Estimating the Serial Combination’s Performance from That of Individual Base Classifiers

  • Gian Luca Marcialis
  • Luca Didaci
  • Fabio Roli
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)


Although the large number of MCS topics, serial fusion of multiple classifiers has been poorly investigated so far. In this paper, we propose a model which, starting from the performance of individual classifiers and the traditional hypothesis of decision independence given the class, is able to estimate the performance, in terms of error rates, of the whole serial classification scheme. The model is tested on a large set of data sets and classifiers, and the importance of the basis hypothesis is evaluated under different scenarios, which can be in agreement or not with such hypothesis.


Serial System Biometric System Sequential Probability Ratio Test Rejection Region Random Split 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    El Gayar, N., Kittler, J., Roli, F. (eds.): MCS 2010. LNCS, vol. 5997. Springer, Heidelberg (2010)zbMATHGoogle Scholar
  2. 2.
    Sansone, C., Kittler, J., Roli, F. (eds.): MCS 2011. LNCS, vol. 6713. Springer, Heidelberg (2011)zbMATHGoogle Scholar
  3. 3.
    Suen, C.Y., Lam, L.: Multiple Classifier Combination Methodologies for Different Output Levels. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 52–66. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  4. 4.
    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On Combining Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)CrossRefGoogle Scholar
  5. 5.
    Pudil, P., Novovicova, J., Blaha, S., Kittler, J.: Multistage Pattern Recognition with Reject Option. In: Proc. 11th IAPR-ICPR International Conference, vol. 2, pp. 92–95 (1992)Google Scholar
  6. 6.
    Last, M., Bunke, H., Kandel, A.: A feature-based serial approach to classifier combination. Pattern Analysis and Applications 5(4), 385–398 (2002)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Sansone, C., Vento, M.: Signature verification: increasing performance by a multi-stage system. Pattern Analysis and Applications 3, 169–181 (2000)CrossRefGoogle Scholar
  8. 8.
    Pao, L., Trailovic, L.: The optimal order of processing sensor information in sequential multisensor fusion algorithms. IEEE Transactions on Automatic Control 45(8), 1532–1536 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Marcialis, G.L., Roli, F., Didaci, L.: Personal identity verification by serial fusion of fingerprint and face matchers. Pattern Recognition 42(11), 2807–2817 (2009)CrossRefzbMATHGoogle Scholar
  10. 10.
    Marcialis, G.L., Mastinu, P., Roli, F.: Serial fusion of multi-modal biometric systems. In: Proc. of IEEE International Workshop on Biometric Measurements and Systems for Security and Medical Applications, BioMS 2010 (2010), doi:10.1109/BIOMS.2010.5610438Google Scholar
  11. 11.
    Allano, L., Dorizzi, B., Garcia-Salicetti, S.: Tuning cost and performance in multi-modal biometric systems: a novel and consistent view of fusion strategies based on the Sequential Probability Ratio Test (SPRT). Pattern Recognition Letters 31, 884–890 (2010)CrossRefGoogle Scholar
  12. 12.
    Chow, C.K.: On optimum rejection error trade-off. IEEE Transactions on Information Theory 16(1), 41–46 (1970)CrossRefzbMATHGoogle Scholar
  13. 13.
    Fumera, G., Roli, F., Giacinto, G.: Reject Option with Multiple Thresholds. Pattern Recognition 33(12), 2099–2101 (2000)CrossRefGoogle Scholar
  14. 14.
    Frank, A., Asuncion, A.: UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine (2010),
  15. 15.
    Du, J., Ling, C.X., Zhou, Z.-H.: When Does Co-Training Work in Real Data? IEEE Transactions on Knowledge and Data Engineering 23(35), 788–799 (2011)CrossRefGoogle Scholar
  16. 16.
    Giusti, N., Masulli, F., Sperduti, A.: Theoretical and Experimental Analysis of a Two-Stage System for Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(7), 893–904 (2002)CrossRefGoogle Scholar
  17. 17.
    Senator, T.: Multi-stage classification. In: Proc. of IEEE 5th Int. Conf. on Data Mining, ICDM 2005 (2005)Google Scholar
  18. 18.
    Trapeznikov, K., Saligrama, V., Castanon, D.: Multi-stage classifier design. In: JMLR Asian Conference on Machine Learning (ACML 2012), pp. 1–16 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Gian Luca Marcialis
    • 1
  • Luca Didaci
    • 1
  • Fabio Roli
    • 1
  1. 1.Dept. of Electrical and Electronic EngineeringUniversity of CagliariCagliariItaly

Personalised recommendations