GMM-UBM based Person Verification using footfall signatures for Smart Home Applications

In this paper, we propose a novel person verification system based on footfall signatures using Gaussian Mixture Model-Universal Background Model (GMM-UBM). Ground vibration generated by footfall of an individual is used as a biometric modality. We conduct extensive experiments to compare the proposed technique with various baselines of footfall based person verification. The system is evaluated on an indigenous dataset containing 7750 footfall events of twenty subjects. Different scenarios are created for analyzing the robustness of the system by varying the number of registered and non registered users. We obtained a Half Total Error Rate (HTER) of 7% with the proposed model and achieved an overall performance gain of ~46% and ~33% over Support Vector Machine (SVM) and Convolution Neural Network (CNN) based techniques respectively. Experimental results validate the efficacy of the proposed algorithms.