Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/441607
Title: A System Identification Approach for Video-based Face Recognition University of Maryland
Authors: Aggarwal, Gaurav;Park, College;Chowdhury, Amit K Roy
subject: Science & Technology
Year: 2004
Abstract: The paper poses video-to-video face recognition as a dynamical system identification and classification problem. Video-to-video means that both gallery and probe consists of videos. We model a moving face as a linear dynamical system whose appearance changes with pose. An autore- gressive and moving average (ARMA) model is used to rep- resent such a system. The choice of ARMA model is based on its ability to take care of the change in appearancewhile modeling the dynamics of pose, expression etc. Recognition is performed using the concept of subspace angles to com- pute distances between probe and gallery video sequences. The results obtained are very promising given the extent of pose, expression and illumination variation in the video data used for experiments.
Description: 
URI: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1333732
http://localhost/handle/Hannan/353087
http://localhost/handle/Hannan/441607
ISSN: 769521282
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL540931.pdf128.92 kBAdobe PDF
Title: A System Identification Approach for Video-based Face Recognition University of Maryland
Authors: Aggarwal, Gaurav;Park, College;Chowdhury, Amit K Roy
subject: Science & Technology
Year: 2004
Abstract: The paper poses video-to-video face recognition as a dynamical system identification and classification problem. Video-to-video means that both gallery and probe consists of videos. We model a moving face as a linear dynamical system whose appearance changes with pose. An autore- gressive and moving average (ARMA) model is used to rep- resent such a system. The choice of ARMA model is based on its ability to take care of the change in appearancewhile modeling the dynamics of pose, expression etc. Recognition is performed using the concept of subspace angles to com- pute distances between probe and gallery video sequences. The results obtained are very promising given the extent of pose, expression and illumination variation in the video data used for experiments.
Description: 
URI: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1333732
http://localhost/handle/Hannan/353087
http://localhost/handle/Hannan/441607
ISSN: 769521282
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL540931.pdf128.92 kBAdobe PDF
Title: A System Identification Approach for Video-based Face Recognition University of Maryland
Authors: Aggarwal, Gaurav;Park, College;Chowdhury, Amit K Roy
subject: Science & Technology
Year: 2004
Abstract: The paper poses video-to-video face recognition as a dynamical system identification and classification problem. Video-to-video means that both gallery and probe consists of videos. We model a moving face as a linear dynamical system whose appearance changes with pose. An autore- gressive and moving average (ARMA) model is used to rep- resent such a system. The choice of ARMA model is based on its ability to take care of the change in appearancewhile modeling the dynamics of pose, expression etc. Recognition is performed using the concept of subspace angles to com- pute distances between probe and gallery video sequences. The results obtained are very promising given the extent of pose, expression and illumination variation in the video data used for experiments.
Description: 
URI: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1333732
http://localhost/handle/Hannan/353087
http://localhost/handle/Hannan/441607
ISSN: 769521282
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL540931.pdf128.92 kBAdobe PDF