Home >

news Help

Publication Information


Title
Japanese: 
English:Statistical Person Verification Using Behavioral Patterns from Complex Human Motion 
Author
Japanese: Gomez Caballero Felipe, 篠崎 隆宏, 古井 貞熙, 篠田 浩一.  
English: Felipe Gomez-Caballero, Takahiro Shinozaki, Sadaoki Furui, Koichi Shinoda.  
Language English 
Journal/Book name
Japanese: 
English:New Trends in Image Analysis and Processing ICIAP 2013 
Volume, Number, Page         pp. 550-558
Published date Sept. 9, 2013 
Publisher
Japanese: 
English: 
Conference name
Japanese: 
English:New Trends in Image Analysis and Processing ICIAP 2013 
Conference site
Japanese: 
English:Napoli 
File
DOI http://dx.doi.org/10.1007/978-3-642-41190-8_60
Abstract We propose a person verification method based on behav- ioral patterns from complex human m ovements. Behavioral patterns are represented by anthropometric and kinematic features of human body motion acquired by a Kinect RGBD sensor. We focus on complex move- ments to demonstrate that independent and rhythmic movement of body parts carries a significant amount of behavioral information. We take a statistical approach by Gaussian mixture models to model the individual behavioral patterns. We demonstrate that subject-preferred movements are more robust against forgery attacks and variations over time than predetermined subject-independent movements. The obtained equal er- ror rate was 15.7% when using subject-preferred movements and 27.3% when using a predefined sequence of movements.

©2007 Tokyo Institute of Technology All rights reserved.