In this paper we describe a novel method for gait based identity verification based on Bayesian classification. The verification task is reduced to a two class problem (Client or Impostor) with logistic functions constructed to provide probability estimates of intra-class (Client) and inter-class (Impostor) likelihoods. These likelihoods are combined using Bayes rule and thresholded to provide a decision boundary. Since the outputs of the classifier are probabilities they are particularly well suited for use without modification in classifier fusion schemes. On tests using 1664 examples from 100 clients and 100 impostors the Bayesian method achieved an equal error rate of 7.3%. The improvement over a Euclidean distance classifier was shown to be statistically significant at the 5% level using McNemar's test.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Gait Verification Using Probabilistic Methods


    Contributors:


    Publication date :

    2005-01-01


    Size :

    332424 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Safety Verification for Probabilistic Hybrid Systems

    Zhang, L. / She, Z. / Ratschan, S. et al. | British Library Online Contents | 2012


    Probabilistic Verification of Spacecraft Acquisition Sequence Using Polynomial Chaos Expansion

    Izquierdo Serra, Mario / Martin, Maurice / Delchambre, Simon et al. | AIAA | 2025


    Gait recognition using a few gait frames.

    Yao, L / Kusakunniran, W / Wu, Q et al. | BASE | 2021

    Free access

    Automatic gait event detection in pathologic gait using an auto-selection approach among concurrent methods

    Cardoso Fonseca, Mickaël / Dumas, Raphaël / Armand, Stéphane | BASE | 2022

    Free access