Probabilistic Fusion of Gait Features for Biometric Verification


Bazin, Alex I., Middleton, Lee and Nixon, Mark S. (2005) Probabilistic Fusion of Gait Features for Biometric Verification. At Eighth International Conference of Information Fusion, 2005., Philadelphia, PA, USA, 25 - 29 Jul 2005.

Download

[img] PDF
Download (373Kb)

Description/Abstract

This paper examines the fusion of various gait metrics in a probabilistic framework. Using three gait modalities we describe a process for determining probabilistic match scores using intra and inter-class variance models together with Bayes rule. We then propose to fuse these modalities based on established fusion rules with weights determined in a principled manner. Using a large publicly available database we show improvements through fusion, both in terms of verification accuracy and class separation; we also consider how the accuracy of each modality and the correlation between the modalities affects overall performance.

Item Type: Conference or Workshop Item (Speech)
Additional Information: Event Dates: 25th-29th July 2005
Keywords: Fusion, Biometrics, Logistic function, Bayesian
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Comms, Signal Processing & Control
Faculty of Physical Sciences and Engineering > Electronics and Computer Science
Faculty of Physical Sciences and Engineering > Electronics and Computer Science > IT Innovation Centre
ePrint ID: 261148
Date Deposited: 11 Aug 2005
Last Modified: 27 Mar 2014 20:04
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/261148

Actions (login required)

View Item View Item