Applied Intelligence

, Volume 39, Issue 1, pp 14–27 | Cite as

Vision-based rock-type classification of limestone using multi-class support vector machine

  • Snehamoy ChatterjeeEmail author


Rock-type classification is a challenging and difficult job due to the heterogeneous properties of rocks. In this paper, an image-based rock-type analysis and classification method is proposed. The study was conducted at a limestone mine in western India using stratified random sampling from a case study mine. The analysis of collected sample images was performed in laboratory. Color, morphology, and textural features were extracted from the captured image and a total of 189 features were recorded. The multi-class support vector machine (SVM) algorithm was then applied for rock-type classification. The hyper-parameters and the number of input features of the SVM model were selected by genetic algorithm. The results revealed that the SVM model performed best when 40 features were selected out of the 189 extracted features. The results demonstrated that the overall accuracy of the proposed technique for rock type classification is 96.2 %. A comparative study shows that the proposed SVM model performed better than a competing neural network model in this case study mine.


Image classification Support vector machine Feature selection Genetic algorithm 


  1. 1.
    Donskoi E, Suthers S, Fradd S, Young J, Campbell J, Raynlyn T, Clout J (2007) Utilization of optical image analysis and automatic texture classification for iron ore particle characterization. Miner Eng 20(5):461–471 CrossRefGoogle Scholar
  2. 2.
    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(1–4):28–36 CrossRefGoogle Scholar
  3. 3.
    Kulatilake PHSW, Hudaverdi T, Wu Q (2012) New prediction models for mean particle size in rock blast fragmentation. Geotech Geolog Eng 30(3):665–684 CrossRefGoogle Scholar
  4. 4.
    Singh N, Singh TN, Tiwary A, Sarkar KM (2010) Textural identification of basaltic rock mass using image processing and neural network. Comput Geosci 14(2):301–310 zbMATHCrossRefGoogle Scholar
  5. 5.
    Tessier J, Duchesne C, Bartolacci G (2007) A machine vision approach to on-line estimation of run-of-mine ore composition on conveyor belts. Miner Eng 20(12):1129–1144 CrossRefGoogle Scholar
  6. 6.
    Remy N, Boucher A, Wu J (2009) Applied geostatistics with SGeMs: a users’s guide. Cambridge University Press, Cambridge CrossRefGoogle Scholar
  7. 7.
    Perez C, Casali A, Gonzalez G, Vallebuona G, Vargas R (1999) Lithological composition sensor based on digital image feature extraction, genetic selection of features and neural classification. In: International conference on information intelligence and systems (ICIIS’99), p 236 Google Scholar
  8. 8.
    Casali G, Vallebuona C, Pérez G, Vargas R (2000) Lithological composition and ore grindability sensors, based on image analysis. In: Proc. of the XXI IMPC, Rome, p A1(9-16) Google Scholar
  9. 9.
    Singh V, Rao SM (2005) Application of image processing and radial basis neural network techniques for ore sorting and ore classification. Miner Eng 18:1412–1420 CrossRefGoogle Scholar
  10. 10.
    Lepisto L, Kunttu I, Visa A (2005) Rock image classification using color features in Gabor space. J Electron Imaging 14(4):28–36 CrossRefGoogle Scholar
  11. 11.
    Hunter GC, McDermott C, Miles NJ, Singh A, Scoble MJ (1990) A review of image analysis techniques for measuring blast fragmentation. Min Sci Technol 11:19–36 CrossRefGoogle Scholar
  12. 12.
    Wang W (2008) Rock particle image segmentation and systems in pattern recognition. In: Yin P-Y (ed) Pattern recognition techniques, technology and applications. InTech, Rijeka, pp 197–226 Google Scholar
  13. 13.
