Advertisement

MUBAI: multiagent biometrics for ambient intelligence

  • Andrea F. AbateEmail author
  • Maria De Marsico
  • Daniel Riccio
  • Genny Tortora
Original Research

Abstract

Present technological progress opens new scenarios, where people can interact with electronic equipment which is embedded in every-day objects and settings. The so called ambient intelligence allows to automatically detect context from wearable or environmental sensor systems and to exploit such information for adaptive support. Domotic systems are a spreading example of such philosophy. Advanced sensors and devices make up context-aware environments which are sensitive and responsive to the presence of users. When each single user in a set can be recognized, it is possible to provide enhanced personalization of functionalities and services. Recognition in such situations is preferably not bound to a voluntary, or conscious at least, user’s interaction with the equipment, but rather relies on the ability of an underlying control system to automatically and autonomously catch some user’s characteristic and to use it for identification. This implicit requirement makes reference to biometric techniques. We propose here Multiagent Biometrics for Ambient Intelligence (MUBAI) architecture, which specifies the composition of more biometric modules in a multiagent recognition system. In principle, each module implements an autonomous agent, which performs its own recognition process; however, not all such agents are equally reliable on any single input. System Response Reliability (SRR) allows to assess reliability on a single-response basis, and is a crucial element during fusion of agents’ results. A further improvement is obtained by communication/collaboration activities, which are a core characteristic of multiagent systems. MUBAI architecture exploits two types of agents, according to the “the brawn and the brains” approach: more Classifier Agents perform biometric processing on (possibly) different traits exploiting the inter-agent communication ruled by the N-Cross Testing Protocol. A different type of agent implements a Supervisor Module to produce a final recognition result and to possibly update Classifiers’ parameters. Such agent allows overcoming the parameter invariance to which present multibiometric architectures are bound. In the experiments presented in this paper, the assessed MUBAI instance includes four modules implementing different face recognition techniques, and a supervisor module. The obtained results demonstrated how MUBAI allows to achieve far better performances than single classifiers. As a further contribution, we show how MUBAI architecture can also be used in a dynamic setting, where new agents added from time to time to the system can be effectively trained online.

Keywords

Biometrics Multi-agent 

References

  1. Aarts E, Harwig R, Schuurmans M (2002) Ambient Intelligence. In: Denning PJ (eds) The invisible future: the seamless integration of technology in everyday life. McGraw-Hill, New York, pp 235–250Google Scholar
  2. Abate AF, Nappi M, Riccio D, De Marsico M (2007) Data normalization and fusion in multibiometric systems. In: International conference on distributed multimedia systems, DMS 2007, pp 87–92Google Scholar
  3. Abate AF, Nappi M, Riccio D, De Marsico M (2007) Face, ear and fingerprint: designing multibiometric architectures. In: 14th international conference on image analysis and processing, ICIAP 2007, pp 437–442Google Scholar
  4. Abate AF, De Marsico M, Nappi M, Riccio D (2009) A self-updating multiexpert system for face identification. In: Vento M, Foggia P, Sansone C (eds) Proceedings of the 15-th international conference on image analysis and processing, ICIAP 2009, LNCS 5716Google Scholar
  5. Basten T, Geilen M, de Groot H (2003) Omnia fieri posset. In: Basten T, Geilen M, de Groot H (eds) Ambient intelligence: impact on embedded system design. Kluwer, The NetherlandsGoogle Scholar
  6. Cai D, He X, Han J, Zhang H-J (2006) Orthogonal laplacianfaces for face recognition. IEEE Trans Image Process. 15:3608–3614CrossRefGoogle Scholar
  7. de Man H (2003) Foreword. In: Basten T, Geilen M, H de Groot (eds) Ambient intelligence: impact on embedded system design. Kluwer, The NetherlandsGoogle Scholar
  8. De Marsico M, Riccio D (2008) A new data normalization function for multibiometric contexts: a case study. In: Proceedings of international conference on image analysis and recognition, ICIAR 08, LNCS 5112, pp 1033–1040Google Scholar
  9. De Marsico M, Nappi M, Riccio D, Tortora G (2009) A multiexpert collaborative biometric system for people identification. J Visual Lang Comput 20(2):91–100CrossRefGoogle Scholar
  10. De Marsico M, Nappi M, Riccio D (2010) FARO: face recognition against occlusions and expression variations. IEEE Trans Syst Man Cybern A 40(1):121–132CrossRefGoogle Scholar
  11. He X, Cai D, Yan S, Zhang H-J (2005) Neighborhood preserving embedding. In: Proceedings of IEEE international conference on computer vision, ICCV 2005, vol 2, pp 1208–1213Google Scholar
  12. Hewitt C, Bishop P, Steiger R (1973) A universal modular actor formalism for artificial intelligence. In: International joint conference on artificial intelligence IJCAI 1973, pp 235–245Google Scholar
  13. Hewitt C (1977) Viewing control structures as patterns of passing messages. Artif Intel 8(3):323–364Google Scholar
  14. Martinez AM, Benavente R (1998) The AR face database—CVC technical report no. 24Google Scholar
  15. Ross A, Jain AK, Qian J-Z (2001) Information fusion in biometrics. In: International conference on audio- and video-based biometric person authentication. Springer, Berlin, pp 354–359Google Scholar
  16. Weiser M (1991) The computer for the 21st century. Sci Am 265(3):94–104CrossRefGoogle Scholar
  17. Zhao H, Yuen PC (2008) Incremental linear discriminant analysis for face recognition, IEEE Trans Syst Man Cybern B Cybern 38(1): 210–221zbMATHCrossRefGoogle Scholar
  18. Privaris (2010) http://www.privaris.com/. Accessed 13 January 2010

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Andrea F. Abate
    • 1
    Email author
  • Maria De Marsico
    • 2
  • Daniel Riccio
    • 1
  • Genny Tortora
    • 1
  1. 1.Fisciano (SA)Italy
  2. 2.RomaItaly

Personalised recommendations