User authentication method and implementation using a three-axis accelerometer

Abstract

The rapid growth of accelerometer use on consumer electronics has brought an opportunity for unique user authentication. We present an efficient recognition algorithm for such interaction using a single three-axis accelerometer. Unlike common user authentication methods which require memorizing complex phrases and are prone to physical attacks, our method requires a single training sample for a gesture pattern which allows users to authenticate themselves in a fast and secure manner. Our work imitates the use of physical handwritten signatures, which are a common authentication technique and tries to integrate them in a digital form. The presented method aims at providing easy to remember personalized gesture passwords through the muscle memory ability of the human body. An implementation using the wii remote sensor, along with identification results for different users is presented as a proof of concept. © 2010 Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.