Person identification from actions based on dynemes and discriminant learning

Author

Iosifidis, Alexandros ; Tefas, Anastasios ; Pitas, Ioannis

Author_Institution

Dept. of Inf., Aristotle Univ. of Thessaloniki, Thessaloniki, Greece

fYear

2013

fDate

4-5 April 2013

Firstpage

1

Lastpage

4

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

cameras; image motion analysis; learning (artificial intelligence); object recognition; video signal processing; discriminant learning; discriminative ability; dyneme video representation; motion information; multicamera setup; view-independent person identification method; viewing angle; Cameras; Databases; Gait recognition; Nickel; Training; Vectors; Visualization; Action-based person identification; Classification results fusion; Discriminant learning; Dyneme video representation;

fLanguage

English

Publisher

ieee

Conference_Titel

Biometrics and Forensics (IWBF), 2013 International Workshop on

Conference_Location

Lisbon

Print_ISBN

978-1-4673-4987-1

Type

conf

DOI

10.1109/IWBF.2013.6547320

Filename

6547320