Combined Effect of Cohort Selection and Decision Level Fusion in a Face Biometric System

  • Jogendra Garain
  • Ravi Kant Kumar
  • Dipak Kumar
  • Dakshina Ranjan Kisku
  • Goutam Sanyal
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 701)


There are different parameters which degrade the performance of a face biometric system due to their variations. The baseline biometric systems can get relief to some extent from this kind of negative effect by utilizing the information of the cohort images and fusion methods. But to achieve the set of suitable cohorts for each and every enrolled person is a task of great challenge. Determining the cohort subset using k-means clustering cohort selection based on the matching proximity is presented in this paper. SIFT and SURF are used as facial features to represent each face image and to calculate the similarity score between two face images. The clusters having highest and lowest centroid value are fused using union rule to form the target, user dependent cohort subset. The query-claimed matching scores are normalized with the help of T-norm cohort normalization technique. The scores after normalization are used in recognition separately for SIFT as well as SURF. Finally, the responses from the classifier for these two different features are fused at decision level to cover up the shortcomings of the cohort selection method if any. The experimental execution is done on FEI face database. This integrated face biometric system gains a significant hike in performance that evidences its effectiveness over baseline.


Face biometric system SIFT SURF K-means clustering Cohort score Cohort subset Score normalization technique Fusion 


  1. 1.
    Auckenthaler, R., Carey, M., Thomas, H.L.: Score normalization for text-independent speaker verification systems. Digit. Signal Proc. 10, 42–54 (2000)CrossRefGoogle Scholar
  2. 2.
    Merati, A., Poh, N., Kittler, J.: User-specific cohort selection and score normalization for biometric systems. IEEE Trans. Info. Forensics Secur. 7(4) (2012)Google Scholar
  3. 3.
    Merati, A., Poh, N., Kittler, J.: Extracting discriminative information from cohort models. In: Proceedings of 4th IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS), 1–6 (2010)Google Scholar
  4. 4.
    Garain, J., Kumar, R.K., Sanyal, G., Kisku, D.R.: Selection of user-dependent cohorts using Bezier curve for person identification. In: International Conference Image Analysis and Recognition, pp. 566–572. Springer International Publishing (2016)Google Scholar
  5. 5.
    Tistarelli, M., Sun, Y., Poh, N.: On the use of discriminative cohort score normalization for unconstrained face recognition. IEEE Trans. Inf. Forensics Secur. 9(12), 2063–2075 (2014)CrossRefGoogle Scholar
  6. 6.
    Aggarwal, G., Ratha, N.K., Bolle, R.M.: Biometric verification: looking beyond raw similarity scores. In: Proceedings of Computer Vision and Pattern Recognition Workshop, pp. 31–31 (2006)Google Scholar
  7. 7.
    Tulyakov, S., Zhang, Z., Govindaraju, V.: Comparison of combination methods utilizing T-normalization and second best score model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 1–5 (2008)Google Scholar
  8. 8.
    Lowe, D.G.: Distinctive image features from scale-invariant key points. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  9. 9.
    Bay, H., Tuytelaars, T., Van Gool, L.: May. surf: speeded up robust features. In: European conference on computer vision (pp. 404–417). Springer, Berlin, HeidelbergCrossRefGoogle Scholar
  10. 10.
    Garain, J., Shah, A., Kumar, R.K., Kisku, D.R., Sanyal, G.: BCP-BCS: best-fit cascaded matching paradigm with cohort selection using Bezier curve for individual recognition. In: Asian Conference on Computer Vision, pp. 377–390. Springer, Cham (2016)Google Scholar
  11. 11.
    Thomaz, C.E., Giraldi, G.A.: A new ranking method for Principal Components Analysis and its application to face image analysis. Image Vis. Comput. 28(6), 902–913 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Jogendra Garain
    • 1
  • Ravi Kant Kumar
    • 1
  • Dipak Kumar
    • 1
  • Dakshina Ranjan Kisku
    • 1
  • Goutam Sanyal
    • 1
  1. 1.Department of Computer Science and EngineeringNational Institute of Technology DurgapurDurgapurIndia

Personalised recommendations