Person Identification Based on Hand Tremor Characteristics

TL;DR

This paper proposes a novel biometric identification method using hand tremor characteristics captured by smartphone sensors, achieving 76% accuracy in distinguishing 17 individuals in real-life scenarios.

Contribution

Introduces a new biometric measure based on hand tremor, utilizing Fourier analysis and machine learning for user identification with smartphones.

Findings

Achieved 76% accuracy in identifying 17 users.

Effectively extracted tremor data using weighted Fourier linear combiner.

Demonstrated feasibility of tremor-based biometrics in real-world conditions.

Abstract

A plethora of biometric measures have been proposed in the past. In this paper we introduce a new potential biometric measure: the human tremor. We present a new method for identifying the user of a handheld device using characteristics of the hand tremor measured with a smartphone built-in inertial sensors (accelerometers and gyroscopes). The main challenge of the proposed method is related to the fact that human normal tremor is very subtle while we aim to address real-life scenarios. To properly address the issue, we have relied on weighted Fourier linear combiner for retrieving only the tremor data from the hand movement and random forest for actual recognition. We have evaluated our method on a database with 10 000 samples from 17 persons reaching an accuracy of 76%.