In this paper, we would like to disseminate surprisingly positive results we obtained by using a framework for generating impostor features in the context of training user-specific models in accelerometric gait biometric user verification. We propose that we directly sample from a poorly fit Universal Background – Gaussian Mixture Model (UBM-GMM) to generative negative class features, which on the face of it, seems like an unreasonable proposal, and combining these with the positive class user-enrollment features to train local user-specific shallow classifiers. Through empirical analysis on the state-of-the-art dataset, we showcase that this simple approach outperforms the classical UBM-GMM approach with or without score normalization, a result that was rather unexpected.
SIMUni: Sampling Impostors from Misfit Universal Background Models in accelerometric gait biometric verification
By Vinay Prabhu October 10, 2018