Advertisement

Ordinal Learning with Vector Space Based Binary Predicates and Its Application to Tahitian Pearls’ Luster Automatic Assessment

  • Gaël MondonneixEmail author
  • Sébastien Chabrier
  • Jean Martial Mari
  • Alban Gabillon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10884)

Abstract

Algorithms designed to solve instance ranking problems are often a trade-off between classification and regression. We propose to solve instance ranking problems where the classes have fixed boundaries by observing that such cases can be reduced to object ranking problems. Object ranking implies determining a total order, which should imply in turn a computational cost exponential with the number of items to order. However, solving this problem in the feature space allows taking advantage of linearity, so as to ensure total order properties at no particular computational cost, in particular, without having to explicitly check for acyclicity. The proposed method is tested for classifying Tahitian pearls against their luster using photographs of commercial culture pearls ranked by experts of the profession and compared with previous support vector machine (SVM) multiclass classification. While the SVM approach had more than \( 20\% \) of error (and more than \( 13\% \) after feature selection), our method allows predicting the class of a pearl with less than \( 10\% \) of error (and less than \( 8\% \) after feature selection). Ordinal learning makes better use of implicit rank information and significantly (\( p < 10^{-4} \)) reduces classification error.

Keywords

Instance ranking Object ranking Luster Pearls classification 

References

  1. 1.
    Fürnkranz, J., Hüllermeier, E.: Preference learning: an introduction. In: Fürnkranz, J., Hüllermeier, E. (eds.) Preference Learning, pp. 1–17. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-14125-6_1CrossRefzbMATHGoogle Scholar
  2. 2.
    Fürnkranz, J., Hüllermeier, E.: Pairwise preference learning and ranking. In: Lavrač, N., Gamberger, D., Blockeel, H., Todorovski, L. (eds.) ECML 2003. LNCS (LNAI), vol. 2837, pp. 145–156. Springer, Heidelberg (2003).  https://doi.org/10.1007/978-3-540-39857-8_15CrossRefzbMATHGoogle Scholar
  3. 3.
    Fürnkranz, J., Hüllermeier, E.: Preference learning and ranking by pairwise comparison. In: Fürnkranz, J., Hüllermeier, E. (eds.) Preference Learning, pp. 65–82. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-14125-6_4CrossRefzbMATHGoogle Scholar
  4. 4.
    Cohen, W.W., Schapire, R.E., Singer, Y.: Learning to order things. J. Artif. Intell. Res. 10, 451–457 (1999)Google Scholar
  5. 5.
    Slater, P.: Inconsistencies in a schedule of paired comparisons. Biometrika 48(3/4), 303–312 (1961)CrossRefGoogle Scholar
  6. 6.
    Hudry, O.: On the complexity of Slater’s problems. Eur. J. Oper. Res. 203(1), 216–221 (2010)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Shmoys, D.: Cut problems and their application to divide and conquer. In: Approximation Algorithms for NP-hard Problems, pp. 192–235 (1996)Google Scholar
  8. 8.
    Institut de la statistique de Polynésie française: Bilan de la perle (2014)Google Scholar
  9. 9.
  10. 10.
    Loesdau, M., Chabrier, S., Gabillon, A.: Automatic nacre thickness measurement of Tahitian pearls. In: Kamel, M., Campilho, A. (eds.) ICIAR 2015. LNCS, vol. 9164, pp. 446–455. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-20801-5_49CrossRefGoogle Scholar
  11. 11.
    Loesdau, M., Chabrier, S., Gabillon, A.: Hue and saturation in the RGB color space. In: Elmoataz, A., Lezoray, O., Nouboud, F., Mammass, D. (eds.) ICISP 2014. LNCS, vol. 8509, pp. 203–212. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-07998-1_23CrossRefGoogle Scholar
  12. 12.
    Loesdau, M., Chabrier, S., Gabillon, A.: Automatic classification of Tahitian pearls. In: Choras, R. (ed.) Image Processing & Communications Challenges 6. Advances in Intelligent Systems and Computing, AISC, vol. 313, pp. 95–101. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-10662-5_12CrossRefGoogle Scholar
  13. 13.
    Mondonneix, G., Chabrier, S., Mari, J.M., Gabillon, A., Barriot, J.P.: Tahitian pearls’ luster assessment. In: McDonald, J., Markham, C., Winstanley, A., (eds.) Proceedings of the 19th Irish Machine Vision and Image Processing Conference, pp. 186–193. Irish Pattern Recognition & Classification Society, Maynooth (2017)Google Scholar
  14. 14.
    Mondonneix, G., Chabrier, S., Mari, J.M., Gabillon, A.: Tahitian pearls’ luster assessment automation. In: Proceedings of the IEEE Applied Imagery Pattern Recognition Workshop: Big Data, Analytics, and Beyond (2017)Google Scholar
  15. 15.
    Mitchell, T.: Machine Learning. McGraw-Hill, New York City (1997)zbMATHGoogle Scholar
  16. 16.
    Charon, I., Hudry, O.: An updated survey on the linear ordering problem for weighted or unweighted tournaments. Ann. Oper. Res. 175(1), 107–158 (2010)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Gaël Mondonneix
    • 1
    Email author
  • Sébastien Chabrier
    • 1
  • Jean Martial Mari
    • 1
  • Alban Gabillon
    • 1
  1. 1.Géopôle du Pacifique Sud EA4238, LABEX CORAILUniversity of French PolynesiaPunaauiaFrench Polynesia

Personalised recommendations