Using Random Forest Tree Classification for Evaluating Vertical Cross-Sections in Epoxy Blocks to Get Unbiased Estimates for 3D Mineral Map

Öz

Areal mineral maps are constructed from the polished sections of particles that settle to the bottom of epoxy resin. However, heavy minerals can preferentially settle to the bottom, making the polished surface rich in heavy minerals. Therefore, polished sections will become biased estimates of the volumetric (3D) map. The study aims to test whether any vertical cross-section (any section along the settling direction of particles) can be an unbiased estimate of the 3D mineral map of a chromite ore sample. For the purpose of this study, 2D maps of the vertical cross-sections were acquired by using Random Forest classification coupled with image pre- and post-processing tools. Then, 3D mineral maps were converted from 2D maps without assuming stereological errors. The modal mineralogy and particle size distributions predicted from 3D maps were compared with the same features estimated from the particulate sample by XRD and dry sieving analyses, respectively. Any 2D map which yields a modal mineralogy and a size distribution similar to the true analyses was selected as an unbiased estimate of the true 3D map. The results suggest that any vertical cross-section is an unbiased estimate, unlike polished section at which heavier minerals settle preferentially.

Anahtar Kelimeler

• X-ray computed tomography,optical microscope,mineral map,polished section,vertical section

Kaynakça

1. [1] Chatterjee S., Bandopadhyay S. and Machuca D., " Ore grade prediction using a genetic algorithm and clustering Based ensemble neural network model ", Mathematical Geosciences, 42: 309 -326, (2010).
2. [2] Köse C., Alp I. and İkibaş C., " Statistical methods for segmentation and quantification of minerals in ore microscopy ", Minerals Engineering, 30: 19 -32, (2012).
3. [3] Mengko TR, Susilowati Y., Mengko R. and Leksono BE, " Digital image processing technique in rock forming minerals identification ", IEEE APCCAS 2000. 2000 IEEE Asia-Pacific Conf. Circuits Syst. Electron. Commun. Syst. (Cat. No.00EX394), 441 -444, (2000).
4. [4] Perez CA, Estévez PA, Vera PA, Castillo LE, Aravena CM, Schulz DA and Medina LE, " Ore grade estimation by feature selection and voting using boundary detection in digital image analysis ", International Journal of Mineral Processing, 101: 28 -36, (2011).
5. [5] Singh N., Singh T., Tiwary A. and Sarkar K., " Textural identification of basaltic rock mass using image processing and neural network ", Computational Geosciences, 14: 301 -310, (2010).
6. [6] Singh V. and Rao SM, " Application of image processing in mineral industry: a case study of ferruginous manganese ores ", Mineral Processing and Extractive Metallurgy (Trans. Inst. Min Met. C)., 115: 155 -160, (2006).
7. [7] Wang W., " Rock particle image segmentation and systems ", Pattern Recognition Techniques Technology and Applications, In-Teh, Crotia, (2008).
8. [8] King RP, " Modeling and Simulation of Mineral Processing Systems ", Butterworth-Heinemann, Oxford, (2001).

9. [9] Leigh GM, Lyman GJ and Gottlieb P., " Stereological estimates of liberation from mineral section measurements: A rederivation of Barbery’s formulae with extensions ", Powder Technology, 87: 141 -152 (1996).
10. [10] Petruk W., " Applied Mineralogy in the Mining Industry ", Elsevier, Ottawa, (2000).
11. [11] Schneider CL, Measurement and calculation of liberation in continuous milling circuit, Doctorate, The University of Utah, (1995).
12. [12] Wightman EM and Evans CL, Representing and interpreting the liberation spectrum in a processing context, Minerals Engineering, 61: 121 -125, (2014).
13. [13] Donskoi E., Raynlyn TD and Poliakov A., Image analysis estimation of iron ore particle segregation in epoxy blocks, Minerals Engineering, 120: 102 -109, (2018).
14. [14] Kwitko-Ribeiro R., "New Sample Preparation Developments to Minimize Mineral Segregation in Process Mineralogy", Proceedings of 10th International Congress on Applied Mineralogy, Trondheim, 411 -417, (2012).
15. [15] Lane GR, Martin C. and Pirard E., " Techniques and applications for predictive metallurgy and ore characterization using optical image analysis ", Minerals Engineering, 21: 568 -577, (2008).
16. [16] Camalan M., Çavur M. and Hoşten Ç., " Assessment of chromite liberation spectrum on microscopic images by means of a supervised image classification ", Powder Technology. 322: 214 -225, (2017).
17. [17] Lätti D. and Adair BJI, " An assessment of stereological adjustment procedures ", Minerals Engineering, 14: 1579 -1587, (2001).
18. [18] Breiman L., " Random forests ", Machine Learning, 45: 5 -32, (2001).
19. [19] Soille P. and Vincent LM, " Determining watersheds in digital pictures via flooding simulations ", SPIE Visual Communications and Image Processing ’90, 240 -250, (1990).
20. [20] Bartyzel K., " Adaptive Kuwahara filter ", Signal, Image and Video Processing, 10: 663 -670, (2016).
21. [21] Khorram F., Memarian H. and Tokhmechi B., " Limestone chemical components estimation using image processing and pattern recognition techniques ", Journal of Mining & Environment, 2: 126 -135, (2011).
22. [22] Arganda-Carreras I., Kaynig V., Rueden C., Eliceiri KW, Schindelin J., Cardona A. and Seung HS, " Trainable Weka Segmentation: A machine learning tool for microscopy pixel classification ", Bioinformatics. 33: 2424 -2426, (2017).
23. [23] Camalan M., Çavur M. and Hoşten Ç., " Assessment of chromite liberation spectrum on microscopic images by means of a supervised image classification ", Powder Technology, 322: 214 -225, (2017).
24. [24] Grant DC, Goudie DJ, Shaffer M. and Sylvester P., " A single-step trans-vertical epoxy preparation method for maximising throughput of iron-ore samples via SEM-MLA analysis ", Transactions of the Institutions of Mining and Metallurgy, Section B: Applied Earth Science, 125: 57 -62, (2016).