    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 Signal Process 152(1):1–8 CrossRefGoogle Scholar
  14. 14.
    Petersen K, Aldrich C, Vandeventer JSJ (1998) Analysis of ore particles based on textural pattern recognition. Miner Eng 11:959–977 CrossRefGoogle Scholar
  15. 15.
    Kachanubal T, Udomhunsakul S (2008) Rock textures classification based on textural and spectral features. Int J Comput Intell 4:240–246 Google Scholar
  16. 16.
    Lin CL, Yen YK, Miller JD (1993) Evaluation of a pc image- based on-line coarse particle size analyzer. In: Emerging computer techniques for the minerals industry, society for mining, metallurgy, and exploration, inc, Littleton, Colorado, pp 201–210 Google Scholar
  17. 17.
    Steppe JM, Bauer KW, Rogers SK (1996) Integrated feature and architecture selection. IEEE Trans Neural Netw 7:1007–1014 CrossRefGoogle Scholar
  18. 18.
    Duda RO, Hart PE (2000) Pattern classification. Wiley-Interscience, New York Google Scholar
  19. 19.
    Chatterjee S, Bhattacherjee A, Samanta B, Pal SK (2008) Rock-type classification of an iron ore deposit using digital image analysis technique. Int J Min Miner Eng 1:22–46 CrossRefGoogle Scholar
  20. 20.
    Chatterjee S, Bhattacherjee A, Samanta B, Pal SK (2009) Image-based quality monitoring system of limestone ore grades. Comput Ind 61:391–408 CrossRefGoogle Scholar
  21. 21.
    Chen X (2003) An improved branch and bound algorithm for feature selection. Pattern Recognit Lett 24(12):1925–1933 CrossRefGoogle Scholar
  22. 22.
    Somol P, Pudil P, Kittler J (2004) Fast branch & bound algorithms for optimal feature selection. IEEE Trans Pattern Anal Mach Intell 26(7):900–912 CrossRefGoogle Scholar
  23. 23.
    Hong J, Cho S (2006) Efficient huge-scale feature selection with speciated genetic algorithm. Pattern Recognit Lett 27:143–150 CrossRefGoogle Scholar
  24. 24.
    Osma-Ruiz V, Godino-Llorente JI, Sáenz-Lechón N, Gómez-Vilda P (2007) An improved watershed algorithm based on efficient computation of shortest paths. Pattern Recognit 40(3):1078–1090 zbMATHCrossRefGoogle Scholar
  25. 25.
    Gonzalez RC, Woods RE, Eddins SL (2004) Segmentation using the watershed transform. In: Digital image processing using MATLAB. Pearson Prentice-Hall, Upper Saddle River Google Scholar
  26. 26.
    Ng HF (2006) Automatic thresholding for defect detection. Pattern Recognit Lett 27(14):1644–1649 CrossRefGoogle Scholar
  27. 27.
    Solomon C, Breckon T (2011) Fundamentals of digital image processing: a practical approach with examples in Matlab, E-book. Willey, New York Google Scholar
  28. 28.
    Cuisenaire O (2006) Locally adaptable mathematical morphology using distance transformations. Pattern Recognit 39(3):405–416 zbMATHCrossRefGoogle Scholar
  29. 29.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66 CrossRefGoogle Scholar
  30. 30.
    Cuevas E, Sención F, Zaldivar D, Pérez-Cisneros M, Sossa H (2012) A multi-threshold segmentation approach based on artificial bee colony optimization. Appl Intell 37(3):321–336 CrossRefGoogle Scholar
  31. 31.
    Saha S, Bandyopadhyay S (2011) Automatic MR brain image segmentation using a multiseed based multiobjective clustering approach. Appl Intell 35(3):411–427 CrossRefGoogle Scholar
  32. 32.
    Haralick RM, Shapiro LG (1992) Computer and robot vision 1 & 2. Addison-Wesley, Reading Google Scholar
  33. 33.
    Chatterjee S, Bhattacherjee A (2011) Genetic Algorithms for feature selection of image analysis-based quality monitoring model: an application to an iron mine. Eng Appl Artif Intell 24(5):786–795 CrossRefGoogle Scholar
  34. 34.
    Huang YL, Chen DR, Jiang YR, Kuo SJ, Wu HK, Moon WK (2008) Computer-aided diagnosis using morphological features for classifying breast lesions on ultrasound. Ultrasound Obstet Gynecol 32:565–572 CrossRefGoogle Scholar
