Tampere University of Technology

TUTCRIS Research Portal

Person identification from actions based on dynemes and discriminant learning

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication2013 International Workshop on Biometrics and Forensics, IWBF 2013
DOIs
Publication statusPublished - 2013
Publication typeA4 Article in a conference publication
Event1st International Workshop on Biometrics and Forensics, IWBF 2013 - Lisbon, Portugal
Duration: 4 Apr 20135 Apr 2013

Conference

Conference1st International Workshop on Biometrics and Forensics, IWBF 2013
CountryPortugal
CityLisbon
Period4/04/135/04/13

Abstract

In this paper we present a view-independent person identification method exploiting motion information. A multi-camera setup is used in order to capture the human body during action execution from different viewing angles. The method is able to incorporate several everyday actions in person identification. A comparative study of the discriminative ability of different actions for person identification is provided, denoting that several actions, except walk, can be exploited for person identification.

Keywords

  • Action-based person identification, Classification results fusion, Discriminant learning, Dyneme video representation