Chapter 1 provided a high-level overview of the field of biometric analysis. This chapter provides three different walk-through examples to build an understanding of biometric matching “from the ground up”. The aim is to demystify some of the calculation of biometric statistics and explain clearly how the different performance measures are derived and interpreted. The concepts introduced in this chapter are repeated in more detail in the relevant sections of Part II.

A biometric algorithm at its core is a comparison system, taking biometric samples as input, and producing as its output a measure of similarity. This similarity (called a matching score) is particular to an algorithm and is the fundamental output of the matching process. No matter the advances in algorithms, sensors or modalities over the coming years, the fundamentals of assessing scores introduced in this chapter will remain the same.

The goals of this chapter are to:
  • Examine three different scenarios, two authentication (Sect. 2.1 and 2.2) and one identification (Sect. 2.3).

  • Introduce standard biometric terms, consistent with the ISO definitions, in the context of these examples.

  • Provide a step-by-step introduction to how the matching process works in both authentication and identification.

  • Explain with worked examples how to derive common biometric graphs (Sect. 2.2.3).

  • Look at the basics of using biometrics to detect fraud (Sect. 2.3.3).


Legitimate User Biometric Authentication False Reject Rate Face Recognition Algorithm Alarm Threshold 
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.
    O’Toole, A.J., Phillips, P.J., Jiang, F., Ayyad, J., Penard, N., Abdi, H.: Face recognition algorithms surpass humans matching faces over changes in illumination.In: IEEE Transactions on Pattern and Machine Intelligence, vol. 29, pp.1642–1646 (2007)CrossRefGoogle Scholar
  2. 2.
    Phillips, P.J.,Wechsler, H., Huang, J., Rauss, P.: The FERET database and evaluation procedure for face recognition algorithms (1998)Google Scholar

Copyright information

© Springer-Verlag US 2009

Personalised recommendations