A Self-tuning People Identification System from Split Face Components

  • Maria De Marsico
  • Michele Nappi
  • Daniel Riccio
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5414)


Multimodal systems can solve a number of problems found in unimodal approaches. We experimented going further along this line, by dividing the face into distinct regions (components) and processing each of them within a single subsystem. Such subsystems are then embedded in a more complex multicomponent architecture. In this way, typical tools of multimodal systems, such as reliability margins or fusion schemes, can be usefully extended to the single face biometry. An additional innovation element in this work is the definition of a global system auto-verification and auto-tuning policy able to produce a significant accuracy enhancement. The paper explores three integration architectures with different subsystem interconnection degree, demonstrating that a tight component interaction increases system accuracy and allows identifying unstable subsystems.


Face Recognition Probe Sequence Fusion Rule Equal Error Rate False Acceptance Rate 
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.
    Heisele, B., Ho, P., Wu, J., Poggio, T.: Face recognition: component-based versus global approaches. Computer Vision and Image Understanding 91, 6–21 (2003)CrossRefGoogle Scholar
  2. 2.
    Harandi, M.T., Ahmadabadi, M.N., Araabi, B.N.: A hierarchical face identification system based on facial components. In: Proceedings of the IEEE/ACS International Conference on Computer Systems and Applications, pp. 669–675 (2007)Google Scholar
  3. 3.
    Abate, A.F., Nappi, M., Riccio, D., Tucci, M.: Occluded face recognition by means of the IFS. In: Kamel, M.S., Campilho, A.C. (eds.) ICIAR 2005. LNCS, vol. 3656, pp. 1073–1080. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Viola P. and Jones M. Rapid object detection using a boosted cascade of simple features. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pages 511–518, 2001.Google Scholar
  5. 5.
    Open Source. Open source computer vision library (2006),
  6. 6.
  7. 7.
    Poh, N., Bengio, S.: Improving fusion with margin-derived confidence in biometric authentication tasks. In: Kanade, T., Jain, A., Ratha, N.K. (eds.) AVBPA 2005. LNCS, vol. 3546, pp. 474–483. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Abate A. F., Nappi M., Riccio D., and De Marsico M. Data normalization and fusion in multibiometric systems. In Proceedings of the 12th International Conference on Distributed Multimedia Systems (DMS 2007), pages 87–92, 2007.Google Scholar
  9. 9.
    Veeramachaneni, K., Osadciw, L., Varshney, P.K.: An adaptive multimodal biometric management algorithm. IEEE Transaction on Systems, Man, and Cybernetics-Part C: Applications and Reviews 35, 344–356 (2005)CrossRefGoogle Scholar
  10. 10.
    Martinez, A.M.: Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class. IEEE Transaction on Pattern Analisys and Machine Intelligence 24, 748–763 (2002)CrossRefGoogle Scholar
  11. 11.
    Abate, A.F., Nappi, M., Riccio, D., De Marsico, M.: Face, ear and fingerprint: Designing multibiometric architectures. In: Proceedings of the 14th International Conference on Image Analysis and Processing (ICIAP 2007), pp. 437–442 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Maria De Marsico
    • 2
  • Michele Nappi
    • 1
  • Daniel Riccio
    • 1
  1. 1.Universitá Degli Studi di SalernoFiscianoItaly
  2. 2.Universitá Degli Studi di Roma - La SapienzaRomaItaly

Personalised recommendations