Yıl: 2020 Cilt: 28 Sayı: 2 Sayfa Aralığı: 1030 - 1043 Metin Dili: İngilizce DOI: 10.3906/elk-1906-60

Development of a supervised classification method to construct 2D mineral maps on backscattered electron images

Öz:
The Mineral Liberation Analyzer (MLA) can be used to obtain mineral maps from backscattered electron(BSE) images of particles. This paper proposes an alternative methodology that includes random forest classification,a prospective machine learning algorithm, to develop mineral maps from BSE images. The results show that theoverall accuracy and kappa statistic of the proposed method are 97% and 0.94, respectively, proving that random forestclassification is accurate. The accuracy indicators also suggest that the proposed method may be applied to classifyminerals with similar appearances under BSE imaging. Meanwhile, random forest predicts fewer middling particles withbinary and ternary composition, but the MLA predicts more middling particles only with ternary composition. Thesediscrepancies may arise because the MLA, unlike random forest, may also measure the elemental compositions of mineralsurfaces below the polished section.
Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık
  • [1] Charikinya E, Bradshaw S, Becker M. Characterizing and quantifying microwave induced damage in coarse sphalerite ore particles. Minerals Engineering 2015; 82: 14-24. doi: 10.1016/j.mineng.2015.07.020
  • [2] Sandmann D, Gutzmer J. Use of Mineral Liberation Analysis (MLA) in the characterization of lithium-bearing micas. Journal of Minerals and Materials Characterization and Engineering 2013; 1: 285-292.
  • [3] Batchelor AR, Jones DA, Plint S, Kingman SW. Increasing the grind size for effective liberation and flotation of a porphyry copper ore by microwave treatment. Minerals Engineering 2016; 94: 61-75. doi: 10.1016/j.mineng.2016.05.011
  • [4] Pascoe RD, Power MR, Simpson B. QEMSCAN analysis as a tool for improved understanding of gravity separator performance. Minerals Engineering 2007; 20: 487-495. doi:10.1016/j.mineng.2006.12.012
  • [5] Little L, Mainza AN, Becker M, Wiese JG. Using mineralogical and particle shape analysis to investigate enhanced mineral liberation through phase boundary fracture. Powder Technology 2016; 301: 794-804. doi: 10.1016/j.powtec.2016.06.052
  • [6] Bérubé MA, Marchand JC. Evolution of the mineral liberation characteristics of an iron ore undergoing grinding. International Journal of Mineral Processing 1984; 13: 223-237. doi: 10.1016/0301-7516(84)90005-X
  • [7] King RP. Particle populations and distribution functions. In: King RP (editor). Modeling and Simulation of Mineral Processing Systems. Oxford, UK: Butterworth-Heinemann, 2001, pp. 5-43.
  • [8] Lyman GJ. Method for interpolation of 2-D histogram data: application to mineral liberation data. Powder Technology 1995; 83: 133-138. doi: 10.1016/0032-5910(94)02949-O
  • [9] Schneider CL. Measurement and calculation of liberation in continuous milling circuit. PhD, University of Utah, Salt Lake City, UT, USA, 1995.
  • [10] Petruk W. Applied Mineralogy in the Mining Industry. Ottawa, Canada: Elsevier, 2000.
  • [11] Lane GR, Martin C, Pirard E. Techniques and applications for predictive metallurgy and ore characterization using optical image analysis. Minerals Engineering 2008; 21: 568-577. doi: 10.1016/j.mineng.2007.11.009
  • [12] Zhong C, Xu C, Lyu R, Zhang Z, Wu X et al. Enhancing mineral liberation of a Canadian rare earth ore with microwave pretreatment. Journal of Rare Earths 2018; 36: 215-224. doi: 10.1016/j.jre.2017.08.007
  • [13] Quinteros J, Wightman E, Johnson NW, Bradshaw D. Evaluation of the response of valuable and gangue minerals on a recovery, size and liberation basis for a low-grade silver ore. Minerals Engineering 2015; 74: 150-155. doi: 10.1016/j.mineng.2014.12.019
  • [14] Devasahayam S. Predicting the liberation of sulfide minerals using the breakage distribution function. Mineral Processing and Extractive Metallurgy Review 2014; 36: 136-144. doi: 10.1080/08827508.2014.898638
  • [15] Medina JF. Liberation-limited grade/recovery curves for auriferous pyrite ores as determined by high resolution x-ray microtomography. PhD, University of Utah, Salt Lake City, UT, USA, 2012.
