We propose a person verification method using behavioral patterns of human upper body motion. Behavioral\r\npatterns are represented by three-dimensional features obtained from a time-of-flight camera. We take a statistical\r\napproach to model the behavioral patterns using Gaussian mixture models (GMM) and support vector machines. We\r\nemploy the maximum likelihood linear regression adaptation method to estimate GMM parameters with a limited\r\namount of data. Experimental results show that it reduced by 28.6% the relative equal error rates from a system using\r\nthe maximum likelihood estimation with 25 samples per subject. We also demonstrate that the proposed approach is\r\nrobust against variations in body motion over time.
Loading....