Inertial Gait-based Person Authentication Using Siamese Networks

Gait-based person authentication using smartphones and wearable devices has attracted a lot of attention in recent years due to its unobtrusive nature and the widespread inertial sensors embedded in such devices. While traditional methods of authentication relied on hand-crafted feature extraction tailored for specific conditions, recent deep learning algorithms have been used to automatically discover hidden features and patterns in the raw data. However, current deep learning methods of gait authentication are not portable. They train models to classify a specific user as legitimate and the rest as imposters without being able to change that user to a different one without retraining the model from scratch. Furthermore, they are impractical, since they require a large volume of data for each class to train properly. In this work, we propose using a Siamese Network-based model which (1) Can be trained using only a few samples per subject. (2) Automatically extract features from raw inertial data. (3) Once trained, can authenticate any new user given only one gait instance of that new user. We apply our model to three publicly available datasets and show that it can achieve very promising results. For example, our model achieves 3.42% EER on the world's largest inertial gait dataset (OU-ISIR) after training on raw data of 592 subjects and testing on the raw data of completely different 78 subjects, where each subject provided an average of 5.9 seconds of gait data only. We show some performance analysis on different architectural variations. and finally, we show the ability of our model to generalize to new unseen datasets using transfer learning.