  • [16] Finch JA, Gomez CO. Separability curves from image analysis data. Minerals Engineering 1989; 2: 565-568. doi: 10.1016/0892-6875(89)90090-3
  • [17] Leißner T, Mütze T, Bachmann K, Rode S, Gutzmer J et al. Evaluation of mineral processing by assessment of liberation and upgrading. Minerals Engineering 2013; 53: 171-173. doi: 10.1016/j.mineng.2013.07.018
  • [18] Craig JR, Vaughan DJ. Ore Microscopy and Ore Petrography. New York, NY, USA: John Wiley & Sons, 1994.
  • [19] Fandrich R, Gu Y, Burrows D, Moeller K. Modern SEM-based mineral liberation analysis. International Journal of Mineral Processing 2007; 84: 310-320. doi: 10.1016/j.minpro.2006.07.018
  • [20] Zhou J, Gu Y. Geometallurgical characterization and automated mineralogy of gold ores. In: Adams MD (editor). Gold Ore Processing. Amsterdam, Netherlands: Elsevier, 2016, pp. 95-111.
  • [21] Celik IB, Can NM, Sherazadishvili J. Influence of process mineralogy on improving metallurgical performance of a flotation plant. Mineral Processing and Extractive Metallurgy Review 2010; 32: 30-46. doi: 10.1080/08827508.2010.509678
  • [22] Donskoi E, Suthers SP, Fradd SB, Young JM, Campbell JJ et al. Utilization of optical image analysis and automatic texture classification for iron ore particle characterisation. Minerals Engineering 2007; 20: 461-471. doi: 10.1016/j.mineng.2006.12.005
  • [23] Delbem ID, Galéry R, Brandão PRG, Peres AEC. Semi-automated iron ore characterisation based on optical microscope analysis: quartz/resin classification. Minerals Engineering 2015; 82: 2-13. doi: 10.1016/j.mineng.2015.07.021
  • [24] Köse C, Alp İ, İkibaş C. Statistical methods for segmentation and quantification of minerals in ore microscopy. Minerals Engineering 2012; 30: 19-32. doi: 10.1016/j.mineng.2012.01.008
  • [25] Hunt J, Berry R, Walters S. Using mineral maps to rank potential processing behaviour. In: 25th International Mineral Processing Conference, Brisbane, Australia; 2010. pp. 2899-2905.
  • [26] Camalan, Çavur M, Hoşten Ç. Assessment of chromite liberation spectrum on microscopic images by means of a supervised image classification. Powder Technology 2017; 322: 214-225. doi: 10.1016/j.powtec.2017.08.063
  • [27] Neumann R, Stanley CJ. Specular reflectance data for quartz and some epoxy resins: implications for digital image analysis based on reflected light optical microscopy. In: Proceedings of the 9th International Congress for Applied Mineralogy. Brisbane, Australia; 2008. pp. 703-706.
  • [28] Poliakov A, Donskoi E. Automated relief-based discrimination of non-opaque minerals in optical image analysis. Minerals Engineering 2014; 55: 111-124. doi: 10.1016/j.mineng.2013.09.014
  • [29] Gu Y. Automated scanning electron microscope based mineral liberation analysis. Journal of Minerals & Materials Characterization & Engineering 2003; 2: 33-41.
  • [30] Sylvester PJ. Use of the mineral liberation analyzer (MLA) for mineralogical studies of sediments and sedimentary rocks. In: Quantitative Mineralogy and Microanalysis of Sediments and Sedimentary Rocks. St. John’s, NL, Canada: Mineralogical Association of Canada Short Course Series 42, 2012, pp. 1-16.
  • [31] Vizcarra TG, Wightman EM, Johnson NW, Manlapig EV. The effect of breakage mechanism on the mineral liberation properties of sulphide ores. Minerals Engineering 2010; 23: 374-382. doi: 10.1016/j.mineng.2009.11.012
  • [32] Breiman L. Random forests. Machine Learning 2001; 45: 5-32. doi: 10.1023/A:1010933404324
  • [33] Huang JJ, Siu WC, Liu TR. Fast image interpolation via random forests. IEEE Transactions on Image Processing 2015; 24: 3232-3245. doi: 10.1109/TIP.2015.2440751
  • [34] Amancio DR, Comin CH, Casanova D, Travieso G, Bruno M et al. A systematic comparison of supervised classifiers. PLoS ONE 2014; 9: 1-14. doi: 10.1371/journal.pone.0094137
  • [35] Arganda-Carreras I, Kaynig V, Schindelin J, Cardona A, Seung HS. Trainable Weka segmentation: a machine learning tool for microscopy image segmentation. In: Neuroscience 2014 Short Course 2 - Advances in Brain-scale, Automated Anatomical Techniques: Neuronal Reconstruction, Tract Tracing, and Atlasing. 2014, pp. 73-80.
  • [36] Bartyzel K. Adaptive Kuwahara filter. Signal, Image and Video Processing 2016; 10: 663-670. doi: 10.1007/s11760- 015-0791-3
  • [37] Praveen KS, Babu KP, Sreenivasulu M. Implementation of image sharpening and smoothing using filters. International Journal of Scientific Engineering and Applied Science 2016; 2: 7-14.
