Abstract
Lithological classification and monitoring of ore quality are challenging issues in mine operation, especially to maintain desired feed for processing minerals plants. Quantification of visual features is an innovative method to analyze rock components. In this paper, an analysis of vision-based rock type and classification algorithm is proposed for fast, inexpensive, and reliable identification process compared with common chemical analysis. To evaluate the proposed algorithm, samples were collected from the Novin limestone mine in Iran. Based on chemical and thin-section studies, the samples were classified into three different groups as calcium carbonate, dolomite, and dolomitic limestone. The limestone samples were crushed, sieved, and, respectively, divided into three size fractions as 2.5–7, 1.5–2.5, and 0.1–1.5 cm. A set of 58 images as large and medium size samples and 78 images as fine size samples were taken in the laboratory environment. Features were extracted from the captured images and reduced by applying principal component analysis (PCA). The support vector machine (SVM) and Bayesian techniques were used for classification. The best classification accuracy was about 80 and 90% in limestone and dolomite rock samples, respectively. Then, a multi-layer perceptron (MLP) neural network was employed to predict chemical compositions percentages. The determination coefficient within the range of 0.76 to 0.85 was observed and predicted values confirmed good performance of the grade estimation. The outputs illustrated that the proposed intelligent and automated technique can be successfully applied to monitor ore grade and classify lithology in different stages of mining projects.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
ASTM International (2011) ASTM C-25 standard test methods for chemical analysis of limestone, quicklime, and hydrated lime. West Conshohocken, PA, 38 pp
Barker AJ (2014) A key for identification of rock-forming minerals in thin section. CRC Press, 171 pp
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York
Bonifazi G (1995) Digital multi-spectral techniques and automated image analysis procedures for industrial ore modeling. Miner Eng 8:779–794
Casali A, Gonzalez G, Vallebuona G, Perezq C, Vargas R (2001) Grind ability soft-sensors based on lithological composition and on-line measurements. Miner Eng 14:689–700
Chatterjee, S., 2006 Geostatistical and image based quality control models for Indian mineral industry, Ph.D. Thesis dissertation, IIT Kharagour, India, 272 pp.
Chatterjee S (2013) Vision-based rock-type classification of limestone using multi-class support vector machine. Appl Intell 39:14–27
Chatterjee S, Bhattacherjee A, Samanta B, Pal SK (2010) Image-based quality monitoring system of limestone ore grades. Comput Ind 61:391–408
Cheeseman P, Self M, Kelly J, Taylor W, Freeman D, Stutz JC (1988) Bayesian classification. In AAAI 88:607–611
Donskoi E, Poliakov A, Manuel JR, Peterson M, Hapugoda S (2015) Novel developments in optical image analysis for iron ore, sinter and coke characterization. Appl Earth Sci 124:227–244
Dorador J, Rodríguez-Tovar FJ (2016) High resolution digital image treatment to color analysis on cores from IODP Expedition 339: approaching lithologic features and bioturbational influence. Mar Geol 377:127–135
Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New York, 512 pp
Fernandez, R., Viennet, E., Goles, E., Barrientos, R., Telias, M., 1995. On-line coarse ore granulometric analyzer using neural networks, in proceedings of ICANN’95 Paris, industrial session volume, pp. 59-68
Galdames FJ, Perez CA, Estévez PA, Adams M (2017) Classification of rock lithology by laser range 3D and color images. Int J Miner Process 160:47–57
Gonzalez RC, Woods RE (2002) Digital image processing. Prentice-hall, New Jersey, 793 pp
Jouini MS, Vega S, Al-Ratrout A (2015) Numerical estimation of carbonate rock properties using multiscale images. Geophys Prospect 63(2):405–421
Khorram F, Memarian H, Tokhmechi B, Soltanianzadeh H (2011) Limestone chemical components estimation using image processing and pattern recognition techniques. J Min Environ 2:49–58
Laine A, Fan J (1993) Texture classification by wavelet packet signatures. IEEE Trans Pattern Anal Machine Intell 15:1186–1191
Marschallinger R (1997) Automatic mineral classification in the macroscopic scale. Comput Geosci 23:119–126
Meyer-Baese A, Schmid VJ (2014) Pattern recognition and signal analysis in medical imaging. Elsevier, 444 pp
Murtagh F, Qiao X, Crookes D, Walsh P, Basheer PAM, Long A, Starck JL (2005) A machine vision approach to the grading of crushed aggregate. Mach Vis Appl 16:229–235
Murtagh F, Starck JL (2008) Wavelet and curvelet moments for image classification: application to aggregate mixture grading. Pattern Recogn Lett 29:1557–1564
Oestreich J, Tolley W, Rice D (1995) The development of a color sensor system to measure mineral compositions. Miner Eng 8:31–39
Olkin I, Ghurye SG, Hoeffding W, Madow WG, Mann HB (1960) Contributions to probability and statistics, essays in honor of Harold Hotelling, Stanford University Press, 520 pp.
Patel AK, Chatterjee S (2016) Computer vision-based limestone rock-type classification using probabilistic neural network. Geosci Front 7(1):53–60
Perez C, Casali A, Gonzalez G, Vallebuona G, Vargas R (2000) Lithological composition sensor based on digital image feature extraction, genetic selection of features and neural classification, international conference on information intelligence and systems (ICIIS’99). Bethesda, MD, pp 236–241
Perez CA, Estévez PA, Vera PA, Castillo LE, Aravena CM, Schulz DA, Medina LE (2011) Ore grade estimation by feature selection and voting using boundary detection in digital image analysis. Int J Miner Process 101(1):28–36
Rao C, Tutumluer E (2000) Determination of volume of aggregates: new image analysis approach. Transp Res Board 1721:73–80
Salinas RA, Raff U, Farfan C (2005) Automated estimation of rock fragment distributions using computer vision and its application in mining. IEE Proc Vis Image Sig Proces 152:1–8
Saxena N, Mavko G, Hofmann R, Srisutthiyakorn N (2017) Estimating permeability from thin sections without reconstruction: digital rock study of 3D properties from 2D images. Comput Geosci 102:79–99
Schölkopf B, Burges C, Smola A (2000) Advances in kernel methods—support vector learning. MA, MIT Press, Cambridge
Vapnik VN (1995) The nature of statistical learning theory. Springer-Verlag, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Khorram, F., Morshedy, A.H., Memarian, H. et al. Lithological classification and chemical component estimation based on the visual features of crushed rock samples. Arab J Geosci 10, 324 (2017). https://doi.org/10.1007/s12517-017-3116-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-017-3116-8