Chapter

Handbook of Biometric Anti-Spoofing

Part of the series Advances in Computer Vision and Pattern Recognition pp 185-204

Date:

Evaluation Methodologies

  • Ivana ChingovskaAffiliated withIdiap Research Institute Email author 
  • , André AnjosAffiliated withIdiap Research Institute
  • , Sébastien MarcelAffiliated withIdiap Research Institute

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Anti-spoofing systems, regardless of the technique, biometric mode or degree of independence of external equipment, are most commonly treated as binary classification systems. The two classes that they differentiate are genuine accesses and spoofing attacks. From this perspective, their evaluation is equivalent to the established evaluation standards for the binary classification systems. However, the anti-spoofing systems are designed to operate in conjunction with recognition systems and as such can affect their performance. From the point of view of a recognition system, the spoofing attacks are a separate class that they need to detect and reject. As the problem of spoofing attacks detection grows to this pseudo-ternary status, the evaluation methodologies for the recognition systems need to be revised and updated. Consequentially, the database requirements for spoofing databases become more specific. The focus of this chapter is the task of biometric verification and its scope is threefold: first, it gives the definition of the spoofing detection problem from the two perspectives. Second, it states the database requirements for a fair and unbiased evaluation. Finally, it gives an overview of the existing evaluation techniques for anti-spoofing systems and verification systems under spoofing attacks.