Genetic Programming for Multibiometrics

TL;DR

This paper introduces a genetic programming approach to optimize score level fusion functions in multibiometric systems, achieving comparable or superior performance to existing linear and non-linear classifiers across benchmark datasets.

Contribution

The paper presents a novel genetic programming method for deriving score fusion functions in multibiometric authentication, outperforming traditional linear and SVM-based methods.

Findings

Genetic programming-based fusion functions match or outperform existing methods.

Validated on three benchmark biometric datasets.

Achieves improved accuracy with adaptable fusion functions.

Abstract

Biometric systems suffer from some drawbacks: a biometric system can provide in general good performances except with some individuals as its performance depends highly on the quality of the capture. One solution to solve some of these problems is to use multibiometrics where different biometric systems are combined together (multiple captures of the same biometric modality, multiple feature extraction algorithms, multiple biometric modalities...). In this paper, we are interested in score level fusion functions application (i.e., we use a multibiometric authentication scheme which accept or deny the claimant for using an application). In the state of the art, the weighted sum of scores (which is a linear classifier) and the use of an SVM (which is a non linear classifier) provided by different biometric systems provide one of the best performances. We present a new method based on the use of genetic programming giving similar or better performances (depending on the complexity of the database). We derive a score fusion function by assembling some classical primitives functions (+, *, -, ...). We have validated the proposed method on three significant biometric benchmark datasets from the state of the art.