Optimization of thresholds in serial multimodal biometric systems

Abstract

Multimodal biometric verification systems use information from several biometric modalities to verify an identity of a person. The false acceptance rate (FAR) and false rejection rate (FRR) are metrics generally used to measure the performance of such systems.In this paper we propose a novel approach to determine the upper and lower acceptance thresholds in sequential multimodal biometric matching, in such a way that the expected values of FAR and FRR for the entire system are minimized. We linearize locally the score distributions of both genuine users and impostors using the least squares method, and derive formulas for the approximated FAR and FRR for each matcher. Further, we aim to minimize both probabilities for entire processing chain. In order to find the best compromise between them, we analyze the efficient solutions to the associated bi-objective programming problem.The results of our experiments are also reported in the paper. They showed a good performance of the sequential multiple biometric matching system based on optimized thresholds comparing with the widely adopted parallel fusion multimodal biometric systems.

Continuous Distribution Approximation and Thresholds Optimization in Serial Multi-Modal Biometric Systems

“…We solved the non-linear optimization problem numerically. The paper is an extension of [15], where the linear approximation of the biometric scores based on the least squares method was Continuous Distribution Approximation and Thresholds Optimization in Serial Multi-Modal Biometric Systems 733 introduced, and the optimization model was given biometric systems with 2 modalities. One of the advantages of the new approach is the fact that it relays on less input parameters than the previous method.…”

“…In this section we briefly present the local linearization approach used in [15] to approximate the areas involved in Formulas (1) and (2). The discrete score distributions of both genuine users and impostors were approximated using the least squares method.…”

“…In [15] the theoretical presentation of the approach was restricted to bi-modal systems, and quadratic expressions with respect to the thresholds x 1 , x 2 and x 3 , were derived. Combining them, a polynomial expressions of degree 4 were obtained, for the objective functions of the optimization model.…”

“…Combining them, a polynomial expressions of degree 4 were obtained, for the objective functions of the optimization model. The bi-objective optimization problem formulated in [15] is a particular case of Model (3), obtained for N = 2. For a general multi-modal matching system with N modalities, the expressions of the objective functions obtained by the linear approximation are polynomials of degree 2N .…”

“…In order to test the performance of our method we organized the experiments, as in [15]. First, the input data, necessary to construct the score distributions, were randomly generated according to the rules that made them proper data for biometric tests.…”