Sensor fusion for a biometric system using gait
ConferencePaper (Artikel, die in Tagungsbänden erschienen sind)
ID 69716
Author(s) Cattin, PC; Zlatnik, D; Borer, R
Author(s) at UniBasel Cattin, Philippe Claude
Year 2001
Title Sensor fusion for a biometric system using gait
Book title (Conference Proceedings) Conference documentation / International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2001 : August 20 - 22, 2001, Kongresshaus, Baden-Baden, Germany
Place of Conference -
Publisher VDI/VDE-GMA
Place of Publication Düsseldorf
Pages S. 233-238
Keywords Biometry
Abstract We consider a multimodal biometric system which authenticates people based on their gait. Computationally efficient techniques were developed to extract characteristic gait features from ground reaction force and video data of the walking subject. Specifically, the data consists of one classifier based on the ground reaction force and three based on visual features. A new variant of the generalized principal component analysis is used to efficiently reduce data dimensionality and to optimize class separability. A technique based on the Bayes risk criterion subsequently integrates the multiple classifiers. The proposed multimodal approach significantly increases recognition robustness and reliability. Experimental results showed an equal error rate of less than 0.3% which makes the method applicable for medium security applications.
Full Text on edoc No
Digital Object Identifier DOI 10.1109/MFI.2001.1013540
ISI-Number WOS:000176703400040
Document type (ISI) inproceedings

MCSS v5.8 PRO. 0.435 sec, queries - 0.000 sec ©Universität Basel  |  Impressum   |