  35. 35.
    Lefkaditis D, Tsirigotis G (2009) Morphological feature selection and neural classification for electronic components. J Eng Sci Technol Rev 2(1):151–156 Google Scholar
  36. 36.
    McNitt-Gray MF, Huang HK, Sayre JW (1995) Feature selection in the pattern classification problem of digital chest radiograph segmentation. IEEE Trans Med Imaging 14(3):537–547 CrossRefGoogle Scholar
  37. 37.
    Zucker SW, Terzopoulos D (1980) Finding structure in co-occurrence matrices for texture analysis. Comput Graph Image Process 12:286–308 CrossRefGoogle Scholar
  38. 38.
    Haralick RM (1979) Statistical and structural approaches to texture. Proc IEEE 67(5):786–804 CrossRefGoogle Scholar
  39. 39.
    Galloway MM (1975) Texture analysis using gray level run lengths. Comput Graph Image Process 4:172–179 CrossRefGoogle Scholar
  40. 40.
    Chu A, Sehgal CM, Greenleaf JF (1990) Use of gray value distribution of run lengths for texture analysis. Pattern Recognit Lett 11(6):415–420 zbMATHCrossRefGoogle Scholar
  41. 41.
    Dasarathy BR, Holder EB (1991) Image characterizations based on joint gray-level run-length distributions. Pattern Recognit Lett 12:497–502 CrossRefGoogle Scholar
  42. 42.
    Vapnik VN (1995) The nature of statistical learning theory. Springer, New York zbMATHCrossRefGoogle Scholar
  43. 43.
    Dioşan L, Rogozan A, Pecuchet JP (2012) Improving classification performance of Support Vector Machine by genetically optimising kernel shape and hyper-parameters. Appl Intell 36(2):280–294 CrossRefGoogle Scholar
  44. 44.
    Lee LH, Wan CH, Rajkumar R, Isa D (2012) An enhanced Support Vector Machine classification framework by using Euclidean distance function for text document categorization. Appl Intell 37(1):80–99 CrossRefGoogle Scholar
  45. 45.
    Rifkin R, Mukherjee S, Tamayo P, Ramaswamy S, Yeang CH, Angelo M, Reich M, Poggio T, Lander ES, Golub TR, Mesirov JP (2003) An analytical method for multi-class molecular cancer classification. SIAM Rev 45:706–723 MathSciNetzbMATHCrossRefGoogle Scholar
  46. 46.
    Li Y, Zeng X (2010) Sequential multi-criteria feature selection algorithm based on agent genetic algorithm. Appl Intell 33(2):117–131 CrossRefGoogle Scholar
  47. 47.
    Vinh LT, Lee S, Park YT, d’Auriol BJ (2012) A novel feature selection method based on normalized mutual information. Appl Intell 37(1):100–120 CrossRefGoogle Scholar
  48. 48.
    Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison-Wesley, Reading zbMATHGoogle Scholar
  49. 49.
    Congdon CB (1995) A comparison of genetic algorithm and other machine learning systems on a complex classification task from common disease research. PhD thesis, Computer Science and Engineering Division, Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA Google Scholar
  50. 50.
    Ranawana R, Palade V (2005) MVGen—ensemble learning for MCS majority voting with a genetic algorithm. Internal Report, Oxford University Computing Laboratory Google Scholar
  51. 51.
    Chatterjee S (2006) Geostatistical and image-based quality control models for indian mineral industry. Unpublished PhD Thesis dissertation, IIT Kharagpur, India Google Scholar
  52. 52.
    Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, New York zbMATHGoogle Scholar
  53. 53.
    Kim K, Ahn H (2012) Simultaneous optimization of artificial neural networks for financial forecasting. Appl Intell 36(4):887–898 MathSciNetCrossRefGoogle Scholar
  54. 54.
    Nekoukar V, Beheshti MTH (2010) A local linear radial basis function neural network for financial time-series forecasting. Appl Intell 33(3):352–356 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  1. 1.Dept. of Mining EngineeringNational Institute of Technology RourkelaOrissaIndia

Personalised recommendations