Assessment of chromite liberation spectrum on microscopic images by means of a supervised image classification

Abstract Assessment of mineral liberation spectrum with all its aspects is essential for plant control and optimization. This paper aims to estimate 2D mineral map and its associated liberation spectrum of a particular chromite sample from optical micrographs by using Random Forest Classification, a powerful machine-learning algorithm implemented on a user-friendly and an open-source software. This supervised classification method can be used to accurately generate 2D mineral map of this chromite sample. The variation of the measured spectra with the sample size is studied, showing that images of 200 particles randomly selected from the optical micrographs are sufficient to reproduce liberation spectrum of this sample. In addition, the 2D spectrum obtained with this classification method is compared with the one obtained from the Mineral Liberation Analyzer (MLA). Although 2D mineralogical compositions obtained by the two methods are quite similar, microscopic analysis estimates poorer liberation than MLA due to the residual noise (misclassified gangue) generated by the classification. Nevertheless, we cannot compare the reliabilities of the two methods, as there is not a standard produce yet to quantify the accuracy of MLA analysis.

[1]  B.J.I. Adair,et al.  An assessment of stereological adjustment procedures , 2001 .

[2]  Krzysztof Bartyzel,et al.  Adaptive Kuwahara filter , 2016, Signal Image Video Process..

[3]  D. Bradshaw,et al.  Evaluation of the response of valuable and gangue minerals on a recovery, size and liberation basis for a low grade silver ore , 2015 .

[4]  M. Parian,et al.  Analysis of mineral grades for geometallurgy: Combined element-to-mineral conversion and quantitative X-ray diffraction , 2015 .

[5]  N. Lotter,et al.  Process mineralogy as a predictive tool for flowsheet design to advance the Kamoa project , 2016 .

[6]  H. Soltanian-Zadeh,et al.  Limestone chemical components estimation using image processing and pattern recognition techniques , 2011 .

[7]  Jian Zhang,et al.  Prediction of mineral liberation characteristics of comminuted particles of high grade ores , 2013 .

[8]  R. P. King,et al.  An Effective SEM-Based Image Analysis System for Quantitative Mineralogy , 1993 .

[9]  G. J. Lyman.  Method for interpolation of 2-D histogram data: application to mineral liberation data , 1995 .

[10]  James R. Craig,et al.  Ore Microscopy and Ore Petrography , 1981 .

[11]  Jan D. Miller,et al.  Significance of liberation characteristics in the fatty acid flotation of Florida phosphate rock , 2009 .

[12]  Snehamoy Chatterjee,et al.  Image-based quality monitoring system of limestone ore grades , 2010, Comput. Ind..

[13]  Elaine M. Wightman,et al.  Relating mineralogical and textural characteristics to flotation behaviour , 2015 .

[14]  E. Donskoi,et al.  Utilization of optical image analysis and automatic texture classification for iron ore particle characterisation , 2007 .

[15]  R. P. King,et al.  Comminution and liberation of minerals , 1994 .

[16]  J. F. Medina.  Liberation-limited grade/recovery curves for auriferous pyrite ores as determined by high resolution x-ray microtomography , 2012 .

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

[18]  Rolf Fandrich,et al.  Modern SEM based mineral liberation analysis , 2007 .

[19]  E. Vigneau,et al.  Number of particles for the determination of size distribution from microscopic images , 2000 .

[20]  Claudio A. Perez,et al.  Ore grade estimation by feature selection and voting using boundary detection in digital image analysis , 2011 .

[21]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[22]  Weixing Wang,et al.  Rock Particle Image Segmentation and Systems , 2008 .

[23]  C. L. Evans,et al.  Representing and interpreting the liberation spectrum in a processing context , 2014 .

[24]  G. Barbery.  Liberation 1, 2, 3: Theoretical analysis of the effect of space dimension on mineral liberation by size reduction☆ , 1992 .

[25]  Elaine M. Wightman,et al.  An integrated approach of predicting metallurgical performance relating to variability in deposit characteristics , 2015 .

[26]  Javier Montero,et al.  Determining the accuracy in image supervised classification problems , 2011, EUSFLAT Conf..

[27]  Thomas P. Meloy.  Liberation theory — Eight, modern, usable theorems , 1984 .

[28]  J. Oliveira,et al.  Modern Process Mineralogy: Two case studies ☆ , 2011 .

[29]  Ilya Levner,et al.  Ore image segmentation by learning image and shape features , 2009, Pattern Recognit. Lett..

[30]  E. Donskoi,et al.  Modelling and optimization of hydrocyclone for iron ore fines beneficiation — using optical image analysis and iron ore texture classification , 2008 .

[31]  I. B. Celik,et al.  Influence of Process Mineralogy on Improving Metallurgical Performance of a Flotation Plant , 2010 .

[32]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[33]  Thomas Mütze,et al.  Evaluation of mineral processing by assessment of liberation and upgrading , 2013 .

[34]  Eric Pirard,et al.  Particle texture analysis using polarized light imaging and grey level intercepts , 2007 .

[35]  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).

[36]  Przemysław Tymków,et al.  Accuracy assessment of automatic image processing for land cover classification of St. Petersburg protected area , 2014 .

[37]  P. Gottlieb,et al.  Stereological estimates of liberation from mineral section measurements: A rederivation of Barbery's formulae with extensions , 1996 .

[38]  R. D. Pascoe,et al.  QEMSCAN analysis as a tool for improved understanding of gravity separator performance , 2007 .

[39]  R. King.  A model for the quantitative estimation of mineral liberation by grinding , 1979 .

[40]  E. Lester,et al.  Proximate and ultimate analysis correction for kaolinite-rich Chinese coals using mineral liberation analysis , 2016 .

[41]  C. Philander,et al.  The application of a novel geometallurgical template model to characterise the Namakwa Sands heavy mineral deposit, West Coast of South Africa , 2013 .

[42]  Chris Martin,et al.  Techniques and applications for predictive metallurgy and ore characterization using optical image analysis , 2008 .

[43]  Gianni Schena,et al.  Conceiving a high resolution and fast X-ray CT system for imaging fine multi-phase mineral particles and retrieving mineral liberation spectra , 2007 .

[44]  Suhasini Rao,et al.  Application of image processing in mineral industry: a case study of ferruginous manganese ores , 2006 .

[45]  Elaine M. Wightman,et al.  The effect of breakage mechanism on the mineral liberation properties of sulphide ores , 2010 .

[46]  Wan-Chi Siu,et al.  Fast Image Interpolation via Random Forests , 2015, IEEE Transactions on Image Processing.

[47]  Cecilia Lund,et al.  Development of a geometallurgical framework to quantify mineral textures for process prediction , 2015 .

[48]  J. Zhou,et al.  Geometallurgical Characterization and Automated Mineralogy of Gold Ores , 2016 .

[49]  Cevat Ikibas,et al.  Statistical methods for segmentation and quantification of minerals in ore microscopy , 2012 .

[50]  Dee Bradshaw,et al.  Characterising chalcopyrite liberation and flotation potential: Examples from an IOCG deposit , 2011 .

[51]  Jan D. Miller,et al.  Cone beam X-ray microtomography for three-dimensional liberation analysis in the 21st century , 1996 .

[52]  R. Galery,et al.  Semi-automated iron ore characterisation based on optical microscope analysis: Quartz/resin classification , 2015 .

[53]  Rob Lind.  Open source software for image processing and analysis: picture this with ImageJ , 2012 .

[54]  W. Petruk,et al.  Applied Mineralogy in the Mining Industry , 2000 .

[55]  M. Minnis.  An Automatic Point-Counting Method for Mineralogical Assessment , 1984 .