Experimental Evaluation of Matching-Score Normalization Techniques on Different Multimodal Biometric Systems

Author

Ribaric, Slobodan ; Fratric, Ivan

Author_Institution

Fac. of Electr. Eng. & Comput., Zagreb Univ.

fYear

2006

fDate

16-19 May 2006

Firstpage

498

Lastpage

501

Abstract

The goal of this work is the experimental evaluation of matching-score normalization techniques for the following three multimodal biometric systems: a verification system based on the fusion of face and palmprint principal line features, an identification system based on eigenfingers and finger-geometry, and an identification system based on eigenpalm and eigenfinger features. The following normalization techniques are tested: Bayes-based normalization and several heuristic techniques (min-max, z-score, median-MAD, double-sigmoid, tanh, and piecewise-linear). The results of evaluation are represented by means of system performance (expressed by ROC, EER and minTER) and F-statistics

Keywords

Bayes methods; face recognition; feature extraction; fingerprint identification; minimax techniques; piecewise linear techniques; statistical analysis; Bayes-based normalization; EER; F-statistics; ROC; different multimodal biometric systems; double-sigmoid technique; eigenfinger feature identification system; eigenpalm identification system; experimental evaluation; face principal line features verification system; finger-geometry identification system; matching-score normalization techniques; median-MAD technique; min-max technique; minTER; palmprint principal line features verification system; piecewise-linear technique; tanh technique; z-score technique; Biometrics; Biosensors; Databases; Error analysis; Fuses; Impedance matching; Sensor fusion; Statistical distributions; System performance; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrotechnical Conference, 2006. MELECON 2006. IEEE Mediterranean

Conference_Location

Malaga

Print_ISBN

1-4244-0087-2

Type

conf

DOI

10.1109/MELCON.2006.1653147

Filename

1653147