were used. Their digital images were obtained from thin sections, with a polarizing microscope. These photographs were subsequently classified in an automatic manner, by means of four pattern recognition methods: the nearest neighbor algorithm, the K-nearest neighbor, the nearest mode algorithm, and the method of optimal spherical neighborhoods. The effectiveness of these methods was tested in four different color spaces: RGB, CIELab, YIQ, and HSV. The results of the study show that the automatic recognition of the discussed rock types is possible. The study also revealed that, if the CIELab color space and the nearest neighbor classification method are used, the rock samples in question are classified correctly, with the recognition levels of 99.8%.

[1]  Mariusz Flasiński,et al.  Towards constructing pattern recognition-based expert system for petrography and rock mechanics analysis , 2003 .

[2]  Venu Govindaraju,et al.  Automatic recognition of handwritten medical forms for search engines , 2009, International Journal of Document Analysis and Recognition (IJDAR).

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

[4]  Jerome H. Friedman,et al.  Flexible Metric Nearest Neighbor Classification , 1994 .

[5]  Mark Peternell,et al.  Automation of pattern recognition and fractal-geometry-based pattern quantification, exemplified by mineral-phase distribution patterns in igneous rocks , 2009, Comput. Geosci..

[6]  Roberto Tagliaferri,et al.  Textural identification of carbonate rocks by image processing and neural network: Methodology proposal and examples , 2005, Comput. Geosci..

[7]  José Luis Pons Rovira,et al.  Automatic fruit recognition: a survey and new results using Range/Attenuation images , 1999, Pattern Recognit..

[8]  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..

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

[10]  R. V. Rossel,et al.  Colour space models for soil science , 2006 .

[11]  Yang Song,et al.  IKNN: Informative K-Nearest Neighbor Pattern Classification , 2007, PKDD.

[12]  Marek R. Ogiela,et al.  Image languages in intelligent radiological palm diagnostics , 2006, Pattern Recognit..

[13]  Horst Langer,et al.  Pattern recognition of volcanic tremor data on Mt. Etna (Italy) with KKAnalysis - A software program for unsupervised classification , 2011, Comput. Geosci..

[14]  Ronald R. Yager,et al.  Mountain Clustering on Non-Uniform Grids Using P-Trees , 2005, Fuzzy Optim. Decis. Mak..

[15]  Naresh Singh,et al.  Textural identification of basaltic rock mass using image processing and neural network , 2010 .

[16]  Abraham Kandel,et al.  Introduction to Pattern Recognition: Statistical, Structural, Neural and Fuzzy Logic Approaches , 1999 .

[17]  Mariusz MŁynarczuk,et al.  Description and classification of rock surfaces by means of laser profilometry and mathematical morphology , 2010 .

[18]  Virginia C. Gulick,et al.  An automated mineral classifier using Raman spectra , 2013, Comput. Geosci..

[19]  Nicolas H. Younan,et al.  A pattern recognition based approach to consistency analysis of geophysical datasets , 2010, Comput. Geosci..

[20]  Heather Dunlop,et al.  Automatic Rock Detection and Classification in Natural Scenes , 2006 .

[21]  Doheon Lee,et al.  A kernel-based subtractive clustering method , 2005, Pattern Recognit. Lett..

[22]  Cheng-Jin Du,et al.  Comparison of three methods for classification of pizza topping using different colour space transformations , 2005 .

[23]  Javad Ghiasi-Freez,et al.  Semi-automated porosity identification from thin section images using image analysis and intelligent discriminant classifiers , 2012, Comput. Geosci..