A Simple Score Normalization Technique for Multimodal Biometric Authentication

In multimodal biometric authentication, the unimodal scores are used to produce the final decision, following the score fusion approach. Researchers have often decomposed the score fusion problem into two steps: a 'score normalisation' and a 'fusion' step. This paper shows the fusion studies and experiments carried out by the authors. A special effort has been made to manipulate unimodal scores prior to their fusion. We propose a score normalisation technique consisting of a bilinear transformation applied to the independent scores, so that the unimodal thresholds become uniform and the data closest to these thresholds have greater separation between them. Our results show that this procedure improves the final results when compared with classic normalisation procedures. Several score fusion strategies were used in the experiments. All the experiments were carried out using the same scores, that have been obtained through the processing of three unimodal verification systems on three independent biometrical databases

A Simple Score Normalization Technique for Multimodal Biometric Authentication Articles