Cascade of Fusion for Adaptive Classifier Combination Using Context-Awareness

  • Mi Young Nam
  • Suman Sedai
  • Phill Kyu Rhee
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4069)


This paper proposes a novel adaptive classifier combination scheme based on the cascade of classifier selection and fusion, called adaptive classifier combination scheme (ACCS). In the proposed scheme, system working environment is learned and the environmental context is identified. GA is used to search most effective classifier systems for each identified environmental context. The group of selected classifiers is combined based on GA model for reliable fusion. The knowledge of individual context and its associated chromo-somes representing the optimal classifier combination is stored in the context knowledge base. Once the context knowledge is accumulated the system can react to dynamic environment in real time. The proposed scheme has been tested in area of face recognition using standard FERET database, taking illumi-nation as an environmental context. Experimental result showed that using context awareness in classifier combination provides robustness to varying environmental conditions.


Genetic Algorithm Face Recognition Face Image Environmental Context Fusion Method 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kuncheva, L.I.: Switching between selection and fusion in combining classifiers: An experiment. IEEE Transactions On Systems Man And Cybernetics, Part B-cybernetics 32(2), 146–156 (2002)CrossRefGoogle Scholar
  2. 2.
    Kuncheva, L.I., Bezdek, J.C., Duin, R.P.W.: Decision templates for multiple classifier fusion: An experimental comparison. Pattern Recognit. 34(2), 299–314 (2001)MATHCrossRefGoogle Scholar
  3. 3.
    Nam, M.Y., Rhee, P.K.: A Novel Image Preprocessing by Evolvable Neural Network, LNCS(LNAI), vol. 3214, vol. 3, pp. 843–854 (2004)Google Scholar
  4. 4.
    Nam, M.Y., Rhee, P.K.: An Efficient Face Recognition for Variant Illumination Condition. In: ISPACS 2005, vol. 1, pp. 111–115 (2004)Google Scholar
  5. 5.
    Roli, F., Raudys, Š., Marcialis, G.L.: An experimental comparison of fixed and trained fusion rules for crisp classifier outputs. In: Roli, F., Kittler, J. (eds.) MCS 2002. LNCS, vol. 2364, p. 232. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  6. 6.
    Goldberg, D.E.: Genetic Algorirhnis iri Search. Optimiation, arid Machine Leaniirrg. Addison-Wesley, Reading (1989)Google Scholar
  7. 7.
    Huang, Y.S., Suen, C.Y.: A Method of Combining Multiple Classifiers–A Neural Network Approach. In: Proc. of IWFHR-3, pp. 11–20 (1993)Google Scholar
  8. 8.
    Wang, X., Tang, X.: A Unified Framework for Subspace Face Recognition. IEEE Trans. on PAMI 26(9), 1222–1228 (2004)MathSciNetGoogle Scholar
  9. 9.
    Kuncheva, L.I.: A Theoretical Study on Six Classifier Fusion Strategies. IEEE on PAMI 24(2) (2002)Google Scholar
  10. 10.
    Jeon, I.J., Nam, M.-Y., Rhee, P.K.: Adaptive Gabor Wavelet for Efficient Object Recognition. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS, vol. 3682, pp. 308–318. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  11. 11.
    Nam, M.-Y., Rhee, P.K.: Adaptive Classifier Combination for Visual Information Processing Using Data Context-Awareness. In: Famili, A.F., Kok, J.N., Peña, J.M., Siebes, A., Feelders, A. (eds.) IDA 2005. LNCS, vol. 3646, pp. 260–271. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Pȩkalska, E., Duin, R.P.W.: Dissimilarity representations allow for building good classifiers. Pattern Recognition Letters 23(8), 943–956 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Mi Young Nam
    • 1
  • Suman Sedai
    • 1
  • Phill Kyu Rhee
    • 1
  1. 1.Dept. of Computer Science & EngineeringInha UniversityIncheonKorea

Personalised recommendations