  • [38] Shavlik JW, Mooney RJ, Towell GG. Symbolic and neural learning algorithms: an experimental comparison. Machine Learning 1991; 6: 111-143.
  • [39] Meyer D, Leisch F, Hornik K. The support vector machine under test. Neurocomputing 2003; 55: 169-186.
  • [40] Huang J, Ling CX. Using AUC and accuracy in evaluating learning algorithms. IEEE Transactions on Knowledge and Data Engineering 2005; 17: 299-310.
  • [41] Kuhn M, Johnson, K. Applied Predictive Modeling. New York, NY, USA: Springer, 2013.
  • [42] Lind R. Open source software for image processing and analysis: picture this with ImageJ. In: Harland L, Forster M (editors). Open Source Software in Life Science Research, Woodhead Publishing Limited, 2012: pp. 131-149.
  • [43] Arganda-Carreras I, Kaynig V, Rueden C, Eliceiri KW, Schindelin J et al. Trainable Weka segmentation: a machine learning tool for microscopy pixel classification. Bioinformatics 2017; 33: 2424-2426. doi: 10.1093/bioinformatics/btx180
  • [44] Khorram F, Memarian H, Tokhmechi B. Limestone chemical components estimation using image processing and pattern recognition techniques. Journal of Mining & Environment 2011; 2: 126-135.
  • [45] Soille P, Vincent LM. Determining watersheds in digital pictures via flooding simulations. In: Kunt M (editor). SPIE Visual Communications and Image Processing ’90, 1990: pp. 240-250.
  • [46] Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters 2006; 27: 861-874.
  • [47] Stehman SV. Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment 1997; 62: 77-89. doi: 10.1016/S0034-4257(97)00083-7
  • [48] Murty PS, Tiwari H. Accuracy assessment of land use classification — a case study of Ken Basin. Journal of Civil Engineering and Architecture Research 2015; 2: 1199-1206.
  • [49] Figueroa G, Moeller K, Buhot M, Gloy G, Haberlah D. Advanced discrimination of hematite and magnetite by automated mineralogy. In: Proceedings of the 10th International Congress for Applied Mineralogy (ICAM); Berlin, Germany; 2011. pp. 197-204.
  • [50] Goldstein JI, Newbury DE, Michael JR, Ritchie NWM, Scott JHJ et al. Scanning Electron Microscopy and X-ray Microanalysis. New York, NY, USA: Springer, 2018.
  • [51] Reichelt R. Scanning Electron Microscopy. In: Hawkes PW, Spence JCH (editors). Science of Microscopy. New York, NY, USA: Springer, 1997, pp. 133-272.
APA CAMALAN M, ÇAVUR M (2020). Development of a supervised classification method to construct 2D mineral maps on backscattered electron images. Turkish Journal of Electrical Engineering and Computer Sciences, 28(2), 1030 - 1043. 10.3906/elk-1906-60
Chicago CAMALAN Mahmut,ÇAVUR Mahmut Development of a supervised classification method to construct 2D mineral maps on backscattered electron images. Turkish Journal of Electrical Engineering and Computer Sciences 28, no.2 (2020): 1030 - 1043. 10.3906/elk-1906-60
MLA CAMALAN Mahmut,ÇAVUR Mahmut Development of a supervised classification method to construct 2D mineral maps on backscattered electron images. Turkish Journal of Electrical Engineering and Computer Sciences, vol.28, no.2, 2020, ss.1030 - 1043. 10.3906/elk-1906-60
AMA CAMALAN M,ÇAVUR M Development of a supervised classification method to construct 2D mineral maps on backscattered electron images. Turkish Journal of Electrical Engineering and Computer Sciences. 2020; 28(2): 1030 - 1043. 10.3906/elk-1906-60
Vancouver CAMALAN M,ÇAVUR M Development of a supervised classification method to construct 2D mineral maps on backscattered electron images. Turkish Journal of Electrical Engineering and Computer Sciences. 2020; 28(2): 1030 - 1043. 10.3906/elk-1906-60
IEEE CAMALAN M,ÇAVUR M "Development of a supervised classification method to construct 2D mineral maps on backscattered electron images." Turkish Journal of Electrical Engineering and Computer Sciences, 28, ss.1030 - 1043, 2020. 10.3906/elk-1906-60
ISNAD CAMALAN, Mahmut - ÇAVUR, Mahmut. "Development of a supervised classification method to construct 2D mineral maps on backscattered electron images". Turkish Journal of Electrical Engineering and Computer Sciences 28/2 (2020), 1030-1043. https://doi.org/10.3906/elk-1906-60