Agatha: Multimodal biometric authentication platform in large-scale databases

Abstract

Biometric technologies are each time more demanded for security applications. In this sense, systems for identifying people are gaining popularity, especially in governmental sectors, and forensic applications have climbed to the top of the list when talking about biometrics. However, some problems still remain as cornerstones in identification processes, all of them linked to the length of the databases in which the individual is supposed to be. The speed and the error arc parameters that depend on the number of users in the database and measure the quality of the whole system. In this paper, two different biometric technologies are used in order to increase speed and shorten error rates. Face recognition -normally faster than speaker recognition - is used to select a group of individuals and speaker recognition provides a finer adjustment. Multimodality plays an important role not only reducing the search time but also providing lower error rates. © 2009 Vieweg+Teubner | GWV Fachverlage GmbH, Wiesbaden.