Biometric Hash based on Statistical Features of Online Signatures
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Communications of the ACM - Multimodal interfaces that flex, adapt, and persist
Biometric User Authentication for IT Security: From Fundamentals to Handwriting (Advances in Information Security)
Handwriting verification - Comparison of a multi-algorithmic and a multi-semantic approach
Image and Vision Computing
A generalized net model of biometric access-control system
ACMOS'07 Proceedings of the 9th WSEAS international conference on Automatic control, modelling and simulation
The use of static biometric signature data from public service forms
BioID'11 Proceedings of the COST 2101 European conference on Biometrics and ID management
Semantic fusion for biometric user authentication as multimodal signal processing
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
Study of applicability of virtual users in evaluating multimodal biometrics
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
Hi-index | 0.00 |
In this paper a novel fusion approach for combining voice and online signature verification will be introduced. While the matching algorithm for the speaker identification modality is based on a single Gaussian Mixture Model (GMM) algorithm, the signature verification strategy is based on four different distance measurement functions, combined by multialgorithmic fusion. Together with a feature extraction method presented in our earlier work, the Biometric Hash algorithm, they result in four verification experts for the handwriting subsystem. The fusion results of our new subsystem on the multimodal level are elaborated by enhancements to a system, which was previously introduced by us for biometric authentication in HCI scenarios. Tests have been performed on identical data sets for the original and the enhanced system and the first results presented in this paper show that an increase of recognition accuracy can be achieved by our new multialgorithmic approach for the handwriting modality.