Cross-Pocket Gait Recognition

Abstract

Gait authentication using a mobile phone's acceleration sensor offers a convenient, user-friendly and subtle procedure of authenticating individuals to their mobile phone. This study analyses the possibility of cross-pocket gait recognition, which means creating the reference and the probe with the accelerometer sensor in different trouser pockets (left and right). The results of our analysis show that there is a significant performance degradation when comparing same-pocket gait recognition with cross-pocket gait recognition. In our analysis we have used a new distance metric that shows to give good (same-pocket) performance results compared to known analysis methods. We have also shown that a multi-reference template can give excellent performance without any performance degradation for cross-pocket gait recognition.