Mobile Lightweight Wireless Systems. Second International ICST Conference, MOBILIGHT 2010, Barcelona, Spain, May 10-12, 2010, Revised Selected Papers

Research Article

“User Authentication Method and Implementation Using a Three-Axis Accelerometer”

Download
812 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-16644-0_18,
        author={Alexandros Zaharis and Adamantini Martini and Panayotis Kikiras and George Stamoulis},
        title={“User Authentication Method and Implementation Using a Three-Axis Accelerometer”},
        proceedings={Mobile Lightweight Wireless Systems. Second International ICST Conference, MOBILIGHT 2010, Barcelona, Spain, May 10-12, 2010, Revised Selected Papers},
        proceedings_a={MOBILIGHT},
        year={2012},
        month={10},
        keywords={gesture recognition three axis accelerometer sensor user authentication},
        doi={10.1007/978-3-642-16644-0_18}
    }
    
  • Alexandros Zaharis
    Adamantini Martini
    Panayotis Kikiras
    George Stamoulis
    Year: 2012
    “User Authentication Method and Implementation Using a Three-Axis Accelerometer”
    MOBILIGHT
    Springer
    DOI: 10.1007/978-3-642-16644-0_18
Alexandros Zaharis1,*, Adamantini Martini1,*, Panayotis Kikiras1,*, George Stamoulis1,*
  • 1: University of Thessaly
*Contact email: alzahari@inf.uth.gr, admartin@inf.uth.gr, kikirasp@inf.uth.gr, georges@inf.uth.gr

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.