Gait Authentication

Authors

  • Shruti Saiparia Computer Science & Engineering, SLTIET
  • Kuldeep Jindani Computer Science & Engineering, SLTIET
  • Jay Tevani Computer Science & Engineering, SLTIET

Keywords:

Biometric authentication, Gait authentication, Histogram, Cycle-length, Prototype sensor mat

Abstract

This paper describes Gait Authentication which is an emerging biometric technology which involves people
being identified purely through the analysis of the way they walk. It has attracted interest as a method of identification
because it is non-invasive and does not require the subject’s cooperation. This paper presents approaches of Biometric
gait recognition and security and challenges of it as well. There are three types of Biometric gait recognition: machine
vision, wearable sensor and floor sensor. Gait patterns are extracted from physical device which is attached with lower
leg. From output of device acceleration in three directions are noticed: vertical, forward-backward and sideways motion
of lower leg. Two different methods are used for authentication: histogram and cycle length. In histogram equal error rate
is 5% and in cycle length it is 9%.This paper contain cycle length detection. In this paper we have discussed on spoof
attacks on Gait authentication systems as well.

Published

2016-12-31

How to Cite

Shruti Saiparia, Kuldeep Jindani, & Jay Tevani. (2016). Gait Authentication. International Journal of Advance Research in Engineering, Science & Technology, 3(13), -. Retrieved from http://ijarest.com/index.php/ijarest/article/view/2195