Title :
Eigensteps: A giant leap for gait recognition
Author :
Bours, Patrick ; Shrestha, Raju
Author_Institution :
Norwegian Inf. Security Lab., Gjovik Univ. Coll., Gjovik, Norway
Abstract :
In this paper we will show that using Principle Component Analysis (PCA) on accelerometer based gait data will give a large improvement on the performance. On a dataset of 720 gait samples (60 volunteers and 12 gait samples per volunteer) we achieved an EER of 1.6% while the best result so far, using the Average Cycle Method (ACM), gave a result of nearly 6%. This tremendous increase makes gait recognition a viable method in commercial applications in the near future.
Keywords :
accelerometers; computer vision; gait analysis; gesture recognition; principal component analysis; accelerometer based gait data; average cycle method; eigensteps; gait recognition; principle component analysis; Displays; Educational institutions; Educational technology; Internet; Natural languages; Registers; Search engines; Software systems;
Conference_Titel :
Security and Communication Networks (IWSCN), 2010 2nd International Workshop on
Conference_Location :
Karlstad
Print_ISBN :
978-1-4244-6938-3
Electronic_ISBN :
978-1-4244-6939-0
DOI :
10.1109/IWSCN.2010.5497991
