Towards understanding the uniqueness of gait biometric

Abstract

In this paper, we provide some insights towards understanding the uniqueness of gait (ankle motion) by relating the discriminativeness of gait to the shoe type, direction of the motion and gait cycle. For analysis, we use gait samples of the people when all of them walk with the same specific types of footwear, thus eliminating the randomness (noise) introduced by the shoe variability. We collect gait using an accelerometer sensor, which is attached to the ankle of the person. The accelerometer records ankle motion in three directions: up-down, forward-backward and sideway. The verification method is based on detecting and averaging gait cycles in acceleration signal. Our gait data set consists of 480 samples from 30 persons. Each person walked with the 4 different types of footwear. Our analysis reveal that heavy footwear reduces the discrimination and the sideway motion of the foot has the most discriminating power compared to the up-down or forward-backward directions of the motion. Furthermore, various gait cycle parts contribute differently to the recognition performance. In addition, our analysis confirm that recognition performance can significantly decrease when the test and template samples are obtained using different shoe types. The recognition performance in terms of EER was in the range of 5%-18.3% mainly depending on the shoe type and the direction